11 citations · 13 across the 13 of their papers we have counts for
14 papers
MedDiff-FT: Data-Efficient Diffusion Model Fine-tuning with Structural Guidance for Controllable Medical Image Synthesis
Jianhao Xie, Ziang Zhang, Zhenyu Weng +2
Recent advancements in deep learning for medical image segmentation are often limited by the scarcity of high-quality training data.While diffusion models provide a potential solut…
Federated Learning for Medical Image Classification: A Comprehensive Benchmark
Zhekai Zhou, Guibo Luo, Mingzhi Chen +2
The federated learning paradigm is wellsuited for the field of medical image analysis, as it can effectively cope with machine learning on isolated multicenter data while protectin…
FACT: Feature Adaptive Continual-learning Tracker for Multiple Object Tracking
Rongzihan Song, Zhenyu Weng, Huiping Zhuang +3
Multiple object tracking (MOT) involves identifying multiple targets and assigning them corresponding IDs within a video sequence, where occlusions are often encountered. Recent me…
Dual Branch Network Towards Accurate Printed Mathematical Expression Recognition
Yuqing Wang, Zhenyu Weng, Zhaokun Zhou +3
Over the past years, Printed Mathematical Expression Recognition (PMER) has progressed rapidly. However, due to the insufficient context information captured by Convolutional Neura…
Constant Sequence Extension for Fast Search Using Weighted Hamming Distance
Zhenyu Weng, Huiping Zhuang, Haizhou Li +1
Representing visual data using compact binary codes is attracting increasing attention as binary codes are used as direct indices into hash table(s) for fast non-exhaustive search.…
POAR: Towards Open Vocabulary Pedestrian Attribute Recognition
Yue Zhang, Suchen Wang, Shichao Kan +3
Pedestrian attribute recognition (PAR) aims to predict the attributes of a target pedestrian in a surveillance system. Existing methods address the PAR problem by training a multi-…
ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection
Huiping Zhuang, Zhenyu Weng, Hongxin Wei +3
Class-incremental learning (CIL) learns a classification model with training data of different classes arising progressively. Existing CIL either suffers from serious accuracy loss…
Region-aware Attention for Image Inpainting
Zhilin Huang, Chujun Qin, Zhenyu Weng +1
Recent attention-based image inpainting methods have made inspiring progress by modeling long-range dependencies within a single image. However, they tend to generate blurry conten…
Multi-Teacher Knowledge Distillation for Incremental Implicitly-Refined Classification
Longhui Yu, Zhenyu Weng, Yuqing Wang +1
Incremental learning methods can learn new classes continually by distilling knowledge from the last model (as a teacher model) to the current model (as a student model) in the seq…
Structure-aware Image Inpainting with Two Parallel Streams
Zhilin Huang, Chujun Qin, Ruixin Liu +2
Recent works in image inpainting have shown that structural information plays an important role in recovering visually pleasing results. In this paper, we propose an end-to-end arc…
Online Hashing with Similarity Learning
Zhenyu Weng, Yuesheng Zhu
Online hashing methods usually learn the hash functions online, aiming to efficiently adapt to the data variations in the streaming environment. However, when the hash functions ar…
Fast Search on Binary Codes by Weighted Hamming Distance
Zhenyu Weng, Yuesheng Zhu, Ruixin Liu
Weighted Hamming distance, as a similarity measure between binary codes and binary queries, provides superior accuracy in search tasks than Hamming distance. However, how to effici…
Online Hashing with Efficient Updating of Binary Codes
Zhenyu Weng, Yuesheng Zhu
Online hashing methods are efficient in learning the hash functions from the streaming data. However, when the hash functions change, the binary codes for the database have to be r…
Efficient Querying from Weighted Binary Codes
Zhenyu Weng, Yuesheng Zhu
Binary codes are widely used to represent the data due to their small storage and efficient computation. However, there exists an ambiguity problem that lots of binary codes share…