Shichen Lu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Shichen Lu has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Jing Liu
Chinese Academy of Sciences
3 shared publications - Longteng Guo
Institute of Automation, Chinese Academy of Sciences
2 shared publications - Si Liu
Beihang University
2 shared publications - Xingjian He
Institute of Automation, Chinese Academy of Sciences, Beijing, China
2 shared publications - Andrew Lambert
MBRYONICS Ltd
1 shared publication Andrew Zou Li
University of Toronto 4925 Dufferin Street Toronto Ontario Canada
1 shared publication
Latest Publications
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4928-4937
Collaborative Training of Tiny-Large Vision Language Models
Recently, large vision language models (LVLMs) have advanced AI by integrating visual and linguistic data for tasks like visual conversation, image captioning, and visual question answering. Current LVLM research either scales up model size for performance or reduces parameters for limited computational resources. We believe both large and tiny models have unique strengths and that collaborative training yields better results than independent training. We propose Collaborative Training of Tiny-Large Vision Language Models (CTVLMs), a framework connecting large and tiny models via a projection layer and leveraging a synergistic training strategy. Our framework improves training efficiency by strengthening the interconnection between large and tiny models. Using the parameter efficiency of tiny models, we effectively align image-text features, then apply knowledge distillation to help large models better align cross-modal information. During fine-tuning, the large model's extensive knowledge enhances tiny model's performance. This collaborative approach allows models to adapt to various computational resources and outperforms existing methods in vision-language tasks.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4928-4937
Open AccessCollaborative Training of Tiny-Large Vision Language Models
Recently, large vision language models (LVLMs) have advanced AI by integrating visual and linguistic data for tasks like visual conversation, image captioning, and visual question answering. Current LVLM research either scales up model size for performance or reduces parameters for limited computational resources. We believe both large and tiny models have unique strengths and that collaborative training yields better results than independent training. We propose Collaborative Training of Tiny-Large Vision Language Models (CTVLMs), a framework connecting large and tiny models via a projection layer and leveraging a synergistic training strategy. Our framework improves training efficiency by strengthening the interconnection between large and tiny models. Using the parameter efficiency of tiny models, we effectively align image-text features, then apply knowledge distillation to help large models better align cross-modal information. During fine-tuning, the large model's extensive knowledge enhances tiny model's performance. This collaborative approach allows models to adapt to various computational resources and outperforms existing methods in vision-language tasks.
- 31 July 2024
- Published by Springer Nature
- p. 313-324
Fuse and Calibrate: A Bi-directional Vision-Language Guided Framework for Referring Image Segmentation
- 31 July 2024
- Published by Springer Nature
- p. 313-324
Fuse and Calibrate: A Bi-directional Vision-Language Guided Framework for Referring Image Segmentation
- Open Access
Fuse & Calibrate: A bi-directional Vision-Language Guided Framework for Referring Image Segmentation
Referring Image Segmentation (RIS) aims to segment an object described in natural language from an image, with the main challenge being a text-to-pixel correlation. Previous methods typically rely on single-modality features, such as vision or language features, to guide the multi-modal fusion process. However, this approach limits the interaction between vision and language, leading to a lack of fine-grained correlation between the language description and pixel-level details during the decoding process. In this paper, we introduce FCNet, a framework that employs a bi-directional guided fusion approach where both vision and language play guiding roles. Specifically, we use a vision-guided approach to conduct initial multi-modal fusion, obtaining multi-modal features that focus on key vision information. We then propose a language-guided calibration module to further calibrate these multi-modal features, ensuring they understand the context of the input sentence. This bi-directional vision-language guided approach produces higher-quality multi-modal features sent to the decoder, facilitating adaptive propagation of fine-grained semantic information from textual features to visual features. Experiments on RefCOCO, RefCOCO+, and G-Ref datasets with various backbones consistently show our approach outperforming state-of-the-art methods.
Open AccessFuse & Calibrate: A bi-directional Vision-Language Guided Framework for Referring Image Segmentation
Referring Image Segmentation (RIS) aims to segment an object described in natural language from an image, with the main challenge being a text-to-pixel correlation. Previous methods typically rely on single-modality features, such as vision or language features, to guide the multi-modal fusion process. However, this approach limits the interaction between vision and language, leading to a lack of fine-grained correlation between the language description and pixel-level details during the decoding process. In this paper, we introduce FCNet, a framework that employs a bi-directional guided fusion approach where both vision and language play guiding roles. Specifically, we use a vision-guided approach to conduct initial multi-modal fusion, obtaining multi-modal features that focus on key vision information. We then propose a language-guided calibration module to further calibrate these multi-modal features, ensuring they understand the context of the input sentence. This bi-directional vision-language guided approach produces higher-quality multi-modal features sent to the decoder, facilitating adaptive propagation of fine-grained semantic information from textual features to visual features. Experiments on RefCOCO, RefCOCO+, and G-Ref datasets with various backbones consistently show our approach outperforming state-of-the-art methods.
- 29 October 2023
- Published by Springer Nature
- p. 385-395
CSDNet: Contrastive Similarity Distillation Network for Multi-lingual Image-Text Retrieval
- 29 October 2023
- Published by Springer Nature
- p. 385-395
CSDNet: Contrastive Similarity Distillation Network for Multi-lingual Image-Text Retrieval
- Open Access
Boreas: A Multi-Season Autonomous Driving Dataset
The Boreas dataset was collected by driving a repeated route over the course of one year, resulting in stark seasonal variations and adverse weather conditions such as rain and falling snow. In total, the Boreas dataset includes over 350km of driving data featuring a 128-channel Velodyne Alpha Prime lidar, a 360$^\circ$ Navtech CIR304-H scanning radar, a 5MP FLIR Blackfly S camera, and centimetre-accurate post-processed ground truth poses. Our dataset will support live leaderboards for odometry, metric localization, and 3D object detection. The dataset and development kit are available at https://www.boreas.utias.utoronto.ca
Open AccessBoreas: A Multi-Season Autonomous Driving Dataset
The Boreas dataset was collected by driving a repeated route over the course of one year, resulting in stark seasonal variations and adverse weather conditions such as rain and falling snow. In total, the Boreas dataset includes over 350km of driving data featuring a 128-channel Velodyne Alpha Prime lidar, a 360$^\circ$ Navtech CIR304-H scanning radar, a 5MP FLIR Blackfly S camera, and centimetre-accurate post-processed ground truth poses. Our dataset will support live leaderboards for odometry, metric localization, and 3D object detection. The dataset and development kit are available at https://www.boreas.utias.utoronto.ca