Research

Research Interests

My current interest spans object and human recognition, detection, and segmentation, with the following topics:

long-tailed/imbalanced data, biased data, unlabeled data, high-resolution data, multi-modal data

knowledge distillation, open-vocabulary/set recognition, domain adaptation, self/weakly-supervised learning

     transformers for instance-level understanding, network design for mobile applications

Research Statement

I'm developing Machine Learning algorithms for visual object perception in the open world. The major focus is designing effective methods to handle practical challenges in real-world non-ideal environments. Specifically,  I'm taking two broad perspectives: 1) Handle open-world data that may be long-tailed, biased, unlabeled, or contain unknown, anomaly concepts. 2) Develop efficient learning and inference methods to gain superior training data efficiency and runtime efficiency, these include knowledge distillation, X-shot & Y-supervised learning, domain adaptation, and network architecture design.

Academic Activities

Competitions:

Academic Services:

Talks:

Intern Experiences