Exploring vision transformer layer choosing for semantic segmentation
원문 초록
Extensive work has demonstrated the effectiveness of Vision Transformers. The plain Vision Transformer tends to obtain multi-scale features by selecting fixed layers, or the last layer of features aiming to achieve higher performance in dense prediction tasks. However, this selection is often based on manual operation. And different samples often exhibit different features at different layers (e.g., edge, structure, texture, detail, etc.). This requires us to seek a dynamic adaptive fusion method to filter different layer features. In this paper, unlike previous encoder and decoder work, we design a neck network for adaptive fusion and feature selection, called ViTController. We validate the effectiveness of our method on different datasets and models and surpass previous state-of-the-art methods. Finally, our method can also be used as a plug-in module and inserted into different networks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation
Rethinking Decoder Design: Improving Biomarker Segmentation Using Depth-to-Space Restoration and Residual Linear Attention
Pre-Trained LLM is a Semantic-Aware and Generalizable Segmentation Booster
MedSAM-CA: A CNN-Augmented ViT with Attention-Enhanced Multi-Scale Fusion for Medical Image Segmentation
TASeg: Text-aware RGB-T Semantic Segmentation based on Fine-tuning Vision Foundation Models
MedSeg-R: Medical Image Segmentation with Clinical Reasoning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.