Image de couverture de livre

SAILS: Segment Anything with Incrementally Learned Semantics for Task-Invariant and Training-Free Continual Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Muralidhara, Shishir, Stricker, Didier, Schuster, René
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MILE: Mixture of Incremental LoRA Experts for Continual Semantic Segmentation across Domains and Modalities
par: Muralidhara, Shishir, et autres
Publié: (2026)

Domain-Incremental Semantic Segmentation for Autonomous Driving under Adverse Driving Conditions
par: Muralidhara, Shishir, et autres
Publié: (2025)

Modality-Incremental Learning with Disjoint Relevance Mapping Networks for Image-based Semantic Segmentation
par: Hegde, Niharika, et autres
Publié: (2024)

CLoRA: Parameter-Efficient Continual Learning with Low-Rank Adaptation
par: Muralidhara, Shishir, et autres
Publié: (2025)

CLEO: Continual Learning of Evolving Ontologies
par: Muralidhara, Shishir, et autres
Publié: (2024)

Sensor Generalization for Adaptive Sensing in Event-based Object Detection via Joint Distribution Training
par: Saha, Aheli, et autres
Publié: (2026)

LiREC-Net: A Target-Free and Learning-Based Network for LiDAR, RGB, and Event Calibration
par: Dash, Aditya Ranjan, et autres
Publié: (2026)

RMS-FlowNet++: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds
par: Battrawy, Ramy, et autres
Publié: (2024)

ShapeAug: Occlusion Augmentation for Event Camera Data
par: Bendig, Katharina, et autres
Publié: (2024)

ShapeAug++: More Realistic Shape Augmentation for Event Data
par: Bendig, Katharina, et autres
Publié: (2024)

EgoFlowNet: Non-Rigid Scene Flow from Point Clouds with Ego-Motion Support
par: Battrawy, Ramy, et autres
Publié: (2024)

PoseAdapt: Sustainable Human Pose Estimation via Continual Learning Benchmarks and Toolkit
par: Khan, Muhammad Saif Ullah, et autres
Publié: (2024)

SF3D-RGB: Scene Flow Estimation from Monocular Camera and Sparse LiDAR
par: Alhimdiat, Rajai, et autres
Publié: (2026)

AnonyNoise: Anonymizing Event Data with Smart Noise to Outsmart Re-Identification and Preserve Privacy
par: Bendig, Katharina, et autres
Publié: (2024)

SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks
par: Xie, Yaxu, et autres
Publié: (2024)

Continual Learning for Segment Anything Model Adaptation
par: Yang, Jinglong, et autres
Publié: (2024)

Task Consistent Prototype Learning for Incremental Few-shot Semantic Segmentation
par: Xu, Wenbo, et autres
Publié: (2024)

PanoSAMic: Panoramic Image Segmentation from SAM Feature Encoding and Dual View Fusion
par: Chamseddine, Mahdi, et autres
Publié: (2026)

Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning
par: Wu, Fangwen, et autres
Publié: (2025)

Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data
par: Camuffo, Elena, et autres
Publié: (2023)

Beyond Averages: Open-Vocabulary 3D Scene Understanding with Gaussian Splatting and Bag of Embeddings
par: Arafa, Abdalla, et autres
Publié: (2025)

Object-Centric 2D Gaussian Splatting: Background Removal and Occlusion-Aware Pruning for Compact Object Models
par: Rogge, Marcel, et autres
Publié: (2025)

JOPP-3D: Joint Open Vocabulary Semantic Segmentation on Point Clouds and Panoramas
par: Inuganti, Sandeep, et autres
Publié: (2026)

Learning to Prompt Segment Anything Models
par: Huang, Jiaxing, et autres
Publié: (2024)

Learning from the Web: Language Drives Weakly-Supervised Incremental Learning for Semantic Segmentation
par: Liu, Chang, et autres
Publié: (2024)

S4M: 4-points to Segment Anything
par: Meyer, Adrien, et autres
Publié: (2025)

SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completion
par: Nazir, Danish, et autres
Publié: (2022)

Towards End-to-End Semi-Supervised Table Detection with Semantic Aligned Matching Transformer
par: Shehzadi, Tahira, et autres
Publié: (2024)

Learning Yourself: Class-Incremental Semantic Segmentation with Language-Inspired Bootstrapped Disentanglement
par: Wu, Ruitao, et autres
Publié: (2025)

Background Adaptation with Residual Modeling for Exemplar-Free Class-Incremental Semantic Segmentation
par: Zhang, Anqi, et autres
Publié: (2024)

A Classifier-Free Incremental Learning Framework for Scalable Medical Image Segmentation
par: Chen, Xiaoyang, et autres
Publié: (2024)

VVitCutLER: Towards Unsupervised Object Detection and Segmentation in Videos
par: Lu, Zhijing, et autres
Publié: (2026)

Condition-Invariant Semantic Segmentation
par: Sakaridis, Christos, et autres
Publié: (2023)

Annotation-Efficient Task Guidance for Medical Segment Anything
par: Ward, Tyler, et autres
Publié: (2024)

Boosting Few-Shot Semantic Segmentation Via Segment Anything Model
par: Feng, Chen-Bin, et autres
Publié: (2024)

Completely Weakly Supervised Class-Incremental Learning for Semantic Segmentation
par: Kim, David Minkwan, et autres
Publié: (2025)

Matching Anything by Segmenting Anything
par: Li, Siyuan, et autres
Publié: (2024)

Exemplar-Free Class Incremental Learning via Incremental Representation
par: Huang, Libo, et autres
Publié: (2024)

Virtually Objective Quantification of in vitro Wound Healing Scratch Assays with the Segment Anything Model
par: Löwenstein, Katja, et autres
Publié: (2024)

Semantic-Guided Dynamic Sparsification for Pre-Trained Model-based Class-Incremental Learning
par: Liu, Ruiqi, et autres
Publié: (2026)