Ningchuan Li
Research Subjects
Research Interests
Ningchuan Li has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Jianhai Fu
Zhejiang Dahua Technology Co., Ltd, Hangzhou, Zhejiang, China
3 shared publications - Yuanjie Yu
Zhejiang Dahua Technology Co., Ltd
3 shared publications - Jianping Xiong
Zhejiang Dahua Technology Co., Ltd
2 shared publications - Jun Yin
Zhejiang University, Hangzhou, Zhejiang, China
2 shared publications - Qichao Chen
Zhejiang Dahua Technology Co., Ltd
2 shared publications - Yi Zhang
Zhejiang Dahua Technology Co., Ltd
2 shared publications
Latest Publications
- 20 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 332
V-trex: Visual-prompt enhanced detection with attention selection fusion module and random-crop quadruplet loss
- 20 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 332
V-trex: Visual-prompt enhanced detection with attention selection fusion module and random-crop quadruplet loss
- 31 October 2024
- Published by Springer Nature
- p. 456-471
Lite-SAM Is Actually What You Need for Segment Everything
- 31 October 2024
- Published by Springer Nature
- p. 456-471
Lite-SAM Is Actually What You Need for Segment Everything
- Open Access
Lite-SAM Is Actually What You Need for Segment Everything
This paper introduces Lite-SAM, an efficient end-to-end solution for the SegEvery task designed to reduce computational costs and redundancy. Lite-SAM is composed of four main components: a streamlined CNN-Transformer hybrid encoder (LiteViT), an automated prompt proposal network (AutoPPN), a traditional prompt encoder, and a mask decoder. All these components are integrated within the SAM framework. Our LiteViT, a high-performance lightweight backbone network, has only 1.16M parameters, which is a 23% reduction compared to the lightest existing backbone network Shufflenet. We also introduce AutoPPN, an innovative end-to-end method for prompt boxes and points generation. This is an improvement over traditional grid search sampling methods, and its unique design allows for easy integration into any SAM series algorithm, extending its usability. we have thoroughly benchmarked Lite-SAM across a plethora of both public and private datasets. The evaluation encompassed a broad spectrum of universal metrics, including the number of parameters, SegEvery execution time, and accuracy. The findings reveal that Lite-SAM, operating with a lean 4.2M parameters, significantly outpaces its counterparts, demonstrating performance improvements of 43x, 31x, 20x, 21x, and 1.6x over SAM, MobileSAM, Edge-SAM, EfficientViT-SAM, and MobileSAM-v2 respectively, all the while maintaining competitive accuracy. This underscores Lite-SAM's prowess in achieving an optimal equilibrium between performance and precision, thereby setting a new state-of-the-art(SOTA) benchmark in the domain.
Open AccessLite-SAM Is Actually What You Need for Segment Everything
This paper introduces Lite-SAM, an efficient end-to-end solution for the SegEvery task designed to reduce computational costs and redundancy. Lite-SAM is composed of four main components: a streamlined CNN-Transformer hybrid encoder (LiteViT), an automated prompt proposal network (AutoPPN), a traditional prompt encoder, and a mask decoder. All these components are integrated within the SAM framework. Our LiteViT, a high-performance lightweight backbone network, has only 1.16M parameters, which is a 23% reduction compared to the lightest existing backbone network Shufflenet. We also introduce AutoPPN, an innovative end-to-end method for prompt boxes and points generation. This is an improvement over traditional grid search sampling methods, and its unique design allows for easy integration into any SAM series algorithm, extending its usability. we have thoroughly benchmarked Lite-SAM across a plethora of both public and private datasets. The evaluation encompassed a broad spectrum of universal metrics, including the number of parameters, SegEvery execution time, and accuracy. The findings reveal that Lite-SAM, operating with a lean 4.2M parameters, significantly outpaces its counterparts, demonstrating performance improvements of 43x, 31x, 20x, 21x, and 1.6x over SAM, MobileSAM, Edge-SAM, EfficientViT-SAM, and MobileSAM-v2 respectively, all the while maintaining competitive accuracy. This underscores Lite-SAM's prowess in achieving an optimal equilibrium between performance and precision, thereby setting a new state-of-the-art(SOTA) benchmark in the domain.