SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.13859 · 2021

Group-CAM: Group Score-Weighted Visual Explanations for Deep Convolutional Networks

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 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 1 has no contract verdict; 2 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/2103.13859.json · badge: /api/ran/2103.13859.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
wofmanaf/Group-CAM canonical (classifier label)
classifier basis: census
4 ran · 3 no recorded run
FunctionStatusWhere it lives
auc Ran
ran, violated the contract we drafted
wofmanaf/Group-CAM/ins_del_gc.py
code served (permissive licence) · get_code("f612c23143fa7983")
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) 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 numpy as np

torch.manual_seed(0)

# The function auc() takes an array-like object and:
# - calls .sum() on it
# - indexes it with [0] and [-1]
# - accesses .shape[0]
# So we need a tensor or numpy array with at least 1 dimension

# Create a small 1D array with distinct values for testing
arr = torch.tensor([1.0, 2.0, 3.0, 4.0, 5.0])

ARGS = {
    "arr": arr
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
wofmanaf/Group-CAM/backbones/resnet.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from medaitech/scrd4ad, is pointer only (licence: NONE) · get_code("2a80220dabcb742a")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, wofmanaf/Group-CAM, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
wofmanaf/Group-CAM/backbones/resnet.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from medaitech/scrd4ad, is pointer only (licence: NONE) · get_code("600ff2c45e0de056")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, wofmanaf/Group-CAM, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

explain_all Ran
ran on a synthesized input
wofmanaf/Group-CAM/ins_del_gc.py
pointer only (licence: Apache-2.0) · get_code("34005a509b533cc7")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, wofmanaf/Group-CAM, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

cascade_randomization Not yet run
unverified (harvested, no recorded run)
wofmanaf/Group-CAM/sanity_checks.py
pointer only (licence: Apache-2.0) · get_code("9694111b933d77dc")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, wofmanaf/Group-CAM, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. No invocation recorded.

independent_randomization Not yet run
unverified (harvested, no recorded run)
wofmanaf/Group-CAM/sanity_checks.py
pointer only (licence: Apache-2.0) · get_code("50ce68e1644986c2")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, wofmanaf/Group-CAM, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. No invocation recorded.

resnet18 Not yet run
unverified (harvested, no recorded run)
wofmanaf/Group-CAM/backbones/resnet.py
pointer only (licence: Apache-2.0) · get_code("67f906f3faff0271")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, wofmanaf/Group-CAM, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. No invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 4 later) and 3 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
conv1x1 112 other papers
8 dated earlier, 104 later · 6 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1806.01531 (2018-06)
Deep Mixture of Experts via Shallow Embedding
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 109 more not named here
conv3x3 111 other papers
7 dated earlier, 104 later · 6 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1806.01531 (2018-06)
Deep Mixture of Experts via Shallow Embedding
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 108 more not named here
resnet18 36 other papers
3 dated earlier, 33 later
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
2002.09564 (2020-02)
Towards Robust and Reproducible Active Learning Using Neural Networks
2003.04297 (2020-03)
Improved Baselines with Momentum Contrastive Learning
and 33 more not named here
auc 3 other papers
3 later
2211.02912 (2022-11)
New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound
2407.11771 (2024-07)
XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach
2606.22314 (2026-06)
Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution

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

In this paper, we propose an efficient saliency map generation method, called Group score-weighted Class Activation Mapping (Group-CAM), which adopts the "split-transform-merge" strategy to generate saliency maps. Specifically, for an input image, the class activations are firstly split into groups. In each group, the sub-activations are summed and de-noised as an initial mask. After that, the initial masks are transformed with meaningful perturbations and then applied to preserve sub-pixels of the input (i.e., masked inputs), which are then fed into the network to calculate the confidence scores. Finally, the initial masks are weighted summed to form the final saliency map, where the weights are confidence scores produced by the masked inputs. Group-CAM is efficient yet effective, which only requires dozens of queries to the network while producing target-related saliency maps. As a result, Group-CAM can be served as an effective data augment trick for fine-tuning the networks. We comprehensively evaluate the performance of Group-CAM on common-used benchmarks, including deletion and insertion tests on ImageNet-1k, and pointing game tests on COCO2017. Extensive experimental results demonstrate that Group-CAM achieves better visual performance than the current state-of-the-art explanation approaches. The code is available at https://github.com/wofmanaf/Group-CAM.

For agents

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

get_harvested_code_for_paper("2103.13859")
get_code_for_paper("2103.13859")
have("2103.13859")

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

curl https://syntology.ai/api/ran/2103.13859.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.13859.svg)](https://syntology.ai/paper/2103.13859)

Connect an agent — have() is free.