Papers › Active Visual Exploration Based on Attention-Map Entropy

Active Visual Exploration Based on Attention-Map Entropy

11 Mar 2023arXiv:2303.06457archive 2025-07-28

Adam Pardyl, Grzegorz Rypeść, Grzegorz Kurzejamski, Bartosz Zieliński, Tomasz Trzciński

Active visual exploration addresses the issue of limited sensor capabilities in real-world scenarios, where successive observations are actively chosen based on the environment. To tackle this problem, we introduce a new technique called Attention-Map Entropy (AME). It leverages the internal uncertainty of the transformer-based model to determine the most informative observations. In contrast to existing solutions, it does not require additional loss components, which simplifies the training. Through experiments, which also mimic retina-like sensors, we show that such simplified training significantly improves the performance of reconstruction, segmentation and classification on publicly available datasets.

PaperPDFCodeCode 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 15 code samples harvested from 1 repository linked to this paper: 10 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 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: 15 samples from 1 repository, 10 ran (8 with no instrument failure; 2 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.

apardyl/ame officialmentioned in paperpytorchApache-2.0Syntology: 15 samples, 10 ran (2 instrument-failed) · 5 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

15 samples harvested: 10 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 5 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
1ran; the contract check could not run
8ran
5unverified

Licence: 0 of the 15 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 apardyl/ame. “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.

apardyl/ame official repository 15 samples, 10 ran (2 instrument-failed) · 5 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
architectures/selectors.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · dfb4c043722a654f · report fixture: returned Attention · level recorded 2026-09-22
BaseArchitecture architectures/selectors.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 58f4f511ca98ef5e · report fixture: returned BaseArchitecture · level recorded 2026-09-22
BaseDataModule architectures/selectors.py ran Apache-2.0 (permissive) · 9e7fee3e5fb1d70f · report fixture: returned BaseDataModule · level recorded 2026-09-22
BaseSegmentationDataModule architectures/selectors.py ran Apache-2.0 (permissive) · 7b2d49217fdd340e · report fixture: returned BaseSegmentationDataModule · level recorded 2026-09-22
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
architectures/selectors.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · d3c8bd812a7774f9 · report fixture: returned Block · level recorded 2026-09-22
MaeScheduler architectures/selectors.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · e5a019fc9ff41b6f · report fixture: returned MaeScheduler · level recorded 2026-09-22
MaskedAutoencoderViT in 14 papers architectures/selectors.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · d3f43c1a65fc5f44 · report fixture: returned MaskedAutoencoderViT · level recorded 2026-09-22
Retinalizer architectures/selectors.py ran Apache-2.0 (permissive) · b98f3360f10e46f2 · report fixture: returned Retinalizer · level recorded 2026-09-22
dict_to_cpu in 5 papers architectures/selectors.py ran · our draft was wrong Apache-2.0 (permissive) · afe739802249075b · report fixture: signature tensor_dict:dict/0/? · returned dict · level recorded 2026-09-22
get_2d_sincos_pos_embed in 170 papers architectures/selectors.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) · f10b0368daa03927 · report fixture: signature embed_dim:int/0/int, grid_size:tuple/1/int, cls_token:bool/0/bool · returned ndarray · level recorded 2026-09-22
AttentionGlimpseSelector architectures/selectors.py unverified Apache-2.0 (permissive) · 87ceaab158726213 · report
BaseGlimpseMae architectures/selectors.py unverified Apache-2.0 (permissive) · 4acaf185025d6cc9 · report
BaseGlimpseSelector architectures/selectors.py unverified Apache-2.0 (permissive) · 526634f146a3e767 · report
MetricMixin architectures/selectors.py unverified Apache-2.0 (permissive) · 9c8b6524d1d9c312 · report
mae_vit_large_patch16_dec512d8b architectures/selectors.py unverified Apache-2.0 (permissive) · 287ba7a4489fb320 · 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 Attention-Map Entropy (AME) (graph method: Attention-Map Entropy (AME)). 17 bricks; individually on a fixture: 11 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

  1. AttentionGlimpseSelector entry · level 0 · unverified · 87ceaab158726213
  2. BaseGlimpseSelector helper · level 0 · unverified · 526634f146a3e767
  3. BaseGlimpseMae model · level 0 · unverified · 4acaf185025d6cc9
  4. BaseArchitecture helper · level 1 · ran · 58f4f511ca98ef5e
  5. BaseDataModule helper · level 1 · ran · 9e7fee3e5fb1d70f
  6. BaseSegmentationDataModule helper · level 1 · ran · 7b2d49217fdd340e
  7. Retinalizer helper · level 1 · ran · b98f3360f10e46f2
  8. dict_to_cpu helper · level 1 · ran · our draft was wrong · afe739802249075b
  9. MaeScheduler helper · level 1 · ran · e5a019fc9ff41b6f
  10. MetricMixin helper · level 0 · unverified · 9c8b6524d1d9c312
  11. Attention helper · level 1 · ran · dfb4c043722a654f
  12. Block helper · level 1 · ran · d3c8bd812a7774f9
  13. MaskedAutoencoderViT model · level 1 · ran · d3f43c1a65fc5f44
  14. get_1d_sincos_pos_embed_from_grid helper · level 1 · ran; the contract check could not run · 5c8ea92d43ead77d
  15. get_2d_sincos_pos_embed helper · level 1 · ran; the contract check could not run (RAISES) · f10b0368daa03927
  16. get_2d_sincos_pos_embed_from_grid helper · level 0 · unverified · 2884deadbb637c3e
  17. mae_vit_large_patch16_dec512d8b helper · level 0 · unverified · 287ba7a4489fb320

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="2303.06457") returns these assemblies with each brick's role and wiring (how to connect).

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