GTR: Gated Token Recurrence for Efficient Dense Prediction
为解决自注意力机制在高分辨率图像上的效率问题，本文提出Gated Token Recurrence (GTR)方法，采用无softmax的循环结构，提高了密集预测任务的效率。
0 citationsRead paper
Selected work
Representative Papers
A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps
This work addresses the challenges of few-shot object detection in cross-domain scenarios—namely, severe data scarcity, optimization instability, and poor generalization—by proposing a parameter-free hybrid ensemble decoder combined with a unified progressive fine-tuning framework. The approach enhances prediction diversity through parallel decoding branches and stabilizes training via a denoising query mechanism and platform-aware learning rate scheduling. Leveraging the shared hierarchical structure of pretrained models, the method achieves significant performance gains without relying on sophisticated data augmentation or extensive hyperparameter tuning. On the RF100-VL benchmark under the 10-shot setting, it attains 41.9 mAP, outperforming SAM3 (35.7 mAP), and demonstrates superior robustness to out-of-distribution shifts in mixed-domain evaluations on CD-FSOD.
0 citationsRead paper
Recent publications
Latest Papers
GTR: Gated Token Recurrence for Efficient Dense Prediction
为解决自注意力机制在高分辨率图像上的效率问题，本文提出Gated Token Recurrence (GTR)方法，采用无softmax的循环结构，提高了密集预测任务的效率。
0 citationsRead paper
A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps
This work addresses the challenges of few-shot object detection in cross-domain scenarios—namely, severe data scarcity, optimization instability, and poor generalization—by proposing a parameter-free hybrid ensemble decoder combined with a unified progressive fine-tuning framework. The approach enhances prediction diversity through parallel decoding branches and stabilizes training via a denoising query mechanism and platform-aware learning rate scheduling. Leveraging the shared hierarchical structure of pretrained models, the method achieves significant performance gains without relying on sophisticated data augmentation or extensive hyperparameter tuning. On the RF100-VL benchmark under the 10-shot setting, it attains 41.9 mAP, outperforming SAM3 (35.7 mAP), and demonstrates superior robustness to out-of-distribution shifts in mixed-domain evaluations on CD-FSOD.
0 citationsRead paper