Weakly Supervised Segmentation as Semantic-Based Regularization
cs.CV, cs.AI
Submitted: 2026-05-13
Updated: 2026-11-09
Code: https://github.com/StefanoColamonaco/Logic-Guided-Segmentation
Terminology
Sources
- SegDiff: Image Segmentation with Diffusion Probabilistic Models
- TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
- SAM-Med2D
- Neurosymbolic Object-Centric Learning with Distant Supervision
- The DeepLog Neurosymbolic Machine
- REFUGE2 Challenge: A Treasure Trove for Multi-Dimension Analysis and Evaluation in Glaucoma Screening
- Segment Anything is A Good Pseudo-label Generator for Weakly Supervised Semantic Segmentation
- DeepLog: A Software Framework for Modular Neurosymbolic AI
- An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems
- Customized Segment Anything Model for Medical Image Segmentation
- WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs