SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.01183 · 2020

Weakly-Supervised Semantic Segmentation via Sub-category Exploration

arXiv · PDF · Open in the Atlas

Code that ran

11 of 16 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 10 have no contract verdict; 1 failure of our instrument; 5 no recorded run), measured 2026-11-21; 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/2008.01183.json · badge: /api/ran/2008.01183.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
Juliachang/SC-CAM canonical (classifier label)
classifier basis: census
11 ran · 5 no recorded run
FunctionStatusWhere it lives
calculate_class_avg_iou Ran
ran on a synthesized input
Juliachang/SC-CAM/tool/infer_utils.py
code served (permissive licence) · get_code("0f3b88f76a1f1b69")
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 dict. 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)

# The function expects a dict mapping integers 0-19 to lists of IoU values
# Each list contains IoU scores for a class across multiple samples
class_iou_dict = {}

# Populate the dict with 20 classes (0-19)
# Some classes have IoU values, some are empty lists
for i in range(20):
    if i % 3 == 0:
        # Empty list for some classes
        class_iou_dict[i] = []
    else:
        # Non-empty list of IoU scores (between 0 and 1)
        class_iou_dict[i] = [0.75, 0.82, 0.91, 0.68]

ARGS = {
    "class_iou_dict": class_iou_dict
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
compute_acc Ran
ran on a synthesized input
Juliachang/SC-CAM/train_cls.py
code served (permissive licence) · get_code("e7b5ceebedb5efe7")
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 float, 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)

# Analyzing the function:
# - pred_labels: iterated over with "for pred_label in pred_labels"
# - gt_labels: checked with "in gt_labels" membership test, len() is called
# - Both support len() and iteration
# - pred_label values are compared for membership in gt_labels
# - The function treats them as collections of labels (likely integers or strings)

# Create simple label lists for testing
pred_labels = [1, 2, 3]
gt_labels = [2, 3, 4, 5]

ARGS = {
    "pred_labels": pred_labels,
    "gt_labels": gt_labels
}
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 float, 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
create_class_key_in_dict Ran
ran on a synthesized input
Juliachang/SC-CAM/create_pseudo_label.py
code served (permissive licence) · get_code("207543a1e7a80fd3")
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 dict. 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

dict_input = {}
cls_nb_input = 5

ARGS = {
    "dict": dict_input,
    "cls_nb": cls_nb_input
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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_with_box Ran
ran on a synthesized input
Juliachang/SC-CAM/tool/imutils.py
code served (permissive licence) · get_code("1da77dcda491ece7")
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 (2, 2, 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

# Create a small test image (grayscale, 2D)
img_2d = np.arange(20, dtype=np.uint8).reshape(4, 5)

# Create a small test image (color, 3D)
img_3d = np.arange(60, dtype=np.uint8).reshape(4, 5, 3)

# Box format: [y1_dest, y2_dest, x1_dest, x2_dest, y1_src, y2_src, x1_src, x2_src]
# This box crops from source region (rows 1:3, cols 1:3) to destination region (rows 0:2, cols 0:2)
box = [0, 2, 0, 2, 1, 3, 1, 3]

ARGS = {
    "img": img_3d,
    "box": box
}
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 (2, 2, 3) — shape (2, 2, 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
dict2npy Ran
ran on a synthesized input
Juliachang/SC-CAM/tool/camutils.py
code served (permissive licence) · get_code("aede9964dd51e4c8")
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 float, shape (21, 5, 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 numpy as np

# Construct valid arguments for dict2npy function

# cam_dict: a dictionary mapping labels (integers) to numpy arrays of CAM scores
# The function expects the arrays to have shape (height, width)
img_height, img_width = 5, 6
cam_dict = {
    0: np.random.rand(img_height, img_width).astype(np.float32),
    1: np.random.rand(img_height, img_width).astype(np.float32),
    2: np.random.rand(img_height, img_width).astype(np.float32),
    5: np.random.rand(img_height, img_width).astype(np.float32),
    10: np.random.rand(img_height, img_width).astype(np.float32),
}

# gt_label: a list or array of ground truth labels (must be keys in cam_dict)
gt_label = [0, 1, 2, 5, 10]

# th: a threshold value (scalar float)
th = 0.5

ARGS = {
    'cam_dict': cam_dict,
    'gt_label': gt_label,
    'th': th,
}
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 float, shape (21, 5, 6) — shape (21, 5, 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
generate_merged_label Ran
ran on a synthesized input
Juliachang/SC-CAM/create_pseudo_label.py
code served (permissive licence) · get_code("08008d2ed2836147")
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 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 numpy as np

# Analyzing the function:
# - repeat_list: list of lists, where each inner list contains indices
# - label_list: list of arrays/vectors that can be indexed and summed
# The function:
#   1. Iterates through repeat_list
#   2. For each inner list, gets corresponding labels from label_list
#   3. Sums the labels (as numpy arrays)
#   4. Counts non-zero elements and checks if count equals length of indices
#   5. If condition met, appends to result

# Create label_list: list of small binary vectors
label_list = [
    np.array([1, 0, 0, 0]),
    np.array([0, 1, 0, 0]),
    np.array([1, 1, 0, 0]),
    np.array([0, 0, 1, 0]),
    np.array([1, 0, 1, 0]),
]

# Create repeat_list: list of index lists
# Case 1: [0, 1] -> sum([1,0,0,0] + [0,1,0,0]) = [1,1,0,0], nb_nonzero=2, len(indices)=2 ✓
# Case 2: [2] -> sum([1,1,0,0]) = [1,1,0,0], nb_nonzero=2, len(indices)=1 ✗
# Case 3: [3, 4] -> sum([0,0,1,0] + [1,0,1,0]) = [1,0,2,0], nb_nonzero=2, len(indices)=2 ✓
repeat_list = [
    [0, 1],
    [2],
    [3, 4],
]

ARGS = {
    "repeat_list": repeat_list,
    "label_list": label_list,
}
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 list, ndim 2, 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
get_img_path Ran
ran on a synthesized input
Juliachang/SC-CAM/train_cls.py
code served (permissive licence) · get_code("0a5d5355f060c563")
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.

import os

ARGS = {
    'img_name': 'test_image',
    'dataset_path': '/path/to/dataset'
}
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_random_crop_box Ran
ran on a synthesized input
Juliachang/SC-CAM/tool/imutils.py
code served (permissive licence) · get_code("14cb2e4c07b535f6")
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 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 random

# Set random seed for reproducibility
random.seed(0)

# Define arguments for get_random_crop_box
# The function takes two parameters: imgsize and cropsize
# imgsize: tuple of (height, width) representing image dimensions
# cropsize: integer representing the size of the crop

ARGS = {
    "imgsize": (128, 256),  # (height, width) - distinct dimensions for clarity
    "cropsize": 64
}
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 tuple, ndim 1, dtype family int — 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
make_subclass_label Ran
ran on a synthesized input
Juliachang/SC-CAM/create_pseudo_label.py
code served (permissive licence) · get_code("6e46befc4a038fa2")
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 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

torch.manual_seed(0)

# Analyze the function:
# - class_idx: int, used as index in calculation
# - labels: iterable with len(), elements used as indices
# - subclass_nb: int, used in arithmetic
# - all_class_kmeans_label: list, .append() is called on it

class_idx = 2
labels = [0, 1]
subclass_nb = 5
all_class_kmeans_label = []

ARGS = {
    "class_idx": class_idx,
    "labels": labels,
    "subclass_nb": subclass_nb,
    "all_class_kmeans_label": all_class_kmeans_label,
}
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 2, 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
random_crop Ran
ran on a synthesized input
Juliachang/SC-CAM/tool/imutils.py
code served (permissive licence) · get_code("fab5abda02bc5312")
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. 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 PIL.Image
import numpy as np
import random

random.seed(0)
np.random.seed(0)

# Create a small PIL Image for testing
pil_img = PIL.Image.new('RGB', (8, 6), color='red')

# Create a numpy array image (height=6, width=8, channels=3)
np_img = np.ones((6, 8, 3), dtype=np.uint8) * 100

# Create a grayscale numpy array (height=6, width=8)
np_gray = np.ones((6, 8), dtype=np.uint8) * 50

# Test with PIL images and numpy arrays mixed
images = [pil_img, np_img, np_gray]

# Crop size
cropsize = 4

# Fill values for each image (used when creating containers)
fills = [255, 128, 64]

ARGS = {
    'images': images,
    'cropsize': cropsize,
    'fills': fills
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list 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
scores Ran
ran; our contract draft was wrong, not the code
Juliachang/SC-CAM/tool/iouutils.py
code served (permissive licence) · get_code("4d8fbe9ff0f1714e")
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 dict. 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 numpy as np

# Construct small test data for the scores function
# The function expects:
# - label_trues: list of arrays with true labels
# - label_preds: list of arrays with predicted labels
# - n_class: number of classes

n_class = 4

# Create small 2D label arrays (simulating image segmentation outputs)
# Using distinct sizes for clarity: 2x3 spatial dimensions
label_true_1 = np.array([[0, 1, 2], [3, 1, 0]])
label_pred_1 = np.array([[0, 1, 1], [3, 1, 0]])

label_true_2 = np.array([[2, 2, 1], [0, 3, 3]])
label_pred_2 = np.array([[2, 1, 1], [0, 3, 2]])

label_trues = [label_true_1, label_true_2]
label_preds = [label_pred_1, label_pred_2]

ARGS = {
    'label_trues': label_trues,
    'label_preds': label_preds,
    'n_class': n_class
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
cam_npy_to_label_map Not yet run
unverified (harvested, no recorded run)
Juliachang/SC-CAM/tool/camutils.py
code served (permissive licence) · get_code("b991660d9b0a2e9e")
How it ran

no invocation recorded.

cls200_sum Not yet run
unverified (harvested, no recorded run)
Juliachang/SC-CAM/train_cls.py
code served (permissive licence) · get_code("ac9ccf112fb4d9db")
How it ran

no invocation recorded.

convert_mxnet_to_torch Not yet run
unverified (harvested, no recorded run)
Juliachang/SC-CAM/network/resnet38d.py
code served (permissive licence) · get_code("95dfca01d7656b7c")
How it ran

no invocation recorded.

draw_heatmap Not yet run
unverified (harvested, no recorded run)
Juliachang/SC-CAM/tool/camutils.py
code served (permissive licence) · get_code("361a0bf7cb1e701e")
How it ran

no invocation recorded.

draw_heatmap Not yet run
unverified (harvested, no recorded run)
Juliachang/SC-CAM/tool/infer_utils.py
code served (permissive licence) · get_code("b16041930709dec1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 2 later) and 11 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_mxnet_to_torch 7 other papers
3 dated earlier, 4 later
1803.10464 (2018-03)
Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation
1903.00179 (2019-03)
Pyramid Feature Attention Network for Saliency detection
1911.01370 (2019-11)
Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation
and 4 more not named here
scores 3 other papers
3 later
2212.09506 (2022-12)
CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation
Lin_CLIP_Is_Also_an_Efficient_Segmenter_A_Text-Driven_Approach_for_CVPR_2023_paper (2023 (year only))
CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation
aaai_28139 (2024 (year only))
TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP without Training
crop_with_box 1 other paper
1 dated earlier
1803.10464 (2018-03)
Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation
get_random_crop_box 1 other paper
1 dated earlier
1803.10464 (2018-03)
Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation
random_crop 1 other paper
1 dated earlier
1803.10464 (2018-03)
Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised 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 2026-11-21.

Repositories linked to this paper

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

Abstract

Existing weakly-supervised semantic segmentation methods using image-level annotations typically rely on initial responses to locate object regions. However, such response maps generated by the classification network usually focus on discriminative object parts, due to the fact that the network does not need the entire object for optimizing the objective function. To enforce the network to pay attention to other parts of an object, we propose a simple yet effective approach that introduces a self-supervised task by exploiting the sub-category information. Specifically, we perform clustering on image features to generate pseudo sub-categories labels within each annotated parent class, and construct a sub-category objective to assign the network to a more challenging task. By iteratively clustering image features, the training process does not limit itself to the most discriminative object parts, hence improving the quality of the response maps. We conduct extensive analysis to validate the proposed method and show that our approach performs favorably against the state-of-the-art approaches.

For agents

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

get_harvested_code_for_paper("2008.01183")
get_code_for_paper("2008.01183")
have("2008.01183")

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

curl https://syntology.ai/api/ran/2008.01183.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.01183.svg)](https://syntology.ai/paper/2008.01183)

Connect an agent — have() is free.