SOTAVerified

Weakly-Supervised Semantic Segmentation

The semantic segmentation task is to assign a label from a label set to each pixel in an image. In the case of fully supervised setting, the dataset consists of images and their corresponding pixel-level class-specific annotations (expensive pixel-level annotations). However, in the weakly-supervised setting, the dataset consists of images and corresponding annotations that are relatively easy to obtain, such as tags/labels of objects present in the image.

( Image credit: Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 296 papers

TitleStatusHype
Learning without Exact Guidance: Updating Large-scale High-resolution Land Cover Maps from Low-resolution Historical LabelsCode2
Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with TransformersCode2
Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic SegmentationCode2
DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic SegmentationCode2
Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic SegmentationCode2
From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic SegmentationCode2
Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic SegmentationCode2
Modeling the Label Distributions for Weakly-Supervised Semantic SegmentationCode2
CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic SegmentationCode2
Cross Language Image Matching for Weakly Supervised Semantic SegmentationCode2
Dual Progressive Transformations for Weakly Supervised Semantic SegmentationCode1
DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic SegmentationCode1
AME-CAM: Attentive Multiple-Exit CAM for Weakly Supervised Segmentation on MRI Brain TumorCode1
BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance SegmentationCode1
Context Decoupling Augmentation for Weakly Supervised Semantic SegmentationCode1
Affinity Attention Graph Neural Network for Weakly Supervised Semantic SegmentationCode1
Discriminative Region Suppression for Weakly-Supervised Semantic SegmentationCode1
Adaptive Early-Learning Correction for Segmentation from Noisy AnnotationsCode1
Class-incremental Continual Learning for Instance Segmentation with Image-level Weak SupervisionCode1
Background Activation Suppression for Weakly Supervised Object Localization and Semantic SegmentationCode1
Class Re-Activation Maps for Weakly-Supervised Semantic SegmentationCode1
Class Tokens Infusion for Weakly Supervised Semantic SegmentationCode1
Complementary Patch for Weakly Supervised Semantic SegmentationCode1
Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic SegmentationCode1
Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic SegmentationCode1
Show:102550
← PrevPage 1 of 12Next →

No leaderboard results yet.