4 citations · 4 across the 3 of their papers we have counts for
3 papers
cs.CV2023
Self-Supervised Instance Segmentation by Grasping
YuXuan Liu, Xi Chen, Pieter Abbeel
Instance segmentation is a fundamental skill for many robotic applications. We propose a self-supervised method that uses grasp interactions to collect segmentation supervision for…
cs.CV2023★ 4 cited
Detecting Everything in the Open World: Towards Universal Object Detection
Zhenyu Wang, Yali Li, Xi Chen +4
In this paper, we formally address universal object detection, which aims to detect every scene and predict every category. The dependence on human annotations, the limited visual…
cs.LG2022
Leveraging Intrinsic Gradient Information for Further Training of Differentiable Machine Learning Models
Chris McDonagh, Xi Chen
Designing models that produce accurate predictions is the fundamental objective of machine learning (ML). This work presents methods demonstrating that when the derivatives of targ…