6 papers
HeteroTune: Efficient Federated Learning for Large Heterogeneous Models
Ruofan Jia, Weiying Xie, Jie Lei +3
While large pre-trained models have achieved impressive performance across AI tasks, their deployment in privacy-sensitive and distributed environments remains challenging. Federat…
Mamba: CLIP-driven Mamba Model for Multi-modal Remote Sensing Classification
Mingxiang Cao, Weiying Xie, Xin Zhang +4
Multi-modal fusion holds great promise for integrating information from different modalities. However, due to a lack of consideration for modal consistency, existing multi-modal fu…
E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detection
Jiaqing Zhang, Mingxiang Cao, Weiying Xie +5
Multimodal image fusion and object detection are crucial for autonomous driving. While current methods have advanced the fusion of texture details and semantic information, their c…
Towards Accurate and Efficient Sub-8-Bit Integer Training
Wenjin Guo, Donglai Liu, Weiying Xie +7
Neural network training is a memory- and compute-intensive task. Quantization, which enables low-bitwidth formats in training, can significantly mitigate the workload. To reduce qu…
SeaDATE: Remedy Dual-Attention Transformer with Semantic Alignment via Contrast Learning for Multimodal Object Detection
Shuhan Dong, Yunsong Li, Weiying Xie +4
Multimodal object detection leverages diverse modal information to enhance the accuracy and robustness of detectors. By learning long-term dependencies, Transformer can effectively…
Multi-scale direction-aware SAR object detection network via global information fusion
Mingxiang Cao, Weiying Xie, Jie Lei +3
Deep learning has driven significant progress in object detection using Synthetic Aperture Radar (SAR) imagery. Existing methods, while achieving promising results, often struggle…