Mao Ye

Multi-Class 3D Object Detection with Single-Class Supervision

2022 · arXiv (Cornell University)

While multi-class 3D detectors are needed in many robotics applications, training them with fully labeled datasets can be expensive in labeling cost. An alternative approach is to have targeted single-class labels on disjoint data samples. …

Source-Free Domain Adaptation via Target Prediction Distribution Searching

2023 · International Journal of Computer Vision

Abstract Existing Source-Free Domain Adaptation (SFDA) methods typically adopt the feature distribution alignment paradigm via mining auxiliary information (eg., pseudo-labelling, source domain data generation). However, they are largely limited due to that the auxiliary information …

Source-Free Domain Adaptation with Frozen Multimodal Foundation Model

2023 · arXiv (Cornell University)

Source-Free Domain Adaptation (SFDA) aims to adapt a source model for a target domain, with only access to unlabeled target training data and the source model pre-trained on a supervised source domain. Relying on pseudo …