Search Results for author: Xiangtao Kong

Found 9 papers, 7 papers with code

E-EVAL: A Comprehensive Chinese K-12 Education Evaluation Benchmark for Large Language Models

1 code implementation29 Jan 2024 Jinchang Hou, Chang Ao, Haihong Wu, Xiangtao Kong, Zhigang Zheng, Daijia Tang, Chengming Li, Xiping Hu, Ruifeng Xu, Shiwen Ni, Min Yang

The integration of LLMs and education is getting closer and closer, however, there is currently no benchmark for evaluating LLMs that focuses on the Chinese K-12 education domain.

Ethics Multiple-choice

Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild

no code implementations24 Jan 2024 Fanghua Yu, Jinjin Gu, Zheyuan Li, JinFan Hu, Xiangtao Kong, Xintao Wang, Jingwen He, Yu Qiao, Chao Dong

We introduce SUPIR (Scaling-UP Image Restoration), a groundbreaking image restoration method that harnesses generative prior and the power of model scaling up.

Descriptive Image Restoration

Towards Effective Multiple-in-One Image Restoration: A Sequential and Prompt Learning Strategy

1 code implementation7 Jan 2024 Xiangtao Kong, Chao Dong, Lei Zhang

While single task image restoration (IR) has achieved significant successes, it remains a challenging issue to train a single model which can tackle multiple IR tasks.

Image Restoration

HAT: Hybrid Attention Transformer for Image Restoration

2 code implementations11 Sep 2023 Xiangyu Chen, Xintao Wang, Wenlong Zhang, Xiangtao Kong, Yu Qiao, Jiantao Zhou, Chao Dong

In the training stage, we additionally adopt a same-task pre-training strategy to further exploit the potential of the model for further improvement.

Image Compression Image Denoising +2

DegAE: A New Pretraining Paradigm for Low-Level Vision

1 code implementation CVPR 2023 Yihao Liu, Jingwen He, Jinjin Gu, Xiangtao Kong, Yu Qiao, Chao Dong

However, we argue that pretraining is more significant for high-cost tasks, where data acquisition is more challenging.

Philosophy

Reflash Dropout in Image Super-Resolution

no code implementations CVPR 2022 Xiangtao Kong, Xina Liu, Jinjin Gu, Yu Qiao, Chao Dong

Dropout is designed to relieve the overfitting problem in high-level vision tasks but is rarely applied in low-level vision tasks, like image super-resolution (SR).

Common Sense Reasoning Image Super-Resolution +1

Efficient Image Super-Resolution Using Pixel Attention

1 code implementation2 Oct 2020 Hengyuan Zhao, Xiangtao Kong, Jingwen He, Yu Qiao, Chao Dong

Pixel attention (PA) is similar as channel attention and spatial attention in formulation.

Image Super-Resolution

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