6 papers
DirMixE: Harnessing Test Agnostic Long-tail Recognition with Hierarchical Label Variations
Zhiyong Yang, Qianqian Xu, Sicong Li +3
This paper explores test-agnostic long-tail recognition, a challenging long-tail task where the test label distributions are unknown and arbitrarily imbalanced. We argue that the v…
A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization
Zitai Wang, Qianqian Xu, Zhiyong Yang +4
Due to the inherent imbalance in real-world datasets, naïve Empirical Risk Minimization (ERM) tends to bias the learning process towards the majority classes, hindering generaliza…
Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification
Sicong Li, Qianqian Xu, Zhiyong Yang +4
Real-world datasets often follow a long-tailed distribution, making generalization to tail classes difficult. Recent methods resorted to long-tail variants of Sharpness-Aware Minim…
One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework
Feiran Li, Qianqian Xu, Shilong Bao +3
Concept erasing has recently emerged as an effective paradigm to prevent text-to-image diffusion models from generating visually undesirable or even harmful content. However, curre…
Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques
Benyuan Meng, Qianqian Xu, Zitai Wang +3
Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as feat…
Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features
Benyuan Meng, Qianqian Xu, Zitai Wang +2
Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense fea…