7 papers · 1 filter
Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
Meng Lou, Hanzhong Guo, Linwei Chen +1
Recent studies suggest that Reinforcement Fine-Tuning (RFT) is inherently more resilient to catastrophic forgetting than Supervised Fine-Tuning (SFT). However, whether RFT (e.g., G…
Fourier Angle Alignment for Oriented Object Detection in Remote Sensing
Changyu Gu, Linwei Chen, Lin Gu +1
In remote sensing rotated object detection, mainstream methods suffer from two bottlenecks, directional incoherence at detector neck and task conflict at detecting head. Ulitising…
SkinFlow: Efficient Information Transmission for Open Dermatological Diagnosis via Dynamic Visual Encoding and Staged RL
Lijun Liu, Linwei Chen, Zhishou Zhang +7
General-purpose Large Vision-Language Models (LVLMs), despite their massive scale, often falter in dermatology due to "diffuse attention" - the inability to disentangle subtle path…
Frequency-Dynamic Attention Modulation for Dense Prediction
Linwei Chen, Lin Gu, Ying Fu
Vision Transformers (ViTs) have significantly advanced computer vision, demonstrating strong performance across various tasks. However, the attention mechanism in ViTs makes each l…
Spatial Frequency Modulation for Semantic Segmentation
Linwei Chen, Ying Fu, Lin Gu +2
High spatial frequency information, including fine details like textures, significantly contributes to the accuracy of semantic segmentation. However, according to the Nyquist-Shan…
Frequency-Adaptive Dilated Convolution for Semantic Segmentation
Linwei Chen, Lin Gu, Ying Fu
Dilated convolution, which expands the receptive field by inserting gaps between its consecutive elements, is widely employed in computer vision. In this study, we propose three st…