439 citations · 1.1k across the 32 of their papers we have counts for
32 papers
Multi-Centroid Representation Network for Domain Adaptive Person Re-ID
Yuhang Wu, Tengteng Huang, Haotian Yao +5
Recently, many approaches tackle the Unsupervised Domain Adaptive person re-identification (UDA re-ID) problem through pseudo-label-based contrastive learning. During training, a u…
Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework
Tengteng Huang, Yifan Sun, Xun Wang +2
Model smoothing is of central importance for obtaining a reliable teacher model in the student-teacher framework, where the teacher generates surrogate supervision signals to train…
Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning
Chi Zhang, Henghui Ding, Guosheng Lin +3
Few-shot learning aims to adapt knowledge learned from previous tasks to novel tasks with only a limited amount of labeled data. Research literature on few-shot learning exhibits g…
Scalable Data Annotation Pipeline for High-Quality Large Speech Datasets Development
Mingkuan Liu, Chi Zhang, Hua Xing +4
This paper introduces a human-in-the-loop (HITL) data annotation pipeline to generate high-quality, large-scale speech datasets. The pipeline combines human and machine advantages…
Calibrating Class Activation Maps for Long-Tailed Visual Recognition
Chi Zhang, Guosheng Lin, Lvlong Lai +2
Real-world visual recognition problems often exhibit long-tailed distributions, where the amount of data for learning in different categories shows significant imbalance. Standard…
Binocular Mutual Learning for Improving Few-shot Classification
Ziqi Zhou, Xi Qiu, Jiangtao Xie +2
Most of the few-shot learning methods learn to transfer knowledge from datasets with abundant labeled data (i.e., the base set). From the perspective of class space on base set, ex…
Temporal Knowledge Consistency for Unsupervised Visual Representation Learning
Weixin Feng, Yuanjiang Wang, Lihua Ma +2
The instance discrimination paradigm has become dominant in unsupervised learning. It always adopts a teacher-student framework, in which the teacher provides embedded knowledge as…
DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection
Limeng Qiao, Yuxuan Zhao, Zhiyuan Li +3
Few-shot object detection, which aims at detecting novel objects rapidly from extremely few annotated examples of previously unseen classes, has attracted significant research inte…
M2IOSR: Maximal Mutual Information Open Set Recognition
Xin Sun, Henghui Ding, Chi Zhang +2
In this work, we aim to address the challenging task of open set recognition (OSR). Many recent OSR methods rely on auto-encoders to extract class-specific features by a reconstruc…
IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID
Yongxing Dai, Jun Liu, Yifan Sun +3
Unsupervised domain adaptive person re-identification (UDA re-ID) aims at transferring the labeled source domain's knowledge to improve the model's discriminability on the unlabele…
Few-shot Segmentation with Optimal Transport Matching and Message Flow
Weide Liu, Chi Zhang, Henghui Ding +2
We tackle the challenging task of few-shot segmentation in this work. It is essential for few-shot semantic segmentation to fully utilize the support information. Previous methods…
More Separable and Easier to Segment: A Cluster Alignment Method for Cross-Domain Semantic Segmentation
Shuang Wang, Dong Zhao, Yi Li +5
Feature alignment between domains is one of the mainstream methods for Unsupervised Domain Adaptation (UDA) semantic segmentation. Existing feature alignment methods for semantic s…
Efficient DETR: Improving End-to-End Object Detector with Dense Prior
Zhuyu Yao, Jiangbo Ai, Boxun Li +1
The recently proposed end-to-end transformer detectors, such as DETR and Deformable DETR, have a cascade structure of stacking 6 decoder layers to update object queries iteratively…
Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales
Yifan Sun, Yuke Zhu, Yuhan Zhang +4
This paper introduces a new fundamental characteristic, \ie, the dynamic range, from real-world metric tools to deep visual recognition. In metrology, the dynamic range is a basic…
Memory-based Jitter: Improving Visual Recognition on Long-tailed Data with Diversity In Memory
Jialun Liu, Jingwei Zhang, Yi yang +3
This paper considers deep visual recognition on long-tailed data. To be general, we consider two applied scenarios, \ie, deep classification and deep metric learning. Under the lon…
Learning Disentangled Representations of Video with Missing Data
Armand Comas-Massagué, Chi Zhang, Zlatan Feric +2
Missing data poses significant challenges while learning representations of video sequences. We present Disentangled Imputed Video autoEncoder (DIVE), a deep generative model that…
Unsupervised Learning of Depth, Optical Flow and Pose with Occlusion from 3D Geometry
Guangming Wang, Chi Zhang, Hesheng Wang +3
In autonomous driving, monocular sequences contain lots of information. Monocular depth estimation, camera ego-motion estimation and optical flow estimation in consecutive frames a…
Cross-Spectrum Dual-Subspace Pairing for RGB-infrared Cross-Modality Person Re-Identification
Xing Fan, Hao Luo, Chi Zhang +1
Due to its potential wide applications in video surveillance and other computer vision tasks like tracking, person re-identification (ReID) has become popular and been widely inves…
Circle Loss: A Unified Perspective of Pair Similarity Optimization
Yifan Sun, Changmao Cheng, Yuhan Zhang +4
This paper provides a pair similarity optimization viewpoint on deep feature learning, aiming to maximize the within-class similarity and minimize the between-class similarit…
Vehicle Re-identification with Viewpoint-aware Metric Learning
Ruihang Chu, Yifan Sun, Yadong Li +3
This paper considers vehicle re-identification (re-ID) problem. The extreme viewpoint variation (up to 180 degrees) poses great challenges for existing approaches. Inspired by the…
Re-ID Driven Localization Refinement for Person Search
Chuchu Han, Jiacheng Ye, Yunshan Zhong +4
Person search aims at localizing and identifying a query person from a gallery of uncropped scene images. Different from person re-identification (re-ID), its performance also depe…
Re-Identification Supervised Texture Generation
Jian Wang, Yunshan Zhong, Yachun Li +2
The estimation of 3D human body pose and shape from a single image has been extensively studied in recent years. However, the texture generation problem has not been fully discusse…
Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification
Yifan Sun, Qin Xu, Yali Li +4
This paper considers a realistic problem in person re-identification (re-ID) task, i.e., partial re-ID. Under partial re-ID scenario, the images may contain a partial observation o…
STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification
Hao Luo, Xing Fan, Chi Zhang +1
Partial person re-identification (ReID) is a challenging task because only partial information of person images is available for matching target persons. Few studies, especially on…