2026
Dual-Phase Visual-Language Pretraining and Adaptation for Long-Tailed Multi-Label Recognition
AAAI 2026technical
Long-Tailed Multi-Label Recognition (LTML) is a critical yet challenging task due to two core issues: the severe scarcity of training samples for rare "tail" classes, and the complex co-occurrence patterns among labels that often lead to biased models. To address this, we propose DP-VLPA, a novel Du