IIE Science Group's Report

Year 2021

2020.02.21 Jia Xiaojun:
- Bag of tricks for adversarial training, ICLR 2021
- Robust reinforcement learning on state observations with learned optimal adversary, ICLR 2021
2020.02.06 Yan YanYang:
- LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond, NeurIPS 2020
- Unfolding the Alternating Optimization for Blind Super Resolution, NeurIPS 2020
2020.02.03 Lv Feixiao:
- RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning, NeurIPS 2020
- Diverse Image Captioning with Context-Object Split Latent Spaces, NeurIPS 2020
2020.02.01 Liang Dong:
- Differentiable Augmentationfor Data-Efficient GAN Training, NeurIPS 2020
- Multi-type Disentanglement without Adversarial Training, AAAI 2021
2020.01.11 Jiang Yuchen:
- Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge, NeurIPS 2020
- Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach, NeurIPS 2020
2020.01.08 Han Bing:
- An Image is worth 16X16 words: Transformaers for image recognition at scale, ICLR2021
- Rethinking Pre-training and Self-training, NeurIPS 2020 oral
2020.01.05 Zhang Sanyi:
- Deep Variational Instance Segmentation, NeurIPS 2020
- SOLOv2: Dynamic and Fast Instance Segmentation, NeurIPS 2020