Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More

1 code implementation • CVPR 2019 • Jingwen Ye, Yixin Ji, Xinchao Wang, Kairi Ou, Dapeng Tao, Mingli Song

In this paper, we investigate a novel deep-model reusing task.

Depth Estimation Scene Parsing

Amalgamating Filtered Knowledge: Learning Task-customized Student from Multi-task Teachers

1 code implementation • 28 May 2019 • Jingwen Ye, Xinchao Wang, Yixin Ji, Kairi Ou, Mingli Song

Many well-trained Convolutional Neural Network(CNN) models have now been released online by developers for the sake of effortless reproducing.

Data-Free Knowledge Amalgamation via Group-Stack Dual-GAN

no code implementations • CVPR 2020 • Jingwen Ye, Yixin Ji, Xinchao Wang, Xin Gao, Mingli Song

Then a dual generator is trained by taking the output from the former generator as input.

Multi-Label Classification

Test-Time Adaptation with Perturbation Consistency Learning

no code implementations • 25 Apr 2023 • Yi Su, Yixin Ji, Juntao Li, Hai Ye, Min Zhang

Accordingly, in this paper, we propose perturbation consistency learning (PCL), a simple test-time adaptation method to promote the model to make stable predictions for samples with distribution shifts.

Adversarial Robustness Pseudo Label +1

基于字词粒度噪声数据增强的中文语法纠错(Chinese Grammatical Error Correction enhanced by Data Augmentation from Word and Character Levels)

no code implementations • CCL 2021 • Zecheng Tang, Yixin Ji, Yibo Zhao, Junhui Li

Data Augmentation Grammatical Error Correction