AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

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

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

ECCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training · 67 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add CVLP class-wise pre-training (with distillation) (ablation)VL-LTR (ResNet-50) · ImageNet-LToverall top-1 accuracy (%): 62.8 -> 70.1Improved
initialize with CLIP pre-trained weights (ablation)VL-LTR (ResNet-50) · ImageNet-LToverall top-1 accuracy (%): 46.8 -> 70.1Improved
add distillation loss from CLIP in pre-training (ablation)VL-LTR (ResNet-50) · ImageNet-LToverall top-1 accuracy (%): 66.2 -> 70.1Improved
use LGR head instead of FC head (ablation)VL-LTR (ResNet-50) · ImageNet-LToverall top-1 accuracy (%): 62.1 -> 70.1Improved
use LGR head instead of KNN head (ablation)VL-LTR (ResNet-50) · ImageNet-LToverall top-1 accuracy (%): 63.9 -> 70.1Improved
use anchor sentence selection instead of Cut Off (ablation)VL-LTR (ResNet-50) · ImageNet-LToverall top-1 accuracy (%): 69.7 -> 70.1Improved
add logits distillation (lambda 0.5) instead of feature distillation (lambda 0.5) (ablation)VL-LTR (ResNet-50) · ImageNet-LToverall top-1 accuracy (%): 68.0 -> 70.1Improved
raise logits distillation weight lambda from 0.1 to 0.5 (ablation)VL-LTR (ResNet-50) · ImageNet-LToverall top-1 accuracy (%): 68.3 -> 70.1Improved
add Wikipedia text to prompt-only descriptions (ablation)VL-LTR (ResNet-50) · ImageNet-LToverall top-1 accuracy (%): 69.4 -> 70.1Improved
add Wikipedia text to prompt-only descriptions (ablation)VL-LTR (ResNet-50) · Places-LToverall top-1 accuracy (%): 47.3 -> 48.0Improved
add class-level text and CVLP/LGR to vision-only baseline (few-shot)Baseline (ResNet-50) · ImageNet-LTfew-shot accuracy (%): 34.5 -> 50.8Improved
add VL-LTR to vision-only baselineBaseline (ResNet-50) · Places-LToverall top-1 accuracy (%): 39.7 -> 48.0Improved

Later papers that compared with this method

3 later accepted papers report VL-LTR as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy