24 citations · 103 across the 13 of their papers we have counts for
14 papers
Diverse Cotraining Makes Strong Semi-Supervised Segmentor
Yijiang Li, Xinjiang Wang, Lihe Yang +3
Deep co-training has been introduced to semi-supervised segmentation and achieves impressive results, yet few studies have explored the working mechanism behind it. In this work, w…
Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection
Xinjiang Wang, Xingyi Yang, Shilong Zhang +6
In this study, we dive deep into the inconsistency of pseudo targets in semi-supervised object detection (SSOD). Our core observation is that the oscillating pseudo-targets undermi…
Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation
Lihe Yang, Lei Qi, Litong Feng +2
In this work, we revisit the weak-to-strong consistency framework, popularized by FixMatch from semi-supervised classification, where the prediction of a weakly perturbed image ser…
ViM: Out-Of-Distribution with Virtual-logit Matching
Haoqi Wang, Zhizhong Li, Litong Feng +1
Most of the existing Out-Of-Distribution (OOD) detection algorithms depend on single input source: the feature, the logit, or the softmax probability. However, the immense diversit…
Semantically Coherent Out-of-Distribution Detection
Jingkang Yang, Haoqi Wang, Litong Feng +4
Current out-of-distribution (OOD) detection benchmarks are commonly built by defining one dataset as in-distribution (ID) and all others as OOD. However, these benchmarks unfortuna…
Progressive Representative Labeling for Deep Semi-Supervised Learning
Xiaopeng Yan, Riquan Chen, Litong Feng +3
Deep semi-supervised learning (SSL) has experienced significant attention in recent years, to leverage a huge amount of unlabeled data to improve the performance of deep learning w…
Webly Supervised Image Classification with Metadata: Automatic Noisy Label Correction via Visual-Semantic Graph
Jingkang Yang, Weirong Chen, Litong Feng +3
Webly supervised learning becomes attractive recently for its efficiency in data expansion without expensive human labeling. However, adopting search queries or hashtags as web lab…
Webly Supervised Image Classification with Self-Contained Confidence
Jingkang Yang, Litong Feng, Weirong Chen +4
This paper focuses on webly supervised learning (WSL), where datasets are built by crawling samples from the Internet and directly using search queries as web labels. Although WSL…
Scale-Equalizing Pyramid Convolution for Object Detection
Xinjiang Wang, Shilong Zhang, Zhuoran Yu +2
Feature pyramid has been an efficient method to extract features at different scales. Development over this method mainly focuses on aggregating contextual information at different…
How Does BN Increase Collapsed Neural Network Filters?
Sheng Zhou, Xinjiang Wang, Ping Luo +3
Improving sparsity of deep neural networks (DNNs) is essential for network compression and has drawn much attention. In this work, we disclose a harmful sparsifying process called…
Gradual Network for Single Image De-raining
Zhe Huang, Weijiang Yu, Wayne Zhang +2
Most advances in single image de-raining meet a key challenge, which is removing rain streaks with different scales and shapes while preserving image details. Existing single image…
Learning Efficient Detector with Semi-supervised Adaptive Distillation
Shitao Tang, Litong Feng, Wenqi Shao +3
Knowledge Distillation (KD) has been used in image classification for model compression. However, rare studies apply this technology on single-stage object detectors. Focal loss sh…
Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos
Zhaoyang Zhang, Zhanghui Kuang, Ping Luo +2
Video Analytics Software as a Service (VA SaaS) has been rapidly growing in recent years. VA SaaS is typically accessed by users using a lightweight client. Because the transmissio…
Fast Video Shot Transition Localization with Deep Structured Models
Shitao Tang, Litong Feng, Zhangkui Kuang +2
Detection of video shot transition is a crucial pre-processing step in video analysis. Previous studies are restricted on detecting sudden content changes between frames through si…