Search Results for author: Changsong Liu

Found 13 papers, 2 papers with code

CX-ToM: Counterfactual Explanations with Theory-of-Mind for Enhancing Human Trust in Image Recognition Models

1 code implementation3 Sep 2021 Arjun R. Akula, Keze Wang, Changsong Liu, Sari Saba-Sadiya, Hongjing Lu, Sinisa Todorovic, Joyce Chai, Song-Chun Zhu

More concretely, our CX-ToM framework generates sequence of explanations in a dialog by mediating the differences between the minds of machine and human user.

Explainable Artificial Intelligence (XAI)

Occlusion Robust Face Recognition Based on Mask Learning with PairwiseDifferential Siamese Network

1 code implementation17 Aug 2019 Lingxue Song, Dihong Gong, Zhifeng Li, Changsong Liu, Wei Liu

Deep Convolutional Neural Networks (CNNs) have been pushing the frontier of the face recognition research in the past years.

Face Recognition Robust Face Recognition

Learning with Rethinking: Recurrently Improving Convolutional Neural Networks through Feedback

no code implementations15 Aug 2017 Xin Li, Zequn Jie, Jiashi Feng, Changsong Liu, Shuicheng Yan

However, most of the existing CNN models only learn features through a feedforward structure and no feedback information from top to bottom layers is exploited to enable the networks to refine themselves.

Prune the Convolutional Neural Networks with Sparse Shrink

no code implementations8 Aug 2017 Xin Li, Changsong Liu

These results have demonstrated the effectiveness of our "Sparse Shrink" algorithm.

FoveaNet: Perspective-aware Urban Scene Parsing

no code implementations ICCV 2017 Xin Li, Zequn Jie, Wei Wang, Changsong Liu, Jimei Yang, Xiaohui Shen, Zhe Lin, Qiang Chen, Shuicheng Yan, Jiashi Feng

Thus, they suffer from heterogeneous object scales caused by perspective projection of cameras on actual scenes and inevitably encounter parsing failures on distant objects as well as other boundary and recognition errors.

Scene Parsing

Heteroscedastic Max-Min Distance Analysis

no code implementations CVPR 2015 Bing Su, Xiaoqing Ding, Changsong Liu, Ying Wu

Many discriminant analysis methods such as LDA and HLDA actually maximize the average pairwise distances between classes, which often causes the class separation problem.

Dimensionality Reduction

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