Papers › VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition

VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition

26 Nov 2021arXiv:2111.13579archive 2025-07-28

Changyao Tian, Wenhai Wang, Xizhou Zhu, Jifeng Dai, Yu Qiao

Deep learning-based models encounter challenges when processing long-tailed data in the real world. Existing solutions usually employ some balancing strategies or transfer learning to deal with the class imbalance problem, based on the image modality. In this work, we present a visual-linguistic long-tailed recognition framework, termed VL-LTR, and conduct empirical studies on the benefits of introducing text modality for long-tailed recognition (LTR). Compared to existing approaches, the proposed VL-LTR has the following merits. (1) Our method can not only learn visual representation from images but also learn corresponding linguistic representation from noisy class-level text descriptions collected from the Internet; (2) Our method can effectively use the learned visual-linguistic representation to improve the visual recognition performance, especially for classes with fewer image samples. We also conduct extensive experiments and set the new state-of-the-art performance on widely-used LTR benchmarks. Notably, our method achieves 77.2% overall accuracy on ImageNet-LT, which significantly outperforms the previous best method by over 17 points, and is close to the prevailing performance training on the full ImageNet. Code is available at https://github.com/ChangyaoTian/VL-LTR.

PaperPDFCode

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

Code

ChangyaoTian/VL-LTR 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationLong-tail LearningTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification iNaturalist 2018 VL-LTR (ViT-B-16) Top-1 Accuracy 81.0% #14 of 60 Archive leaderboard report
Image Classification iNaturalist 2018 VL-LTR (ResNet-50) Top-1 Accuracy 74.6% #29 of 60 Archive leaderboard report
Long-tail Learning ImageNet-LT VL-LTR (ViT-B-16) Top-1 Accuracy 77.2 #5 of 69 Archive leaderboard report
Long-tail Learning ImageNet-LT VL-LTR (ResNet-50) Top-1 Accuracy 70.1 #9 of 69 Archive leaderboard report
Long-tail Learning Places-LT VL-LTR (ViT-B-16) Top-1 Accuracy 50.1 #4 of 29 Archive leaderboard report
Long-tail Learning Places-LT VL-LTR (ResNet-50) Top-1 Accuracy 48.0 #7 of 29 Archive leaderboard report
Long-tail Learning iNaturalist 2018 VL-LTR (ViT-B-16) Top-1 Accuracy 81.0% #4 of 43 Archive leaderboard report
Long-tail Learning iNaturalist 2018 VL-LTR (ResNet-50) Top-1 Accuracy 74.6% #17 of 43 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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