Yu Tong
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
Yu Tong has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Jun Liu
School of Computer Science and Engineering, Northeastern University, Shenyang 110169, China
3 shared publications - Guixing Cao
College of Computer Science and Engineering, Northeastern University, Shenyang 110819, China
2 shared publications - Kaina Xiong
College of Computer Science and Engineering, Northeastern University, Shenyang 110819, China
2 shared publications - Xinyue Fan
College of Computer Science and Engineering, Northeastern University, Shenyang 110819, China
2 shared publications - Cheng-Hao Tsai
Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan
1 shared publication Cheng-Kuang Wei
National Taiwan University
1 shared publication
Latest Publications
- Open Access
- 4 September 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (17) , 3008
M-FSAD-KD: Full-Link Multi-Granularity Distillation for SAR Object Detection
Multi-modal synthetic aperture radar (SAR)–optical object detectors raise detection accuracy by fusing complementary physical responses, but require both modalities to be simultaneously available at inference. When the optical stream becomes unavailable—under heavy cloud cover, night-time conditions, or downlink disruption—the detector reverts to SAR-only operation and accuracy degrades sharply. A natural remedy is to distil a multi-modal teacher into a SAR-only student via privileged-information knowledge distillation. However, we observe that the leading channel-wise feature-level method (CWD) reduces the student’s accuracy below the non-distilled baseline, with its smallest-target AP collapsing to near zero, because SAR speckle and target high-frequency edges share the same band and the alignment loss is dominated by broadband speckle energy. We refer to this failure mode as the speckle-fitting trap, formalize it as a gradient-pollution effect, and validate it through spectral and feature-manifold diagnostics. To counter the trap, we propose M-FSAD-KD, a full-link distillation framework whose neck-stage Fourier-gated alignment transfers low-frequency structural content while preserving target-edge high-frequency content; a joint spatial–channel attention mask, a shallow backbone adapter, and a response-level knowledge distillation (KD) term complete the chain. With a MAIENet teacher on OGSOD-1.0, the advantage of M-FSAD-KD over the strongest response-level KD baseline scales with student capacity: it matches KD on a 2.39 M-parameter student (both ≈48% mean average precision at an intersection-over-union (IoU) threshold of 0.5 (), averaged over multiple seeds) and exceeds it by 2.0 absolute points on a 19.98 M-parameter student ( over the non-distilled baseline), where it is the best of all distillation methods; at full convergence the 19.98 M-parameter student reaches 81.9% , within 8.9 absolute points of the multi-modal teacher. A frozen-feature transfer test to an out-of-domain SAR benchmark (SSDD ship detection) further shows that distilling from the multi-modal teacher yields substantially more transferable SAR features—about ten absolute points above the non-distilled backbone—with M-FSAD-KD transferring best. Cross-architecture validation with a dual-stream DEYOLO teacher yields 48.6% at the student—1.1 absolute points below the MAIENet result—indicating that the framework transfers across the two representative teacher architectures tested (single-stream and dual-stream).- 4 September 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (17) , 3008
Open AccessM-FSAD-KD: Full-Link Multi-Granularity Distillation for SAR Object Detection
Multi-modal synthetic aperture radar (SAR)–optical object detectors raise detection accuracy by fusing complementary physical responses, but require both modalities to be simultaneously available at inference. When the optical stream becomes unavailable—under heavy cloud cover, night-time conditions, or downlink disruption—the detector reverts to SAR-only operation and accuracy degrades sharply. A natural remedy is to distil a multi-modal teacher into a SAR-only student via privileged-information knowledge distillation. However, we observe that the leading channel-wise feature-level method (CWD) reduces the student’s accuracy below the non-distilled baseline, with its smallest-target AP collapsing to near zero, because SAR speckle and target high-frequency edges share the same band and the alignment loss is dominated by broadband speckle energy. We refer to this failure mode as the speckle-fitting trap, formalize it as a gradient-pollution effect, and validate it through spectral and feature-manifold diagnostics. To counter the trap, we propose M-FSAD-KD, a full-link distillation framework whose neck-stage Fourier-gated alignment transfers low-frequency structural content while preserving target-edge high-frequency content; a joint spatial–channel attention mask, a shallow backbone adapter, and a response-level knowledge distillation (KD) term complete the chain. With a MAIENet teacher on OGSOD-1.0, the advantage of M-FSAD-KD over the strongest response-level KD baseline scales with student capacity: it matches KD on a 2.39 M-parameter student (both ≈48% mean average precision at an intersection-over-union (IoU) threshold of 0.5 (), averaged over multiple seeds) and exceeds it by 2.0 absolute points on a 19.98 M-parameter student ( over the non-distilled baseline), where it is the best of all distillation methods; at full convergence the 19.98 M-parameter student reaches 81.9% , within 8.9 absolute points of the multi-modal teacher. A frozen-feature transfer test to an out-of-domain SAR benchmark (SSDD ship detection) further shows that distilling from the multi-modal teacher yields substantially more transferable SAR features—about ten absolute points above the non-distilled backbone—with M-FSAD-KD transferring best. Cross-architecture validation with a dual-stream DEYOLO teacher yields 48.6% at the student—1.1 absolute points below the MAIENet result—indicating that the framework transfers across the two representative teacher architectures tested (single-stream and dual-stream). - Open Access
- 28 November 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (23) , 3866
MAIENet: Multi-Modality Adaptive Interaction Enhancement Network for SAR Object Detection
Syntheticaperture radar (SAR) object detection offers significant advantages in remote sensing applications, particularly under adverse weather conditions or low-light environments. However, single-modal SAR image object detection encounters numerous challenges, including speckle noise, limited texture information, and interference from complex backgrounds. To address these issues, we present Modality-Aware Adaptive Interaction Enhancement Network (MAIENet), a multimodal detection framework designed to effectively extract complementary information from both SAR and optical images, thereby enhancing object detection performance. MAIENet comprises three primary components: batch-wise splitting and channel-wise concatenation (BSCC) module, modality-aware adaptive interaction enhancement (MAIE) module, and multi-directional focus (MF) module. The BSCC module extracts and reorganizes features from each modality to preserve their distinct characteristics. The MAIE module component facilitates deeper cross-modal fusion through channel reweighting, deformable convolutions, atrous convolution, and attention mechanisms, enabling the network to emphasize critical modal information while reducing interference. By integrating features from various spatial directions, the MF module expands the receptive field, allowing the model to adapt more effectively to complex scenes. The MAIENet framework is end-to-end trainable and can be seamlessly integrated into existing detection networks with minimal modifications. Experimental results on the publicly available OGSOD-1.0 dataset demonstrate that MAIENet achieves superior performance compared with existing methods, achieving 90.8% .- 28 November 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (23) , 3866
Open AccessMAIENet: Multi-Modality Adaptive Interaction Enhancement Network for SAR Object Detection
Syntheticaperture radar (SAR) object detection offers significant advantages in remote sensing applications, particularly under adverse weather conditions or low-light environments. However, single-modal SAR image object detection encounters numerous challenges, including speckle noise, limited texture information, and interference from complex backgrounds. To address these issues, we present Modality-Aware Adaptive Interaction Enhancement Network (MAIENet), a multimodal detection framework designed to effectively extract complementary information from both SAR and optical images, thereby enhancing object detection performance. MAIENet comprises three primary components: batch-wise splitting and channel-wise concatenation (BSCC) module, modality-aware adaptive interaction enhancement (MAIE) module, and multi-directional focus (MF) module. The BSCC module extracts and reorganizes features from each modality to preserve their distinct characteristics. The MAIE module component facilitates deeper cross-modal fusion through channel reweighting, deformable convolutions, atrous convolution, and attention mechanisms, enabling the network to emphasize critical modal information while reducing interference. By integrating features from various spatial directions, the MF module expands the receptive field, allowing the model to adapt more effectively to complex scenes. The MAIENet framework is end-to-end trainable and can be seamlessly integrated into existing detection networks with minimal modifications. Experimental results on the publicly available OGSOD-1.0 dataset demonstrate that MAIENet achieves superior performance compared with existing methods, achieving 90.8% . - Open Access
- 9 March 2022
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2022, 1-16
Space Information Network Resource Scheduling for Cloud Computing: A Deep Reinforcement Learning Approach
With the development of satellite technology, space information networks (SINs) have been applied to various fields. SINs can provide more and more complex services and receive more and more tasks. The existing resource scheduling algorithms are difficult to play an efficient role in such a complex environment of resources and tasks. We propose a resource allocation scheme based on reinforcement learning. Firstly, according to the characteristics of the resources of SINs, we established the cloud computing architecture of SINs to manage the resources uniformly. Next, we adopt a variable granularity resources clustering algorithm based on fuzzy and hierarchical clustering algorithms. This algorithm can adaptively adjust the resource size and reduce the scheduling range. Finally, we model the resource scheduling process by a reinforcement learning algorithm to solve the joint resource scheduling problem. The simulation results show that the scheme can effectively reduce resources consumption, shorten the task execution time, and improve the resource utilization efficiency of SINs.
- 9 March 2022
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2022, 1-16
Open AccessSpace Information Network Resource Scheduling for Cloud Computing: A Deep Reinforcement Learning Approach
With the development of satellite technology, space information networks (SINs) have been applied to various fields. SINs can provide more and more complex services and receive more and more tasks. The existing resource scheduling algorithms are difficult to play an efficient role in such a complex environment of resources and tasks. We propose a resource allocation scheme based on reinforcement learning. Firstly, according to the characteristics of the resources of SINs, we established the cloud computing architecture of SINs to manage the resources uniformly. Next, we adopt a variable granularity resources clustering algorithm based on fuzzy and hierarchical clustering algorithms. This algorithm can adaptively adjust the resource size and reduce the scheduling range. Finally, we model the resource scheduling process by a reinforcement learning algorithm to solve the joint resource scheduling problem. The simulation results show that the scheme can effectively reduce resources consumption, shorten the task execution time, and improve the resource utilization efficiency of SINs.
- Open Access
- 3 April 2020
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 34 (01) , 1137-1144
Towards Hands-Free Visual Dialog Interactive Recommendation
With the recent advances of multimodal interactive recommendations, the users are able to express their preference by natural language feedback to the item images, to find the desired items. However, the existing systems either retrieve only one item or require the user to specify (e.g., by click or touch) the commented items from a list of recommendations in each user interaction. As a result, the users are not hands-free and the recommendations may be impractical. We propose a hands-free visual dialog recommender system to interactively recommend a list of items. At each time, the system shows a list of items with visual appearance. The user can comment on the list in natural language, to describe the desired features they further want. With these multimodal data, the system chooses another list of items to recommend. To understand the user preference from these multimodal data, we develop neural network models which identify the described items among the list and further predict the desired attributes. To achieve efficient interactive recommendations, we leverage the inferred user preference and further develop a novel bandit algorithm. Specifically, to avoid the system exploring more than needed, the desired attributes are utilized to reduce the exploration space. More importantly, to achieve sample efficient learning in this hands-free setting, we derive additional samples from the user's relative preference expressed in natural language and design a pairwise logistic loss in bandit learning. Our bandit model is jointly updated by the pairwise logistic loss on the additional samples derived from natural language feedback and the traditional logistic loss. The empirical results show that the probability of finding the desired items by our system is about 3 times as high as that by the traditional interactive recommenders, after a few user interactions.
- 3 April 2020
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 34 (01) , 1137-1144
Open AccessTowards Hands-Free Visual Dialog Interactive Recommendation
With the recent advances of multimodal interactive recommendations, the users are able to express their preference by natural language feedback to the item images, to find the desired items. However, the existing systems either retrieve only one item or require the user to specify (e.g., by click or touch) the commented items from a list of recommendations in each user interaction. As a result, the users are not hands-free and the recommendations may be impractical. We propose a hands-free visual dialog recommender system to interactively recommend a list of items. At each time, the system shows a list of items with visual appearance. The user can comment on the list in natural language, to describe the desired features they further want. With these multimodal data, the system chooses another list of items to recommend. To understand the user preference from these multimodal data, we develop neural network models which identify the described items among the list and further predict the desired attributes. To achieve efficient interactive recommendations, we leverage the inferred user preference and further develop a novel bandit algorithm. Specifically, to avoid the system exploring more than needed, the desired attributes are utilized to reduce the exploration space. More importantly, to achieve sample efficient learning in this hands-free setting, we derive additional samples from the user's relative preference expressed in natural language and design a pairwise logistic loss in bandit learning. Our bandit model is jointly updated by the pairwise logistic loss on the additional samples derived from natural language feedback and the traditional logistic loss. The empirical results show that the probability of finding the desired items by our system is about 3 times as high as that by the traditional interactive recommenders, after a few user interactions.
- Open Access
- 11 August 2013
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Effective string processing and matching for author disambiguation
- 11 August 2013
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessEffective string processing and matching for author disambiguation