Papers › What Do Deep Saliency Models Learn about Visual Attention?

What Do Deep Saliency Models Learn about Visual Attention?

14 Oct 2023NeurIPS 2023 11arXiv:2310.09679archive 2025-07-28

Shi Chen, Ming Jiang, Qi Zhao

In recent years, deep saliency models have made significant progress in predicting human visual attention. However, the mechanisms behind their success remain largely unexplained due to the opaque nature of deep neural networks. In this paper, we present a novel analytic framework that sheds light on the implicit features learned by saliency models and provides principled interpretation and quantification of their contributions to saliency prediction. Our approach decomposes these implicit features into interpretable bases that are explicitly aligned with semantic attributes and reformulates saliency prediction as a weighted combination of probability maps connecting the bases and saliency. By applying our framework, we conduct extensive analyses from various perspectives, including the positive and negative weights of semantics, the impact of training data and architectural designs, the progressive influences of fine-tuning, and common failure patterns of state-of-the-art deep saliency models. Additionally, we demonstrate the effectiveness of our framework by exploring visual attention characteristics in various application scenarios, such as the atypical attention of people with autism spectrum disorder, attention to emotion-eliciting stimuli, and attention evolution over time. Our code is publicly available at https://github.com/szzexpoi/saliency_analysis.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 14 code samples harvested from 1 repository linked to this paper: 8 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 8 ran (7 with no instrument failure; 1 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.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

szzexpoi/saliency_analysis officialmentioned in paperpytorchSyntology: 14 samples, 8 ran (1 instrument-failed) · 6 unverified 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.

Code Syntology ran Syntology

14 samples harvested: 8 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 6 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
7ran
6unverified

Licence: 14 of the 14 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 szzexpoi/saliency_analysis. “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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

szzexpoi/saliency_analysis official repository 14 samples, 8 ran (1 instrument-failed) · 6 unverified
Inception_Encoder prototype_dissection.py ran fingerprinted no licence file found · pointer only · bbf87470b090a5d9 · report fixture: returned Inception_Encoder · level recorded 2026-09-22
MLP in 375 papers prototype_dissection.py ran no licence file found · pointer only · ae7e55b26b6c63fa · report fixture: returned MLP · level recorded 2026-09-22
PatchEncoder in 5 papers prototype_dissection.py ran no licence file found · pointer only · 67bbc52e2db5c13f · report fixture: returned PatchEncoder · level recorded 2026-09-22
Proto_Decoder prototype_dissection.py ran no licence file found · pointer only · 7bf51d5279e351ea · report fixture: returned Proto_Decoder · level recorded 2026-09-22
ResNet in 139 papers prototype_dissection.py ran no licence file found · pointer only · 6cade961c640cc5e · report fixture: returned ResNet · level recorded 2026-09-22
Simple_Decoder prototype_dissection.py ran no licence file found · pointer only · 82100b664e3f65ec · report fixture: returned Simple_Decoder · level recorded 2026-09-22
Trans_encoder prototype_dissection.py ran no licence file found · pointer only · cee2ce9baa77dd88 · report fixture: signature image:Tensor/3/float · returned Tensor · level recorded 2026-09-24
resnet50 in 121 papers prototype_dissection.py ran · our draft was wrong no licence file found · pointer only · 6b45190dae2942f6 · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-22
DINet prototype_dissection.py unverified no licence file found · pointer only · 0dacde37ea08e367 · report
SALICON prototype_dissection.py unverified no licence file found · pointer only · 630eb55dff774d6e · report
TranSalNet prototype_dissection.py unverified no licence file found · pointer only · 5f960bc5b10ad788 · report
VG_generator prototype_dissection.py unverified no licence file found · pointer only · 46e9fb4dced5b47f · report
compute_iou in 68 papers prototype_dissection.py unverified no licence file found · pointer only · 423681206c2b5298 · report
prototype_dissection prototype_dissection.py unverified no licence file found · pointer only · 289a8337ec2a6d9d · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for novel analytic framework (graph method: novel analytic framework). 15 bricks; individually on a fixture: 9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

  1. prototype_dissection entry · level 0 · unverified · 289a8337ec2a6d9d
  2. DINet helper · level 0 · unverified · 0dacde37ea08e367
  3. SALICON helper · level 0 · unverified · 630eb55dff774d6e
  4. TranSalNet helper · level 0 · unverified · 5f960bc5b10ad788
  5. VG_generator sampler · level 0 · unverified · 46e9fb4dced5b47f
  6. compute_iou helper · level 0 · unverified · 423681206c2b5298
  7. Inception_Encoder helper · level 1 · ran · bbf87470b090a5d9
  8. Proto_Decoder helper · level 1 · ran · 7bf51d5279e351ea
  9. Simple_Decoder helper · level 1 · ran · 82100b664e3f65ec
  10. resnet50 helper · level 1 · ran · our draft was wrong · 6b45190dae2942f6
  11. Trans_encoder helper · level 1 · ran · cee2ce9baa77dd88
  12. Bottleneck helper · level 1 · ran · 644c6fab8e48ac8e
  13. ResNet helper · level 1 · ran · 6cade961c640cc5e
  14. MLP helper · level 1 · ran · ae7e55b26b6c63fa
  15. PatchEncoder helper · level 1 · ran · 67bbc52e2db5c13f

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2310.09679") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Saliency Prediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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