SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.14159 · 2024

Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks

arXiv · PDF · Open in the Atlas

Code that ran

15 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 14 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2401.14159.json · badge: /api/ran/2401.14159.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
idea-research/groundingdino canonical (classifier label)
classifier basis: census
15 ran · 0 no recorded run
FunctionStatusWhere it lives
convert_to_xywh Ran
ran, honoured the contract we drafted
idea-research/groundingdino/groundingdino/datasets/cocogrounding_eval.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yuhangzang/contextdet, is pointer only (licence: NOASSERTION) · get_code("f31a58bf6457ced5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from yuhangzang/contextdet, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

create_dummy_class Ran
ran; our contract draft was wrong, not the code
idea-research/groundingdino/groundingdino/models/GroundingDINO/ms_deform_attn.py
code served (permissive licence) · get_code("47b44963c80f19d1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned _DummyMetaClass. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

ARGS = {
    'klass': 'MyClass',
    'dependency': 'some_package',
    'message': 'Please install some_package to use MyClass'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type _DummyMetaClass — a _DummyMetaClass output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create_dummy_func Ran
ran; our contract draft was wrong, not the code
idea-research/groundingdino/groundingdino/models/GroundingDINO/ms_deform_attn.py
code served (permissive licence) · get_code("5f2ed565ef0da8fc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Test with a single dependency (string)
func_name = "some_function"
single_dependency = "missing_library"
message_text = "Please install the missing_library package"

# Test with multiple dependencies (list)
multiple_dependencies = ["lib1", "lib2", "lib3"]

ARGS = {
    "func": func_name,
    "dependency": single_dependency,
    "message": message_text,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
crop Ran
ran; our contract draft was wrong, not the code
idea-research/groundingdino/groundingdino/datasets/transforms.py
code served (permissive licence) · get_code("5012a0e0d69e1a96")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torchvision.transforms.functional as F
from PIL import Image
import numpy as np

torch.manual_seed(0)

# Create a small PIL image for testing
image = Image.new('RGB', (100, 100), color='red')

# Create target dict with boxes and masks
target = {
    'boxes': torch.tensor([[10.0, 10.0, 50.0, 50.0], [30.0, 30.0, 80.0, 80.0]], dtype=torch.float32),
    'labels': torch.tensor([1, 2], dtype=torch.int64),
    'area': torch.tensor([1600.0, 2500.0], dtype=torch.float32),
    'iscrowd': torch.tensor([0, 0], dtype=torch.int64),
    'masks': torch.randint(0, 2, (2, 100, 100), dtype=torch.uint8),
    'size': torch.tensor([100, 100]),
}

# Define region as (top, left, height, width) for cropping
region = (20, 20, 60, 60)

ARGS = {
    'image': image,
    'target': target,
    'region': region,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
evaluate Ran
ran; our contract draft was wrong, not the code
idea-research/groundingdino/groundingdino/datasets/cocogrounding_eval.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yuhangzang/contextdet, is pointer only (licence: NOASSERTION) · get_code("fe0ddcc2d420c9a0")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from yuhangzang/contextdet, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

func_attention Ran
ran; our contract draft was wrong, not the code
idea-research/groundingdino/groundingdino/models/GroundingDINO/fuse_modules.py
code served (permissive licence) · get_code("b749226a635f2b59")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# query: (n_context, queryL, d) - shape (2, 3, 4)
# context: (n_context, sourceL, d) - shape (2, 5, 4)
query = torch.randn(2, 3, 4)
context = torch.randn(2, 5, 4)

ARGS = {
    'query': query,
    'context': context,
    'smooth': 1,
    'raw_feature_norm': 'softmax',
    'eps': 1e-08
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
gen_encoder_output_proposals Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
idea-research/groundingdino/groundingdino/models/GroundingDINO/utils.py
code served (permissive licence) · get_code("0afe797420c1a312")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 4, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch import nn

torch.manual_seed(0)

# Parameters for the function
batch_size = 2
d_model = 4
num_levels = 3

# Create spatial shapes: (height, width) for each level
# Using distinct sizes for probing
spatial_shapes = torch.tensor([
    [8, 6],   # level 0: 8x6
    [4, 3],   # level 1: 4x3
    [2, 2],   # level 2: 2x2
], dtype=torch.int64)

# Calculate total spatial dimension
total_spatial = int((spatial_shapes[:, 0] * spatial_shapes[:, 1]).sum().item())

# Create memory tensor: (batch_size, sum(hw), d_model)
memory = torch.randn(batch_size, total_spatial, d_model)

# Create memory_padding_mask: (batch_size, sum(hw))
# False means valid, True means padding
memory_padding_mask = torch.zeros(batch_size, total_spatial, dtype=torch.bool)
# Mark some positions as padded
memory_padding_mask[0, 40:] = True
memory_padding_mask[1, 45:] = True

# Create learnedwh as a learnable parameter tensor with shape (2,)
learnedwh = torch.randn(2)

ARGS = {
    'memory': memory,
    'memory_padding_mask': memory_padding_mask,
    'spatial_shapes': spatial_shapes,
    'learnedwh': learnedwh,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 4, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
generate_masks_with_special_tokens Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
idea-research/groundingdino/groundingdino/models/GroundingDINO/bertwarper.py
code served (permissive licence) · get_code("2015623fec3ac3bc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a minimal tokenizer stand-in
class MinimalTokenizer:
    pass

tokenizer = MinimalTokenizer()

# Create tokenized dict with input_ids tensor
# Shape: [bs=2, num_token=4]
input_ids = torch.tensor([
    [101, 102, 103, 104],  # batch 0
    [101, 105, 106, 104]   # batch 1
], dtype=torch.long)

tokenized = {
    'input_ids': input_ids
}

# Special tokens list - these are token IDs that appear in input_ids
special_tokens_list = [101, 104]

ARGS = {
    'tokenized': tokenized,
    'special_tokens_list': special_tokens_list,
    'tokenizer': tokenizer
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
generate_masks_with_special_tokens_and_transfer_map Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
idea-research/groundingdino/groundingdino/models/GroundingDINO/bertwarper.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from AIoT-Lab-BKAI/AR-Detector, is pointer only (licence: NONE) · get_code("10c7b3ef85aca8d6")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from AIoT-Lab-BKAI/AR-Detector, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_sine_pos_embed Ran
ran; our contract draft was wrong, not the code
idea-research/groundingdino/groundingdino/models/GroundingDINO/utils.py
code served (permissive licence) · get_code("888d746fcc2165d1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (2, 3, 256) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import math

torch.manual_seed(0)

# Create a position tensor with shape [..., n] where n=2 (x, y coordinates)
# Using batch size 2, and 2 position coordinates
pos_tensor = torch.randn(2, 3, 2, dtype=torch.float32)

ARGS = {
    "pos_tensor": pos_tensor,
    "num_pos_feats": 128,
    "temperature": 10000,
    "exchange_xy": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 3, 256) — shape (2, 3, 256) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
hflip Ran
ran; our contract draft was wrong, not the code
idea-research/groundingdino/groundingdino/datasets/transforms.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from kellyiss/situformer, is pointer only (licence: NONE) · get_code("9be9e658b5bd688a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from kellyiss/situformer, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

l1norm Ran
ran; our contract draft was wrong, not the code
idea-research/groundingdino/groundingdino/models/GroundingDINO/fuse_modules.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Paranioar/SGRAF, is pointer only (licence: NONE) · get_code("b943467457f9825d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Paranioar/SGRAF, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

l2norm Ran
ran; our contract draft was wrong, not the code
idea-research/groundingdino/groundingdino/models/GroundingDINO/fuse_modules.py
code served (permissive licence) · get_code("48cff1d6632b7025")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small tensor with distinct dimensions for testing
# Shape: (batch=2, features=4)
X = torch.randn(2, 4)

# The function uses dim parameter to specify which dimension to normalize along
dim = 1

# eps is already provided with a default value, but we can override it
eps = 1e-08

ARGS = {
    "X": X,
    "dim": dim,
    "eps": eps
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
multi_scale_deformable_attn_pytorch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
idea-research/groundingdino/groundingdino/models/GroundingDINO/ms_deform_attn.py
code served (permissive licence) · get_code("be924e54ed79731b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (2, 3, 32) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# Parameters
bs = 2  # batch size
num_heads = 4
embed_dims = 8
num_queries = 3
num_levels = 2
num_points = 5

# value_spatial_shapes: tensor of shape (num_levels, 2) with [H, W] for each level
value_spatial_shapes = torch.tensor([
    [4, 5],  # level 0: 4x5
    [2, 3]   # level 1: 2x3
])

# Compute total spatial positions
total_spatial_positions = (value_spatial_shapes[:, 0] * value_spatial_shapes[:, 1]).sum().item()

# value: shape (bs, total_spatial_positions, num_heads, embed_dims)
value = torch.randn(bs, total_spatial_positions, num_heads, embed_dims)

# sampling_locations: shape (bs, num_queries, num_heads, num_levels, num_points, 2)
# Each location is normalized to [-1, 1]
sampling_locations = torch.rand(bs, num_queries, num_heads, num_levels, num_points, 2) * 2 - 1

# attention_weights: shape (bs, num_queries, num_heads, num_levels, num_points)
attention_weights = torch.rand(bs, num_queries, num_heads, num_levels, num_points)

ARGS = {
    "value": value,
    "value_spatial_shapes": value_spatial_shapes,
    "sampling_locations": sampling_locations,
    "attention_weights": attention_weights
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 3, 32) — shape (2, 3, 32) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
sigmoid_focal_loss Ran
ran; our contract draft was wrong, not the code
idea-research/groundingdino/groundingdino/models/GroundingDINO/utils.py
code served (permissive licence) · get_code("23eb1c50e6bb2ba5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create small tensors for inputs and targets
batch_size = 2
num_classes = 4

inputs = torch.randn(batch_size, num_classes, requires_grad=True)
targets = torch.randint(0, 2, (batch_size, num_classes)).float()
num_boxes = 2

ARGS = {
    "inputs": inputs,
    "targets": targets,
    "num_boxes": num_boxes,
    "alpha": 0.25,
    "gamma": 2.0,
    "no_reduction": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 13 are also present in other papers whose code we hold (12 with at least one paper dated earlier, 2 the same month, 13 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
convert_to_xywh 24 other papers
17 dated earlier, 1 the same month, 5 later, 1 same year, order not determinable
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2103.11731 (2021-03)
Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
and 21 more not named here
evaluate 23 other papers
16 dated earlier, 1 the same month, 5 later, 1 same year, order not determinable
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2103.11731 (2021-03)
Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
and 20 more not named here
l1norm 12 other papers
7 dated earlier, 5 later · 3 only as an assembly brick
1803.08024 (2018-03)
Stacked Cross Attention for Image-Text Matching
2010.03403 (2020-10)
Universal Weighting Metric Learning for Cross-Modal Matching
2101.01368 (2021-01)
Similarity Reasoning and Filtration for Image-Text Matching
and 9 more not named here
l2norm 12 other papers
10 dated earlier, 2 later · 2 only as an assembly brick
1803.08024 (2018-03)
Stacked Cross Attention for Image-Text Matching
1904.01310 (2019-04)
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis
2010.03403 (2020-10)
Universal Weighting Metric Learning for Cross-Modal Matching
and 9 more not named here
hflip 10 other papers
6 dated earlier, 4 later
2106.00666 (2021-06)
You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection
2112.05375 (2021-12)
Rethinking the Two-Stage Framework for Grounded Situation Recognition
2112.08647 (2021-12)
QAHOI: Query-Based Anchors for Human-Object Interaction Detection
and 7 more not named here
multi_scale_deformable_attn_pytorch 6 other papers
1 dated earlier, 4 later, 1 same year, order not determinable
2312.02153 (2023-12)
Aligning and Prompting Everything All at Once for Universal Visual Perception
Shen_Aligning_and_Prompting_Everything_All_at_Once_for_Universal_Visual_CVPR_2024_paper (2024 (year only))
Aligning and Prompting Everything All at Once for Universal Visual Perception
2407.11335 (2024-07)
LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction
and 3 more not named here
create_dummy_class 5 other papers
1 dated earlier, 3 later, 1 same year, order not determinable
2312.02153 (2023-12)
Aligning and Prompting Everything All at Once for Universal Visual Perception
Shen_Aligning_and_Prompting_Everything_All_at_Once_for_Universal_Visual_CVPR_2024_paper (2024 (year only))
Aligning and Prompting Everything All at Once for Universal Visual Perception
2501.06710 (2025-01)
Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints
and 2 more not named here
create_dummy_func 5 other papers
1 dated earlier, 3 later, 1 same year, order not determinable
2312.02153 (2023-12)
Aligning and Prompting Everything All at Once for Universal Visual Perception
Shen_Aligning_and_Prompting_Everything_All_at_Once_for_Universal_Visual_CVPR_2024_paper (2024 (year only))
Aligning and Prompting Everything All at Once for Universal Visual Perception
2501.06710 (2025-01)
Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints
and 2 more not named here
generate_masks_with_special_tokens_and_transfer_map 3 other papers
1 dated earlier, 2 later · 2 only as an assembly brick
2303.05499 (2023-03)
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
2407.04619 (2024-07)
COUNTGD: Multi-Modal Open-World Counting
func_attention 2 other papers
1 dated earlier, 1 later
2310.08530 (2023-10)
X-Pose: Detecting Any Keypoints
2503.10616 (2025-03)
OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer
get_sine_pos_embed 2 other papers
1 dated earlier, 1 later
2310.08530 (2023-10)
X-Pose: Detecting Any Keypoints
2503.10616 (2025-03)
OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer
sigmoid_focal_loss 2 other papers
1 dated earlier, 1 later
2310.08530 (2023-10)
X-Pose: Detecting Any Keypoints
2503.10616 (2025-03)
OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer
gen_encoder_output_proposals 1 other paper
1 later
2503.10616 (2025-03)
OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We introduce Grounded SAM, which uses Grounding DINO as an open-set object detector to combine with the segment anything model (SAM). This integration enables the detection and segmentation of any regions based on arbitrary text inputs and opens a door to connecting various vision models. As shown in Fig.1, a wide range of vision tasks can be achieved by using the versatile Grounded SAM pipeline. For example, an automatic annotation pipeline based solely on input images can be realized by incorporating models such as BLIP and Recognize Anything. Additionally, incorporating Stable-Diffusion allows for controllable image editing, while the integration of OSX facilitates promptable 3D human motion analysis. Grounded SAM also shows superior performance on open-vocabulary benchmarks, achieving 48.7 mean AP on SegInW (Segmentation in the wild) zero-shot benchmark with the combination of Grounding DINO-Base and SAM-Huge models.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2401.14159")
get_code_for_paper("2401.14159")
have("2401.14159")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2401.14159.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2401.14159.svg)](https://syntology.ai/paper/2401.14159)

Connect an agent — have() is free.