activity
20162023
most citedCenterNet: Keypoint Triplets for Object Detection

168 citations · 879 across the 47 of their papers we have counts for

collaborators

82 papers

cs.CV20232 cited

One-bit Supervision for Image Classification: Problem, Solution, and Beyond

Hengtong Hu, Lingxi Xie, Xinyue Hue +2

This paper presents one-bit supervision, a novel setting of learning with fewer labels, for image classification. Instead of training model using the accurate label of each sample,…

cs.CV20235 cited

Towards AGI in Computer Vision: Lessons Learned from GPT and Large Language Models

Lingxi Xie, Longhui Wei, Xiaopeng Zhang +4

The AI community has been pursuing algorithms known as artificial general intelligence (AGI) that apply to any kind of real-world problem. Recently, chat systems powered by large l…

physics.ao-ph2022127 cited

Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast

Kaifeng Bi, Lingxi Xie, Hengheng Zhang +3

In this paper, we present Pangu-Weather, a deep learning based system for fast and accurate global weather forecast. For this purpose, we establish a data-driven environment by dow…

cs.CV2022

Learnable Distribution Calibration for Few-Shot Class-Incremental Learning

Binghao Liu, Boyu Yang, Lingxi Xie +3

Few-shot class-incremental learning (FSCIL) faces challenges of memorizing old class distributions and estimating new class distributions given few training samples. In this study,…

cs.CV202229 cited

Fine-Grained Semantically Aligned Vision-Language Pre-Training

Juncheng Li, Xin He, Longhui Wei +6

Large-scale vision-language pre-training has shown impressive advances in a wide range of downstream tasks. Existing methods mainly model the cross-modal alignment by the similarit…

cs.CV202212 cited

HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling

Xiaosong Zhang, Yunjie Tian, Wei Huang +4

Recently, masked image modeling (MIM) has offered a new methodology of self-supervised pre-training of vision transformers. A key idea of efficient implementation is to discard the…