SARTM: Segment Any RGB Thermal Model with Language aided Distillation

arXiv:2505.01950 · cs.CV, cs.AI · Submitted 2025-05-04 · Read on arXiv

cs.CV, cs.AI

Submitted: 2025-05-04

Updated: 2026-09-01

Comments: 33 pages. Substantially revised manuscript; author list updated with the consent of all affected authors. arXiv admin note: text overlap with arXiv:2412.04220 by other authors

Code: https://github.com/wahaha-debug/SARTM

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 13× in this paper · explained in 1 episode
• Distillation — 11× in this paper · explained in 2 episodes
• Adaptation — 9× in this paper · explained in 1 episode
• Benchmark — 9× in this paper · explained in 2 episodes
• Loss Function — 9× in this paper · explained in 2 episodes
• Segment Anything Model — 9× in this paper
• Alignment — 8× in this paper · explained in 1 episode
• Generalization — 7× in this paper · explained in 13 episodes
• Transformer — 7× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 6× in this paper
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Downstream Tasks — 5× in this paper · explained in 2 episodes
• Segment Anything Model (SAM) — 5× in this paper · explained in 2 episodes
• Semantic Feature Map — 5× in this paper
• Cross-Modal Knowledge Distillation — 4× in this paper
• Feature Extraction — 4× in this paper · explained in 2 episodes
• Fine-Grained Feature Pyramid — 4× in this paper
• Knowledge Distillation — 4× in this paper · explained in 11 episodes
• Modality Gap — 4× in this paper · explained in 4 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Instance Segmentation — 3× in this paper · explained in 3 episodes
• Intermediate-Resolution Feature Pyramid — 3× in this paper
• Ablation Studies — 2× in this paper · explained in 1 episode
• Ablation study — 2× in this paper · explained in 1 episode
• Aggregation — 2× in this paper · explained in 1 episode
• Embeddings — 2× in this paper · explained in 2 episodes
• F1 Score — 2× in this paper · explained in 3 episodes
• Feature Pyramid Network — 2× in this paper
• Foundation Model — 2× in this paper · explained in 3 episodes
• Hypernetwork — 2× in this paper · explained in 3 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Segmentation Masks — 2× in this paper · explained in 2 episodes
• Semantic Understanding — 2× in this paper · explained in 2 episodes
• Vision-language models — 2× in this paper · explained in 2 episodes
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Adaptability — 1× in this paper · explained in 1 episode
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Composite Loss Function — 1× in this paper · explained in 2 episodes
• Contextual Awareness — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Data Fusion — 1× in this paper · explained in 3 episodes
• Dual-Stream Architecture — 1× in this paper · explained in 3 episodes
• Feature Fusion Module — 1× in this paper
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Multi-modal Inputs — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Two-Stage Framework — 1× in this paper · explained in 2 episodes

Sources

• Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks
• SAM 2: Segment Anything in Images and Videos
• ImageBind-LLM: Multi-modality Instruction Tuning
• LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
• InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
• MAGIC++: Efficient and Resilient Modality-Agnostic Semantic Segmentation via Hierarchical Modality Selection
• Learning Robust Anymodal Segmentor with Unimodal and Cross-modal Distillation
• Customize Segment Anything Model for Multi-Modal Semantic Segmentation with Mixture of LoRA Experts
• Unveiling the Potential of Segment Anything Model 2 for RGB-Thermal Semantic Segmentation with Language Guidance
• OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation
• Unleashing the Potential of SAM2 for Biomedical Images and Videos: A Survey
• Towards Segment Anything Model (SAM) for Medical Image Segmentation: A Survey
• Segment and Track Anything
• OmniBind: Teach to Build Unequal-Scale Modality Interaction for Omni-Bind of All
• GPT-4 Technical Report
• U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models