Papers › Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks

Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks

3 Oct 2019arXiv:1910.01279archive 2025-07-28

Haofan Wang, Zifan Wang, Mengnan Du, Fan Yang, Zijian Zhang, Sirui Ding, Piotr Mardziel, Xia Hu

Recently, increasing attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network makes specific decisions. In this paper, we develop a novel post-hoc visual explanation method called Score-CAM based on class activation mapping. Unlike previous class activation mapping based approaches, Score-CAM gets rid of the dependence on gradients by obtaining the weight of each activation map through its forward passing score on target class, the final result is obtained by a linear combination of weights and activation maps. We demonstrate that Score-CAM achieves better visual performance and fairness for interpreting the decision making process. Our approach outperforms previous methods on both recognition and localization tasks, it also passes the sanity check. We also indicate its application as debugging tools. Official code has been released.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 13 code samples harvested from 5 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 12 samples from 4 repositories, 8 ran (5 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

haofanwang/Score-CAM officialmentioned in papermentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Jupetus/ExplainableAI mentioned on GitHubpytorchSyntology: not harvested report
andreysorokin/scam-net mentioned on GitHubApache-2.0Syntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
frgfm/torch-cam mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
jacobgil/pytorch-grad-cam mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Feature Factorization For Concept Discovery (arXiv:1806.10206; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
matheushent/score-cam mentioned on GitHubtfMITSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
tabayashi0117/Score-CAM mentioned on GitHubtfSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
windstormer/Cfd-CAM mentioned on GitHubpytorchSyntology: not harvested report
yiskw713/scorecam mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization (arXiv:1610.02391; that paper's own run record: 90 ran (of which 32 constructed an object rather than computing a result; 62 with no instrument failure: 6 honoured, 4 violated, 52 with no contract checked; 28 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

13 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
2ran; the contract check could not run
6ran
4unverified

Licence: 2 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 5 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

haofanwang/Score-CAM official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
energy_point_game utils/energyPointGame.py ran MIT (permissive) · 0eb6b543eedbb913 · report fixture: signature bbox:tuple/1/int, saliency_map:Tensor/2/float · returned Tensor · level recorded 2026-09-25
andreysorokin/scam-net community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
resize_activations scam/utils.py ran Apache-2.0 (permissive) · 0092b2f7ee2b970b · report fixture: signature enhanced_model_output:ndarray/4/float, input_shape:tuple/1/int · returned ndarray · level recorded 2026-09-24
normalize_activations scam/utils.py unverified Apache-2.0 (permissive) · 1b3ec8aff736ee84 · report
frgfm/torch-cam community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
swin_reshape_transform in 6 papers scripts/cam_example.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong fingerprinted licence of this copy not recorded · cd9e431963bd28ca · report fixture: signature tensor:Tensor/4/float · returned Tensor · level recorded 2026-09-22
vit_reshape_transform in 7 papers scripts/cam_example.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence of this copy not recorded · 3e3e7c2d436361ca · report fixture: signature tensor:Tensor/3/float, grid_size:int/0/int · returned Tensor · level recorded 2026-09-22
matheushent/score-cam community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
grid_display utils/display.py ran MIT (permissive) · a6751790d12dd02d · report fixture: signature array:ndarray/4/int, num_rows:NoneType/0/?, num_columns:NoneType/0/? · returned ndarray · level recorded 2026-09-24
heatmap_display utils/display.py ran MIT (permissive) · c54afa1ecb39fd2f · report fixture: signature heatmap:ndarray/2/float, original_image:ndarray/3/float, colormap:int/0/int, image_weight:float/0/float · returned ndarray · level recorded 2026-09-24
image_to_uint_255 utils/display.py ran fingerprinted MIT (permissive) · 1ea162efebe64eb5 · report fixture: signature image:ndarray/2/float · returned ndarray · level recorded 2026-09-24
normalize_activations utils/image.py ran fingerprinted MIT (permissive) · 5444b8777b09ceb1 · report fixture: signature tensor:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-24
resize_activations utils/image.py unverified MIT (permissive) · f2f03a34ff27740f · report
tabayashi0117/Score-CAM community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
masked_inputs scorecam/score_cam.py ran; the contract check could not run (RAISES) MIT (permissive) · d3ba787775c076f1 · report fixture: returned ndarray · level recorded 2026-09-22
ScoreCam scorecam/score_cam.py unverified MIT (permissive) · 8abe77c90e3bab0d · report
upsample_and_normalise scorecam/score_cam.py unverified MIT (permissive) · a658de56603d3a9a · report

Tasks

Adversarial AttackDecision MakingError UnderstandingFairness

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Error Understanding CUB-200-2011 Score-CAM Average highest confidence (EfficientNetV2-M) 0.2403 #3 of 4 Archive leaderboard report
Error Understanding CUB-200-2011 Score-CAM Average highest confidence (MobileNetV2) 0.3141 #3 of 4 Archive leaderboard report
Error Understanding CUB-200-2011 Score-CAM Average highest confidence (ResNet-101) 0.2510 #3 of 4 Archive leaderboard report
Error Understanding CUB-200-2011 Score-CAM Insertion AUC score (EfficientNetV2-M) 0.1572 #3 of 4 Archive leaderboard report
Error Understanding CUB-200-2011 Score-CAM Insertion AUC score (MobileNetV2) 0.1195 #3 of 4 Archive leaderboard report
Error Understanding CUB-200-2011 Score-CAM Insertion AUC score (ResNet-101) 0.1073 #3 of 4 Archive leaderboard report
Error Understanding CUB-200-2011 (ResNet-101) Score-CAM Average highest confidence 0.2510 #2 of 3 Archive leaderboard report
Error Understanding CUB-200-2011 (ResNet-101) Score-CAM Insertion AUC score 0.1073 #2 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections