Multi-Faceted Adaptive Token Pruning for Efficient Remote Sensing Image Segmentation
Global context information is essential for semantic segmentation of remote sensing (RS) images. Due to their remarkable capability to capture global context information and model long-range dependencies, vision transformers have demonstrated great performance on semantic segmentation. However, the...
Saved in:
| Main Authors: | Chuge Zhang, Jian Yao |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/14/2508 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Re-Parameterization After Pruning: Lightweight Algorithm Based on UAV Remote Sensing Target Detection
by: Yang Yang, et al.
Published: (2024-12-01) -
Efficient Pruning of Detection Transformer in Remote Sensing Using Ant Colony Evolutionary Pruning
by: Hailin Su, et al.
Published: (2024-12-01) -
Neural Network Pruning for Lightweight Metal Corrosion Image Segmentation Models
by: Vincent F. Yu, et al.
Published: (2025-01-01) -
Accelerating Inference in Retrieval-Augmented Generation Models for Long-Form Question Answering via Dynamic Token Pruning
by: Wooseok Kim, et al.
Published: (2025-07-01) -
DMA-Net: Dynamic Morphology-Aware Segmentation Network for Remote Sensing Images
by: Chao Deng, et al.
Published: (2025-07-01)