3

THOR: A Generic Energy Estimation Approach for On-Device Training

Jiaru Zhang, Zesong Wang, Hao Wang, Tao Song, Huai-an Su, Rui Chen, Yang Hua, Xiangwei Zhou, Ruhui Ma, Miao Pan, Haibing Guan

Exploring Diffusion Models' Corruption Stage in Few-Shot Fine-tuning and Mitigating with Bayesian Neural Networks

Xiaoyu Wu, Jiaru Zhang, Yang Hua, Bohan Lyu, Hao Wang, Tao Song, Haibing Guan

Exploring Diffusion Models' Corruption Stage in Few-Shot Fine-tuning and Mitigating with Bayesian Neural Networks

All Frequency Components Matter: A Learnable Frequency Component Compression Framework for Adversarial Defense

Xiaoyu Wu, Yang Hua, Tao Song, Hao Wang, Jiaru Zhang, Zhengui Xue, Ruhui Ma, Haibing Guan

Generalized Tensor-based Multiple Feature Fusion Network using Block Decomposition

In this paper, we propose a multiple feature fusion method using tensor Block decomposition. Theoretically, it is a general form of two previous tensor decomposition approaches and holds strengths from both of them. Based on the Block decomposition, we construct the corresponding Multiple feature Block Fusion Network (MBFN) practically. Our MBFN is applicable to both unimodal features and multimodal features and it can fuse multiple features at the same time.

Jiaru Zhang, Yang Hua, Zhengui Xue, Tao Song, Ruhui Ma, Haibing Guan

Generalized Tensor-based Multiple Feature Fusion Network using Block Decomposition