AI Paper Atlas

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

Dual-Phase Visual-Language Pretraining and Adaptation for Long-Tailed Multi-Label Recognition

Yongcheng Li, Xuekuan Wang, Zhifei Zhang, Cairong Zhao

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training · 0 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 STAG LLM-generated descriptions to GCL baseline (ablation)DP-VLPA · COCO-LTmAP: 48.23 -> 64.01Improved
add STAG LLM-generated descriptions to GCL baseline (ablation)DP-VLPA · VOC-LTmAP: 82.84 -> 83.21Improved
add QCL fine-grained alignment to GCL baseline (ablation)DP-VLPA · COCO-LTmAP: 48.23 -> 64.07Improved
add QCL fine-grained alignment to GCL baseline (ablation)DP-VLPA · VOC-LTmAP: 82.84 -> 83.62Improved
add DQR on top of STAG+QCL (ablation)DP-VLPA · VOC-LTmAP: 84.65 -> 88.19Improved
add DQR on top of STAG+QCL (ablation)DP-VLPA · COCO-LTmAP: 70.45 -> 72.21Improved
add COA loss on top of STAG+QCL+DQR (ablation)DP-VLPA · VOC-LTmAP: 88.19 -> 90.72Improved
add COA loss on top of STAG+QCL+DQR (ablation)DP-VLPA · COCO-LTmAP: 72.21 -> 74.42Improved
use 16 queries instead of 32 (ablation)DP-VLPA · COCO-LTmAP: 74.42 -> 69.30Hurt
use 16 queries instead of 32 (ablation)DP-VLPA · VOC-LTmAP: 90.72 -> 90.92No clear effect
use 64 queries instead of 32 (ablation)DP-VLPA · COCO-LTmAP: 74.42 -> 65.44Hurt
use 64 queries instead of 32 (ablation)DP-VLPA · VOC-LTmAP: 90.72 -> 89.48Hurt

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