Search Results for author:
Found 5 papers, 2 papers with code
A Flexible 2.5D Medical Image Segmentation Approach with In-Slice and Cross-Slice Attention
This module uses the cross-slice attention mechanism to effectively capture 3D spatial information by learning long-range dependencies between the center slice (for segmentation) and its neighboring slices.
SAM-Lightening: A Lightweight Segment Anything Model with Dilated Flash Attention to Achieve 30 times Acceleration
Moreover, it takes only 244MB memory, which is 3. 5\% of the vanilla SAM.
MicroSegNet: A Deep Learning Approach for Prostate Segmentation on Micro-Ultrasound Images
During the training process, MicroSegNet focuses more on regions that are hard to segment (hard regions), characterized by discrepancies between expert and non-expert annotations.
Human-centric Spatio-Temporal Video Grounding With Visual Transformers
HC-STVG is a video grounding task that requires both spatial (where) and temporal (when) localization.
Robustness-aware 2-bit quantization with real-time performance for neural network
The structural information learned from NN not only plays an important role in improving the performance but also allows for further fine tuning of the quantization network by applying the Lipschitz constraint to the structural loss.
