most citedAIM 2020 Challenge on Real Image Super-Resolution: Methods and Results

20 citations · 76 across the 13 of their papers we have counts for

collaborators

16 papers

cs.CV20213 cited

GLiT: Neural Architecture Search for Global and Local Image Transformer

Boyu Chen, Peixia Li, Chuming Li +6

We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition. Recently, transformers without CNN-based backbones a…

cs.CV20213 cited

AutoSampling: Search for Effective Data Sampling Schedules

Ming Sun, Haoxuan Dou, Baopu Li +3

Data sampling acts as a pivotal role in training deep learning models. However, an effective sampling schedule is difficult to learn due to the inherently high dimension of paramet…

cs.CV2021

Action Segmentation with Mixed Temporal Domain Adaptation

Min-Hung Chen, Baopu Li, Yingze Bao +1

The main progress for action segmentation comes from densely-annotated data for fully-supervised learning. Since manual annotation for frame-level actions is time-consuming and cha…

cs.RO2021

No Need for Interactions: Robust Model-Based Imitation Learning using Neural ODE

HaoChih Lin, Baopu Li, Xin Zhou +2

Interactions with either environments or expert policies during training are needed for most of the current imitation learning (IL) algorithms. For IL problems with no interactions…

cs.CV20219 cited

Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution

Baoli Sun, Xinchen Ye, Baopu Li +3

Existing color-guided depth super-resolution (DSR) approaches require paired RGB-D data as training samples where the RGB image is used as structural guidance to recover the degrad…

cs.CV20218 cited

MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation

Xiaoqing Guo, Chen Yang, Baopu Li +1

Unsupervised domain adaptation (UDA) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain. Existing self-training based UDA approaches assig…