activity
20182021
most citedMixSiam: A Mixture-based Approach to Self-supervised Representation Learning

8 citations · 22 across the 4 of their papers we have counts for

collaborators

6 papers

cs.CV20218 cited

MixSiam: A Mixture-based Approach to Self-supervised Representation Learning

Xiaoyang Guo, Tianhao Zhao, Yutian Lin +1

Recently contrastive learning has shown significant progress in learning visual representations from unlabeled data. The core idea is training the backbone to be invariant to diffe…

cs.CV20217 cited

LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector

Xiaoyang Guo, Shaoshuai Shi, Xiaogang Wang +1

Stereo-based 3D detection aims at detecting 3D object bounding boxes from stereo images using intermediate depth maps or implicit 3D geometry representations, which provides a low-…

cs.CV20197 cited

Group-wise Correlation Stereo Network

Xiaoyang Guo, Kai Yang, Wukui Yang +2

Stereo matching estimates the disparity between a rectified image pair, which is of great importance to depth sensing, autonomous driving, and other related tasks. Previous works b…

cs.CV2019

Unsupervised Cross-spectral Stereo Matching by Learning to Synthesize

Mingyang Liang, Xiaoyang Guo, Hongsheng Li +2

Unsupervised cross-spectral stereo matching aims at recovering disparity given cross-spectral image pairs without any supervision in the form of ground truth disparity or depth. Th…

cs.CV2018

Learning Monocular Depth by Distilling Cross-domain Stereo Networks

Xiaoyang Guo, Hongsheng Li, Shuai Yi +2

Monocular depth estimation aims at estimating a pixelwise depth map for a single image, which has wide applications in scene understanding and autonomous driving. Existing supervis…

cs.LG2018

Neural Network Encapsulation

Hongyang Li, Xiaoyang Guo, Bo Dai +2

A capsule is a collection of neurons which represents different variants of a pattern in the network. The routing scheme ensures only certain capsules which resemble lower counterp…