FoodSAM: Any Food Segmentation

Aug 11, 2023·
Xing Lan
,
Jiayi Lyu
,
Hanyu Jiang
,
Kun Dong
Zehai Niu
Zehai Niu
,
Yi Zhang
,
Jian Xue
· 0 min read
Abstract
We explore the zero-shot capability of the Segment Anything Model (SAM) for food image segmentation, proposing FoodSAM — a novel framework that enhances SAM with class-aware segmentation and instance-level annotations for diverse food categories.
Type
Publication
IEEE Transactions on Multimedia (TMM), 27, 2795-2808
Status
Peer-reviewed
publications
Computer Vision Segmentation SAM
Zehai Niu
Authors
Zehai Niu (he/him)
Assistant Professor · Shenzhen University

Zehai Niu is an Assistant Professor at Shenzhen University. His research focuses on edge-device inference acceleration for Vision-Language Models (VLM) and VLM interpretability — building VLMs that run fast on consumer devices, and that we actually understand.

He received his PhD from the University of Chinese Academy of Sciences (UCAS) in 2024. From July 2024 to May 2026, he was an AI Researcher at HONOR Device, where he led innovation for the gaming business — including M-DLSS 3.0, the industry’s first NPU-GPU heterogeneous frame interpolation system shipped to consumer phones — and the embodied intelligence stack of RobotPhone. During this period, he worked closely with Google’s Gemma team, Qualcomm, and Alibaba’s Qwen (Tongyi Qianwen) Lab.

He has published 20+ papers at ICCV, ECCV, ACM MM, IEEE TCSVT, IEEE TMM and other top venues, holds 10+ patents, and serves as a reviewer for ICLR, ICCV, ECCV, and ACM MM.