Papers › Novel Class Discovery for Ultra-Fine-Grained Visual Categorization

Novel Class Discovery for Ultra-Fine-Grained Visual Categorization

10 May 2024CVPR 2024 1arXiv:2405.06283archive 2025-07-28

Yu Liu, Yaqi Cai, Qi Jia, Binglin Qiu, Weimin WANG, Nan Pu

Ultra-fine-grained visual categorization (Ultra-FGVC) aims at distinguishing highly similar sub-categories within fine-grained objects, such as different soybean cultivars. Compared to traditional fine-grained visual categorization, Ultra-FGVC encounters more hurdles due to the small inter-class and large intra-class variation. Given these challenges, relying on human annotation for Ultra-FGVC is impractical. To this end, our work introduces a novel task termed Ultra-Fine-Grained Novel Class Discovery (UFG-NCD), which leverages partially annotated data to identify new categories of unlabeled images for Ultra-FGVC. To tackle this problem, we devise a Region-Aligned Proxy Learning (RAPL) framework, which comprises a Channel-wise Region Alignment (CRA) module and a Semi-Supervised Proxy Learning (SemiPL) strategy. The CRA module is designed to extract and utilize discriminative features from local regions, facilitating knowledge transfer from labeled to unlabeled classes. Furthermore, SemiPL strengthens representation learning and knowledge transfer with proxy-guided supervised learning and proxy-guided contrastive learning. Such techniques leverage class distribution information in the embedding space, improving the mining of subtle differences between labeled and unlabeled ultra-fine-grained classes. Extensive experiments demonstrate that RAPL significantly outperforms baselines across various datasets, indicating its effectiveness in handling the challenges of UFG-NCD. Code is available at https://github.com/SSDUT-Caiyq/UFG-NCD.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2405.06283")

Code

Syntology Ran 12 of 13 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · violated contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it; 8 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 12 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ssdut-caiyq/ufg-ncd officialmentioned in papermentioned on GitHubpytorch 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

13 samples harvested; 12 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
2ran · our draft was wrong
1ran · fixture could not drive it
8ran
1unverified

Licence: 13 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 SSDUT-Caiyq/UFG-NCD. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

conv1x1 SSDUT-Caiyq/UFG-NCD/models/resnet50.py official repository ran · our draft was wrong no licence file found · pointer only · 158bf4c3a5f11f04 · report
conv3x3 SSDUT-Caiyq/UFG-NCD/models/resnet50.py official repository ran · our draft was wrong no licence file found · pointer only · 29df79c9fdb0cee8 · report
drop_path SSDUT-Caiyq/UFG-NCD/models/vision_transformer.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 55120f2026b56aa2 · report
get_multicrop_transform SSDUT-Caiyq/UFG-NCD/FineGrained/augmentations/resnet_transform.py official repository ran no licence file found · pointer only · 989da03c9daf897b · report
get_swa_model_ SSDUT-Caiyq/UFG-NCD/utils/get_swa_model.py official repository ran no licence file found · pointer only · b0cada34bcabce0e · report
get_train_val_indices SSDUT-Caiyq/UFG-NCD/FineGrained/cifar.py official repository ran no licence file found · pointer only · f3d4ce738fce6463 · report
get_transforms SSDUT-Caiyq/UFG-NCD/FineGrained/augmentations/resnet_transform.py official repository ran no licence file found · pointer only · 3a66d453e02b481a · report
pdist SSDUT-Caiyq/UFG-NCD/utils/Relaxed_losses.py official repository ran no licence file found · pointer only · 2586b178b48ed611 · report
str2bool SSDUT-Caiyq/UFG-NCD/discovery_learning.py official repository ran · violated contract no licence file found · pointer only · 7c508037b40522af · report
subsample_classes SSDUT-Caiyq/UFG-NCD/FineGrained/cifar.py official repository ran no licence file found · pointer only · 905aedc67507c77b · report
subsample_dataset SSDUT-Caiyq/UFG-NCD/FineGrained/cifar.py official repository ran no licence file found · pointer only · 6b976c03af7e2ffc · report
vit_small SSDUT-Caiyq/UFG-NCD/models/vision_transformer.py official repository ran no licence file found · pointer only · 6322d561ced017bc · report
vit_tiny SSDUT-Caiyq/UFG-NCD/models/vision_transformer.py official repository unverified no licence file found · pointer only · 92e76c9d03c24769 · report

Tasks

Contrastive LearningFine-Grained Visual CategorizationNovel Class DiscoveryRepresentation LearningTransfer 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