This repository contains code, figures, source data, and manuscript assets for a focused reliability analysis of SAM-family promptable segmentation models under controlled box-prompt perturbations.
Overview: Compares the leading computer vision APIs, multimodal AI models, and open-source vision frameworks available in ...
The paper has been accepted by IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR) 2024, 2nd Workshop on Scene Graphs and Graph Representation Learning. Predicted road network graph in ...
We improve SAM for plant disease segmentation by introducing a ResNet-50-based detail compensation branch that supplements the fine-grained lesion textures and boundary cues that are difficult for SAM ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results