14 citations · 36 across the 14 of their papers we have counts for
7 papers · 1 filter
EMOv2: Pushing 5M Vision Model Frontier
Jiangning Zhang, Teng Hu, Haoyang He +6
This work focuses on developing parameter-efficient and lightweight models for dense predictions while trading off parameters, FLOPs, and performance. Our goal is to set up the new…
MobileMamba: Lightweight Multi-Receptive Visual Mamba Network
Haoyang He, Jiangning Zhang, Yuxuan Cai +7
Previous research on lightweight models has primarily focused on CNNs and Transformer-based designs. CNNs, with their local receptive fields, struggle to capture long-range depende…
LLaVA-KD: A Framework of Distilling Multimodal Large Language Models
Yuxuan Cai, Jiangning Zhang, Haoyang He +7
The success of Large Language Models (LLMs) has inspired the development of Multimodal Large Language Models (MLLMs) for unified understanding of vision and language. However, the…
Learning Multi-view Anomaly Detection with Efficient Adaptive Selection
Haoyang He, Jiangning Zhang, Guanzhong Tian +2
This study explores the recently proposed and challenging multi-view Anomaly Detection (AD) task. Single-view tasks will encounter blind spots from other perspectives, resulting in…
A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detection
Jiangning Zhang, Haoyang He, Zhenye Gan +7
Visual anomaly detection aims to identify anomalous regions in images through unsupervised learning paradigms, with increasing application demand and value in fields such as indust…
PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning
Qingdong He, Jiangning Zhang, Jinlong Peng +4
Transformers have revolutionized the point cloud learning task, but the quadratic complexity hinders its extension to long sequence and makes a burden on limited computational reso…
MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection
Haoyang He, Yuhu Bai, Jiangning Zhang +7
Recent advancements in anomaly detection have seen the efficacy of CNN- and transformer-based approaches. However, CNNs struggle with long-range dependencies, while transformers ar…