GitHub

Efficient Visual Representation Learning with Bidirectional State Space Model

May. 2nd, 2024: Vision Mamba (Vim) is accepted by ICML2024. 🎉 Conference page can be found here. Feb. 10th, 2024: We update Vim-tiny/small weights and training scripts. By placing the class token at ...
IEEE

An On-Orbit Measurement Method for Visual Axis Pointing of Remote Sensing Satellite Using the FBG Sensor Network and Machine Learning-Based Cascade Algorithm

Abstract: On-orbit monitoring of visual axis pointing has always been a challenge in the field of space remote sensing, but it is crucial for correcting the remote sensing data, improving the ...
IEEE

ELL-ORB-SLAM: Improved Robust Monocular Visual SLAM Algorithm Based on Image Enhancement and Dynamic FAST Threshold for Low-light Environment

Abstract: The accuracy of visual localization estimation heavily relies on the quality of input images and feature point extraction, with variations in illumination significantly impacting matching ...
GitHub

Don’t Blind Your VLA: Aligning Visual Representations for OOD Generalization

To address the degradation of visual-language (VL) representations during VLA supervised fine-tuning (SFT), we introduce Visual Representation Alignment. During SFT, we pull a VLA’s visual tokens ...