SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.04187 · ECCV · 2022

RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation

Xiangyu Yue, Han Hu, Yuhui Yuan, Haodi He

arXiv · PDF · Open in the Atlas

Code that ran

9 of 11 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, 0 violated it and 3 have no contract verdict; 6 failures of our instrument; 2 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/2203.04187.json · badge: /api/ran/2203.04187.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
facebookresearch/Mask2Former canonical (classifier label)
classifier basis not recorded on the link
6 ran · 1 no recorded run
openseg-group/mlseg canonical (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
FunctionStatusWhere it lives
batch_dice_loss Ran
ran; our contract draft was wrong, not the code
facebookresearch/Mask2Former/mask2former/modeling/matcher.py
code served (permissive licence) · get_code("bc2cb481a75c370d")
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, 2) 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 small tensors for inputs and targets
# inputs: arbitrary shape float tensor (predictions)
# targets: same shape as inputs, binary classification labels (0 or 1)
# Using shape (2, 4) - batch size 2, 4 features
inputs = torch.randn(2, 4, dtype=torch.float32)
targets = torch.randint(0, 2, (2, 4), dtype=torch.float32)

ARGS = {
    'inputs': inputs,
    'targets': targets,
}
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, 2) — shape (2, 2) 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
calculate_uncertainty Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/Mask2Former/mask2former/modeling/criterion.py
code served (permissive licence) · get_code("2dcb8123d89bb1ff")
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 4, dtype family float, shape (2, 1, 4, 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 torch

torch.manual_seed(0)

# logits should be a tensor of shape (R, 1, ...) where R is number of predictions
# The function expects logits.shape[1] == 1
# Let's create a tensor with shape (2, 1, 4, 3) - R=2, C=1, and spatial dims 4x3
logits = torch.randn(2, 1, 4, 3)

ARGS = {
    "logits": logits
}
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 4, dtype family float, shape (2, 1, 4, 3) — shape (2, 1, 4, 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
convert_mit Ran
ran on a synthesized input
openseg-group/mlseg/mmseg/model_converters/mit2mmseg.py
code served (permissive licence) · get_code("ecc2fc8b9ed89284")
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 OrderedDict. 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
from collections import OrderedDict

torch.manual_seed(0)

# Create a minimal checkpoint dict that exercises the function's logic
ckpt = OrderedDict()

# Add head entries (should be skipped)
ckpt['head.weight'] = torch.randn(10, 4)
ckpt['head.bias'] = torch.randn(10)

# Add patch_embed entries
ckpt['patch_embed1.proj.weight'] = torch.randn(8, 3, 3, 3)
ckpt['patch_embed1.proj.bias'] = torch.randn(8)
ckpt['patch_embed2.proj.weight'] = torch.randn(16, 8, 3, 3)
ckpt['patch_embed2.proj.bias'] = torch.randn(16)

# Add block entries with attention
ckpt['block1.attn.q.weight'] = torch.randn(12, 4)
ckpt['block1.attn.q.bias'] = torch.randn(12)
ckpt['block1.attn.kv.weight'] = torch.randn(24, 4)
ckpt['block1.attn.kv.bias'] = torch.randn(24)
ckpt['block1.attn.proj.weight'] = torch.randn(4, 12)
ckpt['block1.attn.proj.bias'] = torch.randn(4)
ckpt['block1.attn.sr.weight'] = torch.randn(8, 4)

# Add mlp entries
ckpt['block1.mlp.fc1.weight'] = torch.randn(16, 4)
ckpt['block1.mlp.fc1.bias'] = torch.randn(16)
ckpt['block1.mlp.dwconv.dwconv.weight'] = torch.randn(16, 1, 3, 3)
ckpt['block1.mlp.dwconv.dwconv.bias'] = torch.randn(16)
ckpt['block1.mlp.fc2.weight'] = torch.randn(4, 16)
ckpt['block1.mlp.fc2.bias'] = torch.randn(4)

# Add norm entries
ckpt['norm1.weight'] = torch.randn(4)
ckpt['norm1.bias'] = torch.randn(4)
ckpt['norm2.weight'] = torch.randn(8)
ckpt['norm2.bias'] = torch.randn(8)

# Add a second block to test stage indexing
ckpt['block2.attn.q.weight'] = torch.randn(12, 8)
ckpt['block2.attn.q.bias'] = torch.randn(12)
ckpt['block2.attn.kv.weight'] = torch.randn(24, 8)
ckpt['block2.attn.kv.bias'] = torch.randn(24)
ckpt['block2.attn.proj.weight'] = torch.randn(8, 12)
ckpt['block2.attn.proj.bias'] = torch.randn(8)
ckpt['block2.mlp.fc1.weight'] = torch.randn(32, 8)
ckpt['block2.mlp.fc1.bias'] = torch.randn(32)
ckpt['block2.mlp.dwconv.dwconv.weight'] = torch.randn(32, 1, 3, 3)
ckpt['block2.mlp.dwconv.dwconv.bias'] = torch.randn(32)
ckpt['block2.mlp.fc2.weight'] = torch.randn(8, 32)
ckpt['block2.mlp.fc2.bias'] = torch.randn(8)

ARGS = {
    'ckpt': ckpt
}
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 OrderedDict — a OrderedDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a OrderedDict 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
convert_swin Ran
ran on a synthesized input
openseg-group/mlseg/mmseg/model_converters/swin2mmseg.py
code served (permissive licence) · get_code("285a4b7dcde2ba67")
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 OrderedDict. 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 numpy as np
from collections import OrderedDict

torch.manual_seed(0)

# Create a checkpoint dictionary with various keys that the function processes
ckpt = OrderedDict()

# Add head keys (should be skipped)
ckpt['head.fc'] = torch.randn(10, 768)

# Add layers with attn keys
ckpt['layers.0.attn.qkv'] = torch.randn(2304, 768)
ckpt['layers.0.attn.proj'] = torch.randn(768, 768)

# Add layers with mlp keys
ckpt['layers.0.mlp.fc1.weight'] = torch.randn(3072, 768)
ckpt['layers.0.mlp.fc1.bias'] = torch.randn(3072)
ckpt['layers.0.mlp.fc2.weight'] = torch.randn(768, 3072)
ckpt['layers.0.mlp.fc2.bias'] = torch.randn(768)

# Add layers with downsample keys including reduction
ckpt['layers.0.downsample.reduction.weight'] = torch.randn(256, 1024)
ckpt['layers.0.downsample.norm.weight'] = torch.randn(256)

# Add layers with norm keys
ckpt['layers.0.norm1.weight'] = torch.randn(768)
ckpt['layers.0.norm1.bias'] = torch.randn(768)

# Add patch_embed keys with proj
ckpt['patch_embed.proj.weight'] = torch.randn(768, 12)
ckpt['patch_embed.proj.bias'] = torch.randn(768)

# Add patch_embed keys without proj
ckpt['patch_embed.norm.weight'] = torch.randn(768)

# Add other general keys
ckpt['norm.weight'] = torch.randn(768)
ckpt['norm.bias'] = torch.randn(768)

ARGS = {
    'ckpt': ckpt
}
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 OrderedDict — a OrderedDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a OrderedDict 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
convert_vit Ran
ran on a synthesized input
openseg-group/mlseg/mmseg/model_converters/vit2mmseg.py
code served (permissive licence) · get_code("be6231544c7730c8")
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 OrderedDict. 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
from collections import OrderedDict

torch.manual_seed(0)

# Create a mock checkpoint dictionary with various keys that the function processes
ckpt = OrderedDict()

# Keys that should be skipped (head.*)
ckpt['head.weight'] = torch.randn(10, 768)
ckpt['head.bias'] = torch.randn(10)

# norm.* keys (should be converted to ln1.*)
ckpt['norm.weight'] = torch.randn(768)
ckpt['norm.bias'] = torch.randn(768)

# patch_embed.proj keys (should replace proj with projection)
ckpt['patch_embed.proj.weight'] = torch.randn(768, 3, 16, 16)
ckpt['patch_embed.proj.bias'] = torch.randn(768)

# patch_embed.* keys without proj
ckpt['patch_embed.cls_token'] = torch.randn(1, 1, 768)

# blocks.*.norm keys (should replace norm with ln and blocks with layers)
ckpt['blocks.0.norm1.weight'] = torch.randn(768)
ckpt['blocks.0.norm1.bias'] = torch.randn(768)
ckpt['blocks.0.norm2.weight'] = torch.randn(768)
ckpt['blocks.0.norm2.bias'] = torch.randn(768)

# blocks.*.mlp.fc1 keys
ckpt['blocks.0.mlp.fc1.weight'] = torch.randn(3072, 768)
ckpt['blocks.0.mlp.fc1.bias'] = torch.randn(3072)

# blocks.*.mlp.fc2 keys
ckpt['blocks.0.mlp.fc2.weight'] = torch.randn(768, 3072)
ckpt['blocks.0.mlp.fc2.bias'] = torch.randn(768)

# blocks.*.attn.qkv keys
ckpt['blocks.0.attn.qkv.weight'] = torch.randn(2304, 768)
ckpt['blocks.0.attn.qkv.bias'] = torch.randn(2304)

# blocks.*.attn.proj keys
ckpt['blocks.0.attn.proj.weight'] = torch.randn(768, 768)
ckpt['blocks.0.attn.proj.bias'] = torch.randn(768)

# Other block keys that don't match any pattern
ckpt['blocks.0.other.weight'] = torch.randn(64, 64)

ARGS = {
    'ckpt': ckpt
}
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 OrderedDict — a OrderedDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a OrderedDict 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
dice_loss Ran
ran; our contract draft was wrong, not the code
facebookresearch/Mask2Former/mask2former/modeling/criterion.py
code served (permissive licence) · get_code("89f75e54ff128be0")
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

torch.manual_seed(0)

# Create small tensors for inputs and targets
# inputs should be arbitrary shape that can be flattened
inputs = torch.randn(2, 4, requires_grad=False)  # batch_size=2, features=4
targets = torch.randint(0, 2, (2, 4), dtype=torch.float32)  # same shape as inputs, binary labels

# num_masks is a float representing the number of masks for normalization
num_masks = 2.0

ARGS = {
    "inputs": inputs,
    "targets": targets,
    "num_masks": num_masks,
}
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
sigmoid_ce_loss Ran
ran; our contract draft was wrong, not the code
facebookresearch/Mask2Former/mask2former/modeling/criterion.py
code served (permissive licence) · get_code("d0c61e8dba511aa3")
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
# inputs: predictions (logits), arbitrary shape
# targets: binary labels (0 or 1), same shape as inputs
batch_size = 2
num_elements = 4

inputs = torch.randn(batch_size, num_elements, dtype=torch.float32)
targets = torch.randint(0, 2, (batch_size, num_elements), dtype=torch.float32)

# num_masks: used as divisor in the loss computation
num_masks = 2.0

ARGS = {
    "inputs": inputs,
    "targets": targets,
    "num_masks": num_masks,
}
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
window_partition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/Mask2Former/mask2former/modeling/backbone/swin.py
code served (permissive licence) · get_code("f9fd6241d935f07b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (12, 4, 4, 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 tensor with shape (B, H, W, C)
# B = 2 (batch size)
# H = 8 (height, must be divisible by window_size)
# W = 12 (width, must be divisible by window_size)
# C = 4 (channels)
# window_size = 4

B = 2
H = 8
W = 12
C = 4
window_size = 4

x = torch.randn(B, H, W, C)

ARGS = {
    'x': x,
    'window_size': window_size
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 4, dtype family float, shape (12, 4, 4, 4) — shape (12, 4, 4, 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
window_reverse Ran
ran; our contract draft was wrong, not the code
facebookresearch/Mask2Former/mask2former/modeling/backbone/swin.py
code served (permissive licence) · get_code("fb32094c6dbece71")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (2, 8, 12, 6) 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)

# Define parameters
# We need windows of shape (num_windows*B, window_size, window_size, C)
# where num_windows = (H // window_size) * (W // window_size)

B = 2
H = 8
W = 12
window_size = 4
C = 6

# Calculate num_windows
num_windows_h = H // window_size  # 8 // 4 = 2
num_windows_w = W // window_size  # 12 // 4 = 3
num_windows = num_windows_h * num_windows_w  # 2 * 3 = 6

# Total number of windows across batch
total_windows = num_windows * B  # 6 * 2 = 12

# Create windows tensor
windows = torch.randn(total_windows, window_size, window_size, C)

ARGS = {
    'windows': windows,
    'window_size': window_size,
    'H': H,
    'W': W
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 4, dtype family float, shape (2, 8, 12, 6) — shape (2, 8, 12, 6) 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
batch_sigmoid_ce_loss Not yet run
unverified (harvested, no recorded run)
facebookresearch/Mask2Former/mask2former/modeling/matcher.py
code served (permissive licence) · get_code("1edd24985036b0bf")
How it ran

no invocation recorded.

sem_seg_postprocess Not yet run
unverified (harvested, no recorded run)
openseg-group/mlseg/mask2former/mask2former_video/video_maskformer_model.py
code served (permissive licence) · get_code("c210cc82192616af")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 6 the same month, 7 later) and 4 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
window_reverse 227 other papers
33 dated earlier, 11 the same month, 181 later, 2 same year, order not determinable · 34 only as an assembly brick
1608.03983 (2016-08)
SGDR: Stochastic Gradient Descent with Warm Restarts
1711.10925 (2017-11)
Deep Image Prior
2003.13678 (2020-03)
Designing Network Design Spaces
and 224 more not named here
window_partition 223 other papers
31 dated earlier, 10 the same month, 180 later, 2 same year, order not determinable · 32 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1711.10925 (2017-11)
Deep Image Prior
2003.13678 (2020-03)
Designing Network Design Spaces
and 220 more not named here
dice_loss 46 other papers
2 dated earlier, 1 the same month, 43 later
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
and 43 more not named here
sigmoid_ce_loss 45 other papers
2 dated earlier, 1 the same month, 42 later
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
and 42 more not named here
batch_dice_loss 44 other papers
2 dated earlier, 1 the same month, 41 later
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
and 41 more not named here
batch_sigmoid_ce_loss 44 other papers
2 dated earlier, 1 the same month, 41 later
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
and 41 more not named here
calculate_uncertainty 34 other papers
2 dated earlier, 32 later
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2206.04403 (2022-06)
VITA: Video Instance Segmentation via Object Token Association
and 31 more not named here

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

The segmentation task has traditionally been formulated as a complete-label 4 pixel classification task to predict a class for each pixel from a fixed number of predefined semantic categories shared by all images or videos. Yet, following this formulation, standard architectures will inevitably encounter various challenges under more realistic settings where the scope of categories scales up (e.g., beyond the level of 1k). On the other hand, in a typical image or video, only a few categories, i.e., a small subset of the complete label are present. Motivated by this intuition, in this paper, we propose to decompose segmentation into two sub-problems: (i) image-level or video-level multi-label classification and (ii) pixel-level rank-adaptive selected-label classification. Given an input image or video, our framework first conducts multilabel classification over the complete label, then sorts the complete label and selects a small subset according to their class confidence scores. We then use a rank-adaptive pixel classifier to perform the pixel-wise classification over only the selected labels, which uses a set of rankoriented learnable temperature parameters to adjust the pixel classifications scores. Our approach is conceptually general and can be used to improve various existing segmentation frameworks by simply using a lightweight multi-label classification head and rank-adaptive pixel classifier. We demonstrate the effectiveness of our framework with competitive experimental results across four tasks,

For agents

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

get_harvested_code_for_paper("2203.04187")
get_code_for_paper("2203.04187")
have("2203.04187")

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

curl https://syntology.ai/api/ran/2203.04187.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.04187.svg)](https://syntology.ai/paper/2203.04187)

Connect an agent — have() is free.