A Classification Refinement Strategy for Semantic Segmentation
Based on the observation that semantic segmentation errors are partially predictable, we propose a compact formulation using confusion statistics of the trained classifier to refine (re-estimate) the initial pixel label hypotheses. The proposed strategy is contingent upon computing the classifier confusion probabilities for a given dataset and estimating a relevant prior on the object classes present in the image to be classified. We provide a procedure to robustly estimate the confusion probabilities and explore multiple prior definitions. Experiments are shown comparing performances on multiple challenging datasets using different priors to improve a state-of-the-art semantic segmentation classifier. This study demonstrates the potential to significantly improve semantic labeling and motivates future work for reliable label prior estimation from images.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationGeneral ClassificationSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
Synergistic Foundation Models for Semi-Supervised Fetal Cardiac Ultrasound Analysis: SAM-Med2D Boundary Refinement and DINOv3 Semantic Enhancement
We present a semi-supervised framework for joint segmentation and classification of fetal cardiac ultrasound images. Built upon the EchoCare multi-task backbone, our method integrates SAM-Med2D for boundary refinement an…
Inferring the Class Conditional Response Map for Weakly Supervised Semantic Segmentation
Image-level weakly supervised semantic segmentation (WSSS) relies on class activation maps (CAMs) for pseudo labels generation. As CAMs only highlight the most discriminative regions of objects, the generated pseudo labe…
SegmentationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic SegmentationCRIS: Collaborative Refinement Integrated with Segmentation for Polyp Segmentation
Accurate detection of colorectal cancer and early prevention heavily rely on precise polyp identification during gastrointestinal colonoscopy. Due to limited data, many current state-of-the-art deep learning methods for …
Image SegmentationMedical Image SegmentationSegmentationSemantic SegmentationRePL: Pseudo-label Refinement for Semi-supervised LiDAR Semantic Segmentation
Semi-supervised learning for LiDAR semantic segmentation often suffers from error propagation and confirmation bias caused by noisy pseudo-labels. To tackle this chronic issue, we introduce RePL, a novel framework that e…
LIDAR Semantic SegmentationDiscriminative Region Suppression for Weakly-Supervised Semantic Segmentation
Weakly-supervised semantic segmentation (WSSS) using image-level labels has recently attracted much attention for reducing annotation costs. Existing WSSS methods utilize localization maps from the classification network…
SegmentationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation