Fully Using Classifiers for Weakly Supervised Semantic Segmentation with Modified Cues
This paper proposes a novel weakly-supervised semantic segmentation method using image-level label only. The class-specific activation maps from the well-trained classifiers are used as cues to train a segmentation network. The well-known defects of these cues are coarseness and incompleteness. We use super-pixel to refine them, and fuse the cues extracted from both a color image trained classifier and a gray image trained classifier to compensate for their incompleteness. The conditional random field is adapted to regulate the training process and to refine the outputs further. Besides initializing the segmentation network, the previously trained classifier is also used in the testing phase to suppress the non-existing classes. Experimental results on the PASCAL VOC 2012 dataset illustrate the effectiveness of our method.
Code (0)
등록된 구현이 없습니다.
Tasks
SegmentationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic SegmentationSimilar Papers 제목 키워드 기반
Pseudo-mask Matters in Weakly-supervised Semantic Segmentation
Most weakly supervised semantic segmentation (WSSS) methods follow the pipeline that generates pseudo-masks initially and trains the segmentation model with the pseudo-masks in fully supervised manner after. However, we …
SegmentationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic SegmentationConvolutional Simplex Projection Network (CSPN) for Weakly Supervised Semantic Segmentation
Weakly supervised semantic segmentation has been a subject of increased interest due to the scarcity of fully annotated images. We introduce a new approach for solving weakly supervised semantic segmentation with deep Co…
SegmentationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic SegmentationSimple Does It: Weakly Supervised Instance and Semantic Segmentation
Semantic labelling and instance segmentation are two tasks that require particularly costly annotations. Starting from weak supervision in the form of bounding box detection annotations, we propose a new approach that do…
Instance SegmentationSegmentationSemantic SegmentationMulti-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning
Supervised object detection and semantic segmentation require object or even pixel level annotations. When there exist image level labels only, it is challenging for weakly supervised algorithms to achieve accurate predi…
ClusteringGeneral Classificationimage-classificationImage Classification+15Upsampling DINOv2 features for unsupervised vision tasks and weakly supervised materials segmentation
The features of self-supervised vision transformers (ViTs) contain strong semantic and positional information relevant to downstream tasks like object localization and segmentation. Recent works combine these features wi…
Clusteringgraph partitioningObject LocalizationProperty Prediction+2