← Search

Lechao Cheng*

2 accepted papers

2024

Improving Knowledge Distillation via Regularizing Feature Direction and Norm

ECCV 2024oral

"Knowledge distillation (KD) is a particular technique of model compression that exploits a large well-trained teacher neural network to train a small student network . Treating teacher’s feature as knowledge, prevailing methods train student by aligning its features with the teacher’s, e.g., by min…

2024

MarvelOVD: Marrying Object Recognition and Vision-Language Models for Robust Open-Vocabulary Object Detection

ECCV 2024poster

"Learning from pseudo-labels that generated with VLMs (Vision Language Models) has been shown as a promising solution to assist open vocabulary detection (OVD) in recent studies. However, due to the domain gap between VLM and vision-detection tasks, pseudo-labels produced by the VLMs are prone to be…