183 citations · 711 across the 37 of their papers we have counts for
9 papers · 1 filter
Learned Block-based Hybrid Image Compression
Yaojun Wu, Xin Li, Zhizheng Zhang +2
Recent works on learned image compression perform encoding and decoding processes in a full-resolution manner, resulting in two problems when deployed for practical applications. F…
FAN: Frequency Aggregation Network for Real Image Super-resolution
Yingxue Pang, Xin Li, Xin Jin +4
Single image super-resolution (SISR) aims to recover the high-resolution (HR) image from its low-resolution (LR) input image. With the development of deep learning, SISR has achiev…
Hierarchical Context Embedding for Region-based Object Detection
Zhao-Min Chen, Xin Jin, Borui Zhao +2
State-of-the-art two-stage object detectors apply a classifier to a sparse set of object proposals, relying on region-wise features extracted by RoIPool or RoIAlign as inputs. The…
Learning Disentangled Feature Representation for Hybrid-distorted Image Restoration
Xin Li, Xin Jin, Jianxin Lin +5
Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions. Existing HD-IR approaches usually ignore the inher…
Global Distance-distributions Separation for Unsupervised Person Re-identification
Xin Jin, Cuiling Lan, Wenjun Zeng +1
Supervised person re-identification (ReID) often has poor scalability and usability in real-world deployments due to domain gaps and the lack of annotations for the target domain d…
Feature Alignment and Restoration for Domain Generalization and Adaptation
Xin Jin, Cuiling Lan, Wenjun Zeng +1
For domain generalization (DG) and unsupervised domain adaptation (UDA), cross domain feature alignment has been widely explored to pull the feature distributions of different doma…
Style Normalization and Restitution for Generalizable Person Re-identification
Xin Jin, Cuiling Lan, Wenjun Zeng +2
Existing fully-supervised person re-identification (ReID) methods usually suffer from poor generalization capability caused by domain gaps. The key to solving this problem lies in…
Exploring Categorical Regularization for Domain Adaptive Object Detection
Chang-Dong Xu, Xing-Ran Zhao, Xin Jin +1
In this paper, we tackle the domain adaptive object detection problem, where the main challenge lies in significant domain gaps between source and target domains. Previous work see…
Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification
Xin Jin, Cuiling Lan, Wenjun Zeng +1
Object re-identification (re-id) aims to identify a specific object across times or camera views, with the person re-id and vehicle re-id as the most widely studied applications. R…