SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.02153 · 2023

Aligning and Prompting Everything All at Once for Universal Visual Perception

arXiv · PDF · Open in the Atlas

Code that ran

11 of 14 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; 0 honoured the contract we drafted, 1 violated it and 6 have no contract verdict; 4 failures of our instrument; 3 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/2312.02153.json · badge: /api/ran/2312.02153.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
shenyunhang/ape canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
earth-insights/ClassTrans community (classifier label)
classifier basis not recorded on the link
7 ran · 2 no recorded run
FunctionStatusWhere it lives
create_dummy_class Ran
ran; our contract draft was wrong, not the code
shenyunhang/ape/ape/layers/multi_scale_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
shenyunhang/ape/ape/layers/multi_scale_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
get_checkpoint_url Ran
ran; our contract draft was wrong, not the code
shenyunhang/ape/ape/model_zoo/model_zoo.py
code served (permissive licence) · get_code("0de113f0340ffcd9")
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 str. 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.

# First, let's examine the function signature by looking at the class
# The function appears to be a method of _ModelZooUrls class
# We need to find the get_checkpoint_url method

# Based on the class structure showing CONFIG_PATH_TO_URL_SUFFIX,
# the get_checkpoint_url method likely takes a config path as input

# Looking at the CONFIG_PATH_TO_URL_SUFFIX dictionary keys, they are config paths
# The method should construct and return a full URL

def get_checkpoint_url(config_path: str) -> str:
    """
    Args:
        config_path (str): a config path (relative to detectron2's "configs/")
            like "COCO-Detection/faster_rcnn_R_50_FPN_1x"

    Returns:
        str: checkpoint URL
    """
    if config_path not in _ModelZooUrls.CONFIG_PATH_TO_URL_SUFFIX:
        raise KeyError("Config path {} does not have a corresponding checkpoint".format(config_path))
    suffix = _ModelZooUrls.CONFIG_PATH_TO_URL_SUFFIX[config_path]
    return _ModelZooUrls.S3_PREFIX + suffix

# Now construct valid arguments for this function
ARGS = {
    "config_path": "COCO-Detection/faster_rcnn_R_50_FPN_1x"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
get_image_and_label Ran
ran on a synthesized input
earth-insights/ClassTrans/src/dataset/data.py
code served (permissive licence) · get_code("25190d960f6a2e87")
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 cv2
import os
import numpy as np
import tempfile
from pathlib import Path

# Create temporary directory for test images
temp_dir = tempfile.mkdtemp()

# Create a valid test image (4x3 RGB in BGR format for cv2)
image_array = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
image_path = os.path.join(temp_dir, "test_image.png")
cv2.imwrite(image_path, image_array)

# Create a valid label image with matching dimensions (4x3 grayscale)
label_array = np.random.randint(0, 2, (4, 3), dtype=np.uint8)
label_path = os.path.join(temp_dir, "test_label.png")
cv2.imwrite(label_path, label_array)

ARGS = {
    "image_path": image_path,
    "label_path": label_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — 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
get_next_run_id Ran
ran on a synthesized input
earth-insights/ClassTrans/src/utils.py
code served (permissive licence) · get_code("807451ec22e46bdb")
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 int, ndim 0, dtype family int, 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 os
import tempfile
import shutil

# Create a temporary directory to act as checkpoint path
temp_dir = tempfile.mkdtemp()

# Create some numbered subdirectories to simulate existing runs
os.makedirs(os.path.join(temp_dir, "0"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "1"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "5"), exist_ok=True)

# Create a simple args object with the required ckpt_path attribute
class Args:
    def __init__(self, ckpt_path):
        self.ckpt_path = ckpt_path

args = Args(ckpt_path=temp_dir)

ARGS = {
    "args": args
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, 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
is_image_file Ran
ran, violated the contract we drafted
earth-insights/ClassTrans/src/dataset/utils.py
code served (permissive licence) · get_code("25fea6c1ac82a8c5")
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 bool, 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

torch.manual_seed(0)

ARGS = {
    "filename": "test_image.jpg"
}
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 bool, 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
label2rgb Ran
ran on a synthesized input
earth-insights/ClassTrans/src/visualize.py
code served (permissive licence) · get_code("f54083dba77e2917")
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 ndarray, ndim 3, dtype family int, shape (4, 3, 3) 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 numpy as np

# The function expects a numpy array 'a' with shape (H, W) containing integer labels
# that correspond to keys in the class_gray dictionary (values 0-11)

# Create a small label map with height=4, width=3 containing various class indices
a = np.array([
    [0, 1, 2],
    [3, 4, 5],
    [6, 7, 8],
    [9, 10, 11]
], dtype=np.uint8)

ARGS = {
    'a': a
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (4, 3, 3) — shape (4, 3, 3) 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
main_process Ran
ran on a synthesized input
earth-insights/ClassTrans/src/utils.py
code served (permissive licence) · get_code("3baca7953e57a8e0")
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 bool, 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 argparse
import torch
import torch.distributed as dist
from unittest.mock import Mock, patch

torch.manual_seed(0)

# Create a mock args namespace
args = argparse.Namespace()

# The function checks args.distributed to determine behavior
# We'll test with distributed=False to avoid needing actual distributed setup
args.distributed = False

ARGS = {
    "args": args
}
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 bool, 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
map_ Ran
ran on a synthesized input
earth-insights/ClassTrans/src/utils.py
code served (permissive licence) · get_code("cc9e1a1081e7703d")
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 list, ndim 1, dtype family int; 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
import numpy as np
from typing import Callable, List

torch.manual_seed(0)

def simple_fn(x: int) -> int:
    """Simple function that squares an input."""
    return x * x

test_iterable = [1, 2, 3, 4, 5]

ARGS = {
    "fn": simple_fn,
    "iter": test_iterable,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list 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
multi_scale_deformable_attn_pytorch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
shenyunhang/ape/ape/layers/multi_scale_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
process_image Ran
ran on a synthesized input
earth-insights/ClassTrans/src/dataset/utils.py
code served (permissive licence) · get_code("09e34c3bca52dcda")
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 list, ndim 2, 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 os
from typing import Dict, List, Tuple

# Define ARGS dict with valid arguments for process_image function
ARGS = {
    "item": "image_001.jpg",  # Single filename as string
    "data_root": "/tmp/test_data",  # Root directory path
    "images_dir": "images",  # Images subdirectory
    "labels_dir": "labels"  # Labels subdirectory
}

# Alternative test case with list of filenames
ARGS_LIST = {
    "item": ["image_001.jpg", "image_002.jpg", "image_003.jpg"],  # List of filenames
    "data_root": "/tmp/test_data",
    "images_dir": "images",
    "labels_dir": "labels"
}

# Use the single item version as default
ARGS = ARGS
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list 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
get_config_file Not yet run
unverified (harvested, no recorded run)
shenyunhang/ape/ape/model_zoo/model_zoo.py
code served (permissive licence) · get_code("e8d6610aacdd981b")
How it ran

no invocation recorded.

get_val_loader Not yet run
unverified (harvested, no recorded run)
earth-insights/ClassTrans/src/dataset/data.py
code served (permissive licence) · get_code("bd491478bac24e5a")
How it ran

no invocation recorded.

make_dataset Not yet run
unverified (harvested, no recorded run)
earth-insights/ClassTrans/src/dataset/utils.py
code served (permissive licence) · get_code("4a14363d223db042")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 9 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 later) and 5 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
multi_scale_deformable_attn_pytorch 6 other papers
6 later
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
2401.14159 (2024-01)
Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
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
5 later
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
2401.14159 (2024-01)
Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
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
5 later
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
2401.14159 (2024-01)
Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
2501.06710 (2025-01)
Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints
and 2 more not named here
get_checkpoint_url 1 other paper
1 later
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
get_config_file 1 other paper
1 later
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
get_next_run_id 1 other paper
1 same year, order not determinable
Hajimiri_A_Strong_Baseline_for_Generalized_Few-Shot_Semantic_Segmentation_CVPR_2023_paper (2023 (year only))
A Strong Baseline for Generalized Few-Shot Semantic Segmentation
is_image_file 1 other paper
1 same year, order not determinable
Hajimiri_A_Strong_Baseline_for_Generalized_Few-Shot_Semantic_Segmentation_CVPR_2023_paper (2023 (year only))
A Strong Baseline for Generalized Few-Shot Semantic Segmentation
main_process 1 other paper
1 same year, order not determinable
Hajimiri_A_Strong_Baseline_for_Generalized_Few-Shot_Semantic_Segmentation_CVPR_2023_paper (2023 (year only))
A Strong Baseline for Generalized Few-Shot Semantic Segmentation
map_ 1 other paper
1 same year, order not determinable
Hajimiri_A_Strong_Baseline_for_Generalized_Few-Shot_Semantic_Segmentation_CVPR_2023_paper (2023 (year only))
A Strong Baseline for Generalized Few-Shot Semantic Segmentation

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

Vision foundation models have been explored recently to build general-purpose vision systems. However, predominant paradigms, driven by casting instance-level tasks as an object-word alignment, bring heavy cross-modality interaction, which is not effective in prompting object detection and visual grounding. Another line of work that focuses on pixel-level tasks often encounters a large annotation gap of things and stuff, and suffers from mutual interference between foreground-object and background-class segmentation. In stark contrast to the prevailing methods, we present APE, a universal visual perception model for aligning and prompting everything all at once in an image to perform diverse tasks, i.e., detection, segmentation, and grounding, as an instance-level sentence-object matching paradigm. Specifically, APE advances the convergence of detection and grounding by reformulating language-guided grounding as open-vocabulary detection, which efficiently scales up model prompting to thousands of category vocabularies and region descriptions while maintaining the effectiveness of cross-modality fusion. To bridge the granularity gap of different pixel-level tasks, APE equalizes semantic and panoptic segmentation to proxy instance learning by considering any isolated regions as individual instances. APE aligns vision and language representation on broad data with natural and challenging characteristics all at once without task-specific fine-tuning. The extensive experiments on over 160 datasets demonstrate that, with only one-suit of weights, APE outperforms (or is on par with) the state-of-the-art models, proving that an effective yet universal perception for anything aligning and prompting is indeed feasible. Codes and trained models are released at https://github.com/shenyunhang/APE.

For agents

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

get_harvested_code_for_paper("2312.02153")
get_code_for_paper("2312.02153")
have("2312.02153")

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

curl https://syntology.ai/api/ran/2312.02153.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.02153.svg)](https://syntology.ai/paper/2312.02153)

Connect an agent — have() is free.