5 papers
Attention Transfer Is Not Universally Effective for Vision Transformers
Huaiyuan Qin, Muli Yang, Gabriel James Goenawan +4
A recent work shows that Attention Transfer, which transfers only the attention patterns from a pre-trained teacher Vision Transformer (ViT) to a randomly initialized standard stud…
Beyond Loss Values: Robust Dynamic Pruning via Loss Trajectory Alignment
Huaiyuan Qin, Muli Yang, Gabriel James Goenawan +5
Existing dynamic data pruning methods often fail under noisy-label settings, as they typically rely on per-sample loss as the ranking criterion. This could mistakenly lead to prese…
Conditional Representation Learning for Customized Tasks
Honglin Liu, Chao Sun, Peng Hu +2
Conventional representation learning methods learn a universal representation that primarily captures dominant semantics, which may not always align with customized downstream task…
Learning with Dual-level Noisy Correspondence for Multi-modal Entity Alignment
Haobin Li, Yijie Lin, Peng Hu +2
Multi-modal entity alignment (MMEA) aims to identify equivalent entities across heterogeneous multi-modal knowledge graphs (MMKGs), where each entity is described by attributes fro…
DUDE: Diffusion-Based Unsupervised Cross-Domain Image Retrieval
Ruohong Yang, Peng Hu, Yunfan Li +1
Unsupervised cross-domain image retrieval (UCIR) aims to retrieve images of the same category across diverse domains without relying on annotations. Existing UCIR methods, which al…