Tianyi Gao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Tianyi Gao has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Hong Ji
College of Geomatics, Xi’an University of Science and Technology, Xi’an 710054, China
2 shared publications - Zhi Gao
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China
2 shared publications - Jinchang Ren
Guangdong Polytechnic Normal University
1 shared publication - Ping Ma
College of Information Technology, Shanghai Ocean University, Shanghai 201306, China
1 shared publication - Wei Ao
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
1 shared publication - Weiwei Song
Pengcheng Laboratory, Shenzhen, China
1 shared publication
Latest Publications
- 5 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-13
Query Adaptive Transformer and Multiprototype Rectification for Few-Shot Remote Sensing Image Segmentation
Deep learning has emerged as a powerful tool for semantic segmentation tasks. However, in some data-deficient and resource-limited scenarios, networks are constrained to learn novel concepts. To tackle this problem, few-shot segmentation (FSS) has been proposed by the machine learning community, aiming at segmenting novel objects by leveraging a handful of annotated samples. However, most advanced FSS algorithms suffer from severe performance degradation when directly applied to remote sensing image (RSI) domains. Challenges arise due to the unique characteristics of RSIs. To address the large intra-class variation brought by various imaging conditions and large-scale variations, a Query Adaptive Transformer (QAT) is proposed. QAT incorporates query priors into the feature extraction process, adapting RSI features to novel objects from query RSIs. It is noteworthy that query priors are extracted via a Query Prior Generation (QPG) module devoid of any query label information. To alleviate interference brought by complex object distribution, a multi-prototype strategy is adopted instead of representing objects with a single prototype ambiguously. Moreover, we rectify the prototypes using a Prior Injection Module (PIM), thereby fully leveraging the advantages offered by query priors. The superiority of our method is validated through comprehensive experiments on the public iSAID-5 i dataset and comparisons with state-of-the-art methods. Finally, we propose a novel cross-domain setting to investigate the potential and generalizability of few-shot RSI segmentation for several Earth observation applications.
- 5 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-13
Query Adaptive Transformer and Multiprototype Rectification for Few-Shot Remote Sensing Image Segmentation
Deep learning has emerged as a powerful tool for semantic segmentation tasks. However, in some data-deficient and resource-limited scenarios, networks are constrained to learn novel concepts. To tackle this problem, few-shot segmentation (FSS) has been proposed by the machine learning community, aiming at segmenting novel objects by leveraging a handful of annotated samples. However, most advanced FSS algorithms suffer from severe performance degradation when directly applied to remote sensing image (RSI) domains. Challenges arise due to the unique characteristics of RSIs. To address the large intra-class variation brought by various imaging conditions and large-scale variations, a Query Adaptive Transformer (QAT) is proposed. QAT incorporates query priors into the feature extraction process, adapting RSI features to novel objects from query RSIs. It is noteworthy that query priors are extracted via a Query Prior Generation (QPG) module devoid of any query label information. To alleviate interference brought by complex object distribution, a multi-prototype strategy is adopted instead of representing objects with a single prototype ambiguously. Moreover, we rectify the prototypes using a Prior Injection Module (PIM), thereby fully leveraging the advantages offered by query priors. The superiority of our method is validated through comprehensive experiments on the public iSAID-5 i dataset and comparisons with state-of-the-art methods. Finally, we propose a novel cross-domain setting to investigate the potential and generalizability of few-shot RSI segmentation for several Earth observation applications.
- 14 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21 (1545598X) , 1-5
Prompting-to-Distill Semantic Knowledge for Few-Shot Learning
Recognizing visual patterns in low-data regime necessitates deep neural networks to glean generalized representations from limited training samples. In this paper, we propose a novel few-shot classification method, namely ProDFSL, leveraging multi-modal knowledge and attention mechanism. We are inspired by recent advances of large language models and the great potential they have shown across a wide range of downstream tasks, and tailor it to benefit the remote sensing community. We utilize ChatGPT to produce class-specific textual inputs for enabling CLIP with rich semantic information. To promote the adaptation of CLIP in remote sensing domain, we introduce a Cross-modal Knowledge Generation Module, which dynamically generates a group of soft prompts conditioned on the few-shot visual samples and further uses a shallow Transformer to model the dependencies between language sequences. Fusing the semantic information with few-shot visual samples, we build representative class prototypes, which are conducive to both inductive and transductive inference. In extensive experiments on standard benchmarks, our ProDFSL consistently outperforms the state-of-the-art in few-shot learning.
- 14 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21 (1545598X) , 1-5
Prompting-to-Distill Semantic Knowledge for Few-Shot Learning
Recognizing visual patterns in low-data regime necessitates deep neural networks to glean generalized representations from limited training samples. In this paper, we propose a novel few-shot classification method, namely ProDFSL, leveraging multi-modal knowledge and attention mechanism. We are inspired by recent advances of large language models and the great potential they have shown across a wide range of downstream tasks, and tailor it to benefit the remote sensing community. We utilize ChatGPT to produce class-specific textual inputs for enabling CLIP with rich semantic information. To promote the adaptation of CLIP in remote sensing domain, we introduce a Cross-modal Knowledge Generation Module, which dynamically generates a group of soft prompts conditioned on the few-shot visual samples and further uses a shallow Transformer to model the dependencies between language sequences. Fusing the semantic information with few-shot visual samples, we build representative class prototypes, which are conducive to both inductive and transductive inference. In extensive experiments on standard benchmarks, our ProDFSL consistently outperforms the state-of-the-art in few-shot learning.