14 citations · 23 across the 7 of their papers we have counts for
8 papers
MODAL: Multi-Modal Object Re-ID via Model-Driven Sparse Decoupling and Text-Image Differential Filtering
Chengbo Huang, Jun-Jie Huang, Long Lan +5
Multi-modal object re-identification (Re-ID) aims to facilitate cross-camera object retrieval in complex environments by leveraging complementary information from visual (e.g., RGB…
AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs
Wenxiang Lin, Juntao Huang, Luhan Zhang +5
Quantization is a key method for reducing the GPU memory requirement of training large language models (LLMs). Yet, current approaches are ineffective for 4-bit activations and 8-b…
EASE: Federated Multimodal Unlearning via Entanglement-Aware Anchor Closure
Zihao Ding, Beining Wu, Jun Huang
Federated Multimodal Learning (FML) trains multimodal models across decentralized clients while keeping their image-text pairs private. However, joint embedding training entangles…
Combined Dictionary Unfolding Network with Gradient-Adaptive Fidelity for Transferable Multi-Source Fusion
Ge Luo, Jun-Jie Huang, Qi Yu +6
Deep Unfolding Network-based methods have emerged as effective solutions for multi-source image fusion by combining model-driven iterative optimization with data-driven deep learni…
A Lightweight Deep Exclusion Unfolding Network for Single Image Reflection Removal
Jun-Jie Huang, Tianrui Liu, Zihan Chen +3
Single Image Reflection Removal (SIRR) is a canonical blind source separation problem and refers to the issue of separating a reflection-contaminated image into a transmission and…
Learning-Based Reconstruction of FRI Signals
Vincent C. H. Leung, Jun-Jie Huang, Yonina C. Eldar +1
Finite Rate of Innovation (FRI) sampling theory enables reconstruction of classes of continuous non-bandlimited signals that have a small number of free parameters from their low-r…
Learning Deep Analysis Dictionaries -- Part II: Convolutional Dictionaries
Jun-Jie Huang, Pier Luigi Dragotti
In this paper, we introduce a Deep Convolutional Analysis Dictionary Model (DeepCAM) by learning convolutional dictionaries instead of unstructured dictionaries as in the case of d…
Reconstruction of FRI Signals using Deep Neural Network Approaches
Vincent C. H. Leung, Jun-Jie Huang, Pier Luigi Dragotti
Finite Rate of Innovation (FRI) theory considers sampling and reconstruction of classes of non-bandlimited continuous signals that have a small number of free parameters, such as a…