Imagen de Portada

SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Adamyan, Alen, Čížek, Tomáš, Straka, Matej, Janouskova, Klara, Schmid, Martin
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Koo-Fu CLIP: Closed-Form Adaptation of Vision-Language Models via Fukunaga-Koontz Linear Discriminant Analysis
por: Suchanek, Matej, et al.
Publicado: (2026)

SAM 2: Segment Anything in Images and Videos
por: Ravi, Nikhila, et al.
Publicado: (2024)

AM-SAM: Automated Prompting and Mask Calibration for Segment Anything Model
por: Li, Yuchen, et al.
Publicado: (2024)

MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation
por: Liao, Chenfei, et al.
Publicado: (2025)

Single Image Test-Time Adaptation for Segmentation
por: Janouskova, Klara, et al.
Publicado: (2023)

From SAM to SAM 2: Exploring Improvements in Meta's Segment Anything Model
por: Geetha, Athulya Sundaresan, et al.
Publicado: (2024)

StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models
por: Nguyen, Duy M. H., et al.
Publicado: (2026)

PTQ4SAM: Post-Training Quantization for Segment Anything
por: Lv, Chengtao, et al.
Publicado: (2024)

DeiSAM: Segment Anything with Deictic Prompting
por: Shindo, Hikaru, et al.
Publicado: (2024)

AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization
por: Zhang, Wenlun, et al.
Publicado: (2025)

AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning
por: Huang, Duojun, et al.
Publicado: (2024)

RemoteSAM: Towards Segment Anything for Earth Observation
por: Yao, Liang, et al.
Publicado: (2025)

Atlas-Assisted Segment Anything Model for Fetal Brain MRI (FeTal-SAM)
por: Zeng, Qi, et al.
Publicado: (2026)

Evaluation of Segment Anything Model 2: The Role of SAM2 in the Underwater Environment
por: Lian, Shijie, et al.
Publicado: (2024)

Medical SAM 2: Segment medical images as video via Segment Anything Model 2
por: Zhu, Jiayuan, et al.
Publicado: (2024)

Bringing the Context Back into Object Recognition, Robustly
por: Janouskova, Klara, et al.
Publicado: (2024)

Robust Context-Aware Object Recognition
por: Janouskova, Klara, et al.
Publicado: (2025)

RepViT-SAM: Towards Real-Time Segmenting Anything
por: Wang, Ao, et al.
Publicado: (2023)

EfficientViT-SAM: Accelerated Segment Anything Model Without Accuracy Loss
por: Zhang, Zhuoyang, et al.
Publicado: (2024)

Biomedical SAM 2: Segment Anything in Biomedical Images and Videos
por: Yan, Zhiling, et al.
Publicado: (2024)

Q-SAM2: Accurate Quantization for Segment Anything Model 2
por: Farronato, Nicola, et al.
Publicado: (2025)

SAM-OCTA2: Layer Sequence OCTA Segmentation with Fine-tuned Segment Anything Model 2
por: Chen, Xinrun, et al.
Publicado: (2024)

Multimodal Large Language Models as Image Classifiers
por: Kisel, Nikita, et al.
Publicado: (2026)

A Distractor-Aware Memory for Visual Object Tracking with SAM2
por: Videnovic, Jovana, et al.
Publicado: (2024)

RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything
por: Xu, Shilin, et al.
Publicado: (2024)

Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation
por: Ye, Maoyuan, et al.
Publicado: (2024)

SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes
por: Wang, Yuji, et al.
Publicado: (2025)

Det-SAM2:Technical Report on the Self-Prompting Segmentation Framework Based on Segment Anything Model 2
por: Wang, Zhiting, et al.
Publicado: (2024)

FusionSAM: Visual Multi-Modal Learning with Segment Anything
por: Li, Daixun, et al.
Publicado: (2024)

Compress Any Segment Anything Model (SAM)
por: Fan, Juntong, et al.
Publicado: (2025)

SAM3-I: Segment Anything with Instructions
por: Li, Jingjing, et al.
Publicado: (2025)

PaveSAM Segment Anything for Pavement Distress
por: Owor, Neema Jakisa, et al.
Publicado: (2024)

BiSeg-SAM: Weakly-Supervised Post-Processing Framework for Boosting Binary Segmentation in Segment Anything Models
por: Su, Encheng, et al.
Publicado: (2025)

A Multispectral Automated Transfer Technique (MATT) for machine-driven image labeling utilizing the Segment Anything Model (SAM)
por: Gallagher, James E., et al.
Publicado: (2024)

TinySAM: Pushing the Envelope for Efficient Segment Anything Model
por: Shu, Han, et al.
Publicado: (2023)

SAQ-SAM: Semantically-Aligned Quantization for Segment Anything Model
por: Zhang, Jing, et al.
Publicado: (2025)

pFedSAM: Personalized Federated Learning of Segment Anything Model for Medical Image Segmentation
por: Wang, Tong, et al.
Publicado: (2025)

OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation
por: Zhong, Ding, et al.
Publicado: (2025)

Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation
por: Wu, Junde, et al.
Publicado: (2023)

SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation
por: Xiong, Xinyu, et al.
Publicado: (2024)