DPNeXt: A Lightweight Multi-Scale Feature Fusion Framework for Efficient ViT-Based Multi-Task Dense Prediction
DPNeXt:用于基于高效视觉Transformer的多任务密集预测的轻量级多尺度特征融合框架
机构 * School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院电气工程学院)
AI总结 研究针对机器人感知系统多任务学习中现有解码策略瓶颈,提出DPNeXt框架,用双深度可分离倒置瓶颈及MTBG策略,在多任务密集预测上表现出色,相比DPT大幅减少参数并提升推理速度。
Comments 8 pages, 5 figures. Accepted to the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026)