Papers › DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling

DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling

26 May 2021ICCV 2021 10arXiv:2105.12441archive 2025-07-28

Akis Linardos, Matthias Kümmerer, Ori Press, Matthias Bethge

Since 2014 transfer learning has become the key driver for the improvement of spatial saliency prediction; however, with stagnant progress in the last 3-5 years. We conduct a large-scale transfer learning study which tests different ImageNet backbones, always using the same read out architecture and learning protocol adopted from DeepGaze II. By replacing the VGG19 backbone of DeepGaze II with ResNet50 features we improve the performance on saliency prediction from 78% to 85%. However, as we continue to test better ImageNet models as backbones (such as EfficientNetB5) we observe no additional improvement on saliency prediction. By analyzing the backbones further, we find that generalization to other datasets differs substantially, with models being consistently overconfident in their fixation predictions. We show that by combining multiple backbones in a principled manner a good confidence calibration on unseen datasets can be achieved. This new model, "DeepGaze IIE", yields a significant leap in benchmark performance in and out-of-domain with a 15 percent point improvement over DeepGaze II to 93% on MIT1003, marking a new state of the art on the MIT/Tuebingen Saliency Benchmark in all available metrics (AUC: 88.3%, sAUC: 79.4%, CC: 82.4%).

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 20 code samples harvested from 2 repositories linked to this paper: 13 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 13 ran (9 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 4 samples from 1 repository, 0 ran (0 with no instrument failure; 0 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

matthias-k/DeepGaze officialmentioned on GitHubpytorchSyntology: 16 samples, 13 ran (4 instrument-failed) · 3 unverified report
islab-sophia/odisal mentioned on GitHubpytorchSyntology: 4 samples, 0 ran · 4 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

20 samples harvested: 13 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 7 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.

3ran · our draft was wrong
1ran; the contract check could not run
9ran
7unverified

Licence: 16 of the 20 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 2 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. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

matthias-k/DeepGaze official repository 16 samples, 13 ran (4 instrument-failed) · 3 unverified
Bias deepgaze_pytorch/deepgaze2e.py ran fingerprinted no licence file found · pointer only · 782fbc775dc6b910 · report fixture: returned Bias · level recorded 2026-09-22
Conv2dMultiInput deepgaze_pytorch/deepgaze2e.py ran no licence file found · pointer only · b459556b97135112 · report fixture: returned Conv2dMultiInput · level recorded 2026-09-22
DeepGazeIIIMixture deepgaze_pytorch/deepgaze2e.py ran no licence file found · pointer only · 81c3534e413bef0d · report fixture: returned DeepGazeIIIMixture · level recorded 2026-09-22
FeatureExtractor in 24 papers deepgaze_pytorch/deepgaze2e.py ran fingerprinted no licence file found · pointer only · 05a7be491393286d · report fixture: returned FeatureExtractor · level recorded 2026-09-22
Finalizer deepgaze_pytorch/deepgaze2e.py ran no licence file found · pointer only · 89450c83c8ee18d4 · report fixture: returned Finalizer · level recorded 2026-09-22
GaussianFilterNd deepgaze_pytorch/deepgaze2e.py ran no licence file found · pointer only · 9ed0d69c62c3b5dc · report fixture: returned GaussianFilterNd · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
deepgaze_pytorch/deepgaze2e.py ran no licence file found · pointer only · 17f528f7b814b15f · report fixture: returned LayerNorm · level recorded 2026-09-22
LayerNormMultiInput deepgaze_pytorch/deepgaze2e.py ran no licence file found · pointer only · 4581eabb812cb3ff · report fixture: returned LayerNormMultiInput · level recorded 2026-09-22
MixtureModel deepgaze_pytorch/deepgaze2e.py ran no licence file found · pointer only · 9be88f282c69b1b4 · report fixture: returned MixtureModel · level recorded 2026-09-22
build_saliency_network deepgaze_pytorch/deepgaze2e.py ran · our draft was wrong no licence file found · pointer only · 4b5054af2d648043 · report fixture: signature input_channels:int/0/int · returned Sequential · level recorded 2026-09-22
encode_scanpath_features deepgaze_pytorch/deepgaze2e.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 325af44c6cd8829e · report fixture: signature x_hist:Tensor/2/float, y_hist:Tensor/2/float, size:tuple/1/int, device:NoneType/0/?, include_x:bool/0/bool, include_y:bool/0/bool, include_duration:bool/0/bool · returned Tensor · level recorded 2026-09-22
gaussian_filter_1d deepgaze_pytorch/deepgaze2e.py ran · our draft was wrong no licence file found · pointer only · 27f99b6bedd193fb · report fixture: signature tensor:Tensor/4/float, dim:int/0/int, sigma:float/0/float, truncate:int/0/int, kernel_size:NoneType/0/?, padding_mode:str/0/str, padding_value:float/0/float · returned Tensor · level recorded 2026-09-22
import_class in 29 papers deepgaze_pytorch/deepgaze2e.py ran · our draft was wrong no licence file found · pointer only · fb1d63f8099f907a · report fixture: signature name:str/0/str · returned type · level recorded 2026-09-22
DeepGazeIIE deepgaze_pytorch/deepgaze2e.py unverified no licence file found · pointer only · 070fdd717ed94582 · report
build_deepgaze_mixture deepgaze_pytorch/deepgaze2e.py unverified no licence file found · pointer only · 7d46769a9a82cd86 · report
build_fixation_selection_network deepgaze_pytorch/deepgaze2e.py unverified no licence file found · pointer only · 2d1db431509c80ca · report
islab-sophia/odisal community (archive-listed) 4 samples, 0 ran · 4 unverified
build_deepgaze_mixture program/models/deepgaze2e.py unverified Apache-2.0 (permissive) · 4e411ff28ffe758d · report
build_fixation_selection_network program/models/deepgaze2e.py unverified Apache-2.0 (permissive) · 633b7efb12453cdd · report
build_saliency_network program/models/deepgaze2e.py unverified Apache-2.0 (permissive) · 9141b2bb636a8297 · report
deepgaze2e program/models/deepgaze2e.py unverified Apache-2.0 (permissive) · fa03a00d81540b0f · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for DeepGaze IIE (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for DeepGaze IIE (graph method: DeepGaze IIE). 16 bricks; individually on a fixture: 13 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. DeepGazeIIE entry · level 0 · unverified · 070fdd717ed94582
  2. MixtureModel helper · level 1 · ran · 9be88f282c69b1b4
  3. build_deepgaze_mixture model · level 0 · unverified · 7d46769a9a82cd86
  4. DeepGazeIIIMixture helper · level 1 · ran · 81c3534e413bef0d
  5. FeatureExtractor model · level 1 · ran · 05a7be491393286d
  6. Finalizer model · level 1 · ran · 89450c83c8ee18d4
  7. build_fixation_selection_network model · level 0 · unverified · 2d1db431509c80ca
  8. build_saliency_network model · level 1 · ran · our draft was wrong · 4b5054af2d648043
  9. import_class helper · level 1 · ran · our draft was wrong · fb1d63f8099f907a
  10. encode_scanpath_features helper · level 1 · ran; the contract check could not run (RAISES) · 325af44c6cd8829e
  11. GaussianFilterNd helper · level 1 · ran · 9ed0d69c62c3b5dc
  12. Bias helper · level 1 · ran · 782fbc775dc6b910
  13. Conv2dMultiInput helper · level 1 · ran · b459556b97135112
  14. LayerNorm helper · level 1 · ran · 17f528f7b814b15f
  15. LayerNormMultiInput helper · level 1 · ran · 4581eabb812cb3ff
  16. gaussian_filter_1d helper · level 1 · ran · our draft was wrong · 27f99b6bedd193fb

harvested Assembly for DeepGaze IIE (graph method: DeepGaze IIE). 5 bricks; individually on a fixture: 1 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; 1 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. deepgaze2e entry · level 0 · unverified · fa03a00d81540b0f
  2. build_deepgaze_mixture model · level 0 · unverified · 4e411ff28ffe758d
  3. build_fixation_selection_network helper · level 0 · unverified · 633b7efb12453cdd
  4. build_saliency_network helper · level 0 · unverified · 9141b2bb636a8297
  5. import_class helper · level 1 · ran · our draft was wrong · fb1d63f8099f907a

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="2105.12441") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

PredictionSaliency PredictionTransfer Learning

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