Search Results for author: Litong Feng

Found 10 papers, 6 papers with code

Semantically Coherent Out-of-Distribution Detection

1 code implementation ICCV 2021 Jingkang Yang, Haoqi Wang, Litong Feng, Xiaopeng Yan, Huabin Zheng, Wayne Zhang, Ziwei Liu

The proposed UDG can not only enrich the semantic knowledge of the model by exploiting unlabeled data in an unsupervised manner, but also distinguish ID/OOD samples to enhance ID classification and OOD detection tasks simultaneously.

Out-of-Distribution Detection

Progressive Representative Labeling for Deep Semi-Supervised Learning

no code implementations13 Aug 2021 Xiaopeng Yan, Riquan Chen, Litong Feng, Jingkang Yang, Huabin Zheng, Wayne Zhang

In this paper, we propose to label only the most representative samples to expand the labeled set.

Webly Supervised Image Classification with Metadata: Automatic Noisy Label Correction via Visual-Semantic Graph

1 code implementation12 Oct 2020 Jingkang Yang, Weirong Chen, Litong Feng, Xiaopeng Yan, Huabin Zheng, Wayne Zhang

VSGraph-LC starts from anchor selection referring to the semantic similarity between metadata and correct label concepts, and then propagates correct labels from anchors on a visual graph using graph neural network (GNN).

General Classification Image Classification +2

Scale-Equalizing Pyramid Convolution for Object Detection

2 code implementations CVPR 2020 Xinjiang Wang, Shilong Zhang, Zhuoran Yu, Litong Feng, Wayne Zhang

Inspired by this, a convolution across the pyramid level is proposed in this study, which is termed pyramid convolution and is a modified 3-D convolution.

Object Detection

How Does BN Increase Collapsed Neural Network Filters?

no code implementations30 Jan 2020 Sheng Zhou, Xinjiang Wang, Ping Luo, Litong Feng, Wenjie Li, Wei zhang

This phenomenon is caused by the normalization effect of BN, which induces a non-trainable region in the parameter space and reduces the network capacity as a result.

Object Detection

Gradual Network for Single Image De-raining

no code implementations20 Sep 2019 Zhe Huang, Weijiang Yu, Wayne Zhang, Litong Feng, Nong Xiao

Taking the residual result (the coarse de-rained result) between the rainy image sample (i. e. the input data) and the output of coarse stage (i. e. the learnt rain mask) as input, the fine stage continues to de-rain by removing the fine-grained rain streaks (e. g. light rain streaks and water mist) to get a rain-free and well-reconstructed output image via a unified contextual merging sub-network with dense blocks and a merging block.

Rain Removal

Learning Efficient Detector with Semi-supervised Adaptive Distillation

1 code implementation2 Jan 2019 Shitao Tang, Litong Feng, Wenqi Shao, Zhanghui Kuang, Wei zhang, Yimin Chen

ADL enlarges the distillation loss for hard-to-learn and hard-to-mimic samples and reduces distillation loss for the dominant easy samples, enabling distillation to work on the single-stage detector first time, even if the student and the teacher are identical.

Image Classification Knowledge Distillation +1

Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos

no code implementations15 Aug 2018 Zhaoyang Zhang, Zhanghui Kuang, Ping Luo, Litong Feng, Wei zhang

Secondly, TSD significantly reduces the computations to run video action recognition with compressed frames on the cloud, while maintaining high recognition accuracies.

Action Recognition Action Recognition In Videos +1

Fast Video Shot Transition Localization with Deep Structured Models

3 code implementations13 Aug 2018 Shitao Tang, Litong Feng, Zhangkui Kuang, Yimin Chen, Wei zhang

In order to train a high-performance shot transition detector, we contribute a new database ClipShots, which contains 128636 cut transitions and 38120 gradual transitions from 4039 online videos.

Cannot find the paper you are looking for? You can Submit a new open access paper.