4 papers
Learning from Imperfect Text Guidance: Robust Long-Tail Visual Recognition with High-Noise Label
Mengke Li, Haiquan Ling, Yiqun Zhang +2
Real-world data often exhibit long-tailed distributions with numerous noisy labels, substantially degrading the performance of deep models. While prior research has made progress i…
Improving Sparse Autoencoder with Dynamic Attention
Dongsheng Wang, Jinsen Zhang, Dawei Su +1
Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in foundation models by disentangling features into a sparse set of concepts…
Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis
Mengke Li, Lihao Chen, Peng Zhang +2
Parameter-efficient fine-tuning strategies for foundation models in 1D textual and 2D visual analysis have demonstrated remarkable efficacy. However, due to the scarcity of point c…
PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion
Mengke Li, Zhikai Hu, Yang Lu +3
The imbalanced distribution of long-tailed data presents a significant challenge for deep learning models, causing them to prioritize head classes while neglecting tail classes. Tw…