Efficient Multi-Task Training with Adaptive Feature Alignment for Universal Image Segmentation
Universal image segmentation aims to handle all segmentation tasks within a single model architecture and ideally requires only one training phase. To achieve task-conditioned joint training, a task token needs to be used in the multi-task training to condition the model for specific tasks. Existing...
Saved in:
Main Authors: | Yipeng Qu, Joohee Kim |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2025-01-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/25/2/359 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Adaptive Month Matching: A Phenological Alignment Method for Transfer Learning in Cropland Segmentation
by: Reza Maleki, et al.
Published: (2025-01-01) -
MEVDT: Multi-modal event-based vehicle detection and tracking datasetDeep Blue Data
by: Zaid A. El Shair, et al.
Published: (2025-02-01) -
Dual-Granularity Feature Alignment for Change Detection in Remote Sensing Images
by: Feng Zhou, et al.
Published: (2025-01-01) -
DWSD: Dense waste segmentation datasetMendeley Data
by: Asfak Ali, et al.
Published: (2025-04-01) -
AFN-Net: Adaptive Fusion Nucleus Segmentation Network Based on Multi-Level U-Net
by: Ming Zhao, et al.
Published: (2025-01-01)