Papers › Learning Concise and Descriptive Attributes for Visual Recognition

Learning Concise and Descriptive Attributes for Visual Recognition

7 Aug 2023ICCV 2023 1arXiv:2308.03685archive 2025-07-28

An Yan, Yu Wang, Yiwu Zhong, chengyu dong, Zexue He, Yujie Lu, William Wang, Jingbo Shang, Julian McAuley

Recent advances in foundation models present new opportunities for interpretable visual recognition -- one can first query Large Language Models (LLMs) to obtain a set of attributes that describe each class, then apply vision-language models to classify images via these attributes. Pioneering work shows that querying thousands of attributes can achieve performance competitive with image features. However, our further investigation on 8 datasets reveals that LLM-generated attributes in a large quantity perform almost the same as random words. This surprising finding suggests that significant noise may be present in these attributes. We hypothesize that there exist subsets of attributes that can maintain the classification performance with much smaller sizes, and propose a novel learning-to-search method to discover those concise sets of attributes. As a result, on the CUB dataset, our method achieves performance close to that of massive LLM-generated attributes (e.g., 10k attributes for CUB), yet using only 32 attributes in total to distinguish 200 bird species. Furthermore, our new paradigm demonstrates several additional benefits: higher interpretability and interactivity for humans, and the ability to summarize knowledge for a recognition task.

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 9 code samples harvested from 3 repositories linked to this paper: 4 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 5 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 4 samples from 2 repositories, 1 ran (1 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 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.

wangyu-ustc/LM4CV officialpytorchSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
clearproject/clear mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
trustworthy-ml-lab/vlg-cbm mentioned on GitHubpytorchSyntology: 3 samples, 0 ran · 3 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

9 samples harvested: 4 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 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.

4ran
5unverified

Licence: 9 of the 9 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 3 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 1 sample 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.

wangyu-ustc/LM4CV official repository 5 samples, 3 ran (0 instrument-failed) · 2 unverified
clean_label utils/dataset_utils.py ran fingerprinted no licence file found · pointer only · 0ccd84c8e9497cf2 · report fixture: signature true_labels:list/1/int · returned ndarray · level recorded 2026-09-24
construct_attributes_save_path utils/train_utils.py ran no licence file found · pointer only · 4f9e97f458509f1e · report fixture: signature cfg:dict/0/? · returned str · level recorded 2026-09-24
get_transform_cub dataset.py ran no licence file found · pointer only · 7e3b27ee403aa509 · report fixture: signature model_type:str/0/str, train:bool/0/bool, augment_data:bool/0/bool · returned Compose · level recorded 2026-09-24
cluster in 18 papers cluster.py unverified no licence file found · pointer only · dbbc089ece1bfd75 · report
get_model in 368 papers utils/train_utils.py unverified no licence file found · pointer only · ffcdc952d42599d2 · report
clearproject/clear community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SimpleScoreNet score_based_concepts.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 71eda9d2ebbc932a · report fixture: returned SimpleScoreNet · level recorded 2026-09-22
trustworthy-ml-lab/vlg-cbm community (archive-listed) 3 samples, 0 ran · 3 unverified
glm_saga model/cbm.py unverified no licence file found · pointer only · c98ed8b875f0eb45 · report
train_saga model/cbm.py unverified no licence file found · pointer only · 9f6c1e7f85af77cc · report
train_sparse_final model/cbm.py unverified no licence file found · pointer only · 82bf6af4df94e99b · 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 learning-to-search method (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for learning-to-search method (graph method: learning-to-search method). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 2 siblings

  1. SimpleScoreNet entry · level 1 · ran · 71eda9d2ebbc932a

harvested Assembly for learning-to-search method (graph method: learning-to-search method). 11 bricks; individually on a fixture: 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. train_sparse_final entry · level 0 · unverified · 82bf6af4df94e99b
  2. glm_saga helper · level 0 · unverified · c98ed8b875f0eb45
  3. elastic_loss_and_acc_loader helper · level 1 · ran · our draft was wrong · 22bce7009cca4385
  4. get_device helper · level 1 · ran · our draft was wrong · 406014b884a2aaa7
  5. maximum_reg_loader helper · level 1 · ran · honoured contract · 28bd63a25ca690f6
  6. train_saga helper · level 0 · unverified · 9f6c1e7f85af77cc
  7. elastic_loss_and_acc helper · level 1 · ran · our draft was wrong · db058f8fcbe2bd2f
  8. group_threshold helper · level 1 · ran · our draft was wrong · 6bf94bee8741ddb9
  9. group_threshold_with_shrinkage helper · level 1 · ran · our draft was wrong · eae0b64c4f002409
  10. soft_threshold helper · level 1 · ran · honoured contract · bfe4b187a1c5aeaf
  11. soft_threshold_with_shrinkage helper · level 1 · ran · honoured contract · 9fe33b70d272646e

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="2308.03685") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Descriptive

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