BALD-SAM: Disagreement-based Active Prompting in Interactive Segmentation
cs.CV, cs.AI
Submitted: 2026-03-11
Updated: 2026-11-05
Terminology
Sources
- SAM-PARSER: Fine-tuning SAM Efficiently by Parameter Space Reconstruction
- A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models
- Active Learning for Convolutional Neural Networks: A Core-Set Approach
- Rethinking Atrous Convolution for Semantic Image Segmentation
- SegGPT: Segmenting Everything In Context
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Customized Segment Anything Model for Medical Image Segmentation
- SAM 2: Segment Anything in Images and Videos
- Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings
- Personalize Segment Anything Model with One Shot
- Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
- Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
- Robustness of Segment Anything Model (SAM) for Autonomous Driving in Adverse Weather Conditions
- Can SAM Segment Polyps?
- Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
- Bayesian Active Learning for Classification and Preference Learning
- CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation
- NDD20: A large-scale few-shot dolphin dataset for coarse and fine-grained categorisation
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