Imagen de Portada

SparseSAM: Structured Sparsification of Activations in Segment Anything Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Tran, Hoai-Chau, Nguyen, Chi H., Nguyen, Duy M. H., Niepert, Mathias, Lai, Fan, Doan, Khoa D.
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?
por: Tran, Tuan Anh, et al.
Publicado: (2025)

SAM-EG: Segment Anything Model with Egde Guidance framework for efficient Polyp Segmentation
por: Trinh, Quoc-Huy, et al.
Publicado: (2024)

Dude: Dual Distribution-Aware Context Prompt Learning For Large Vision-Language Model
por: Nguyen, Duy M. H., et al.
Publicado: (2024)

Unveiling Concept Attribution in Diffusion Models
por: Nguyen, Quang H., et al.
Publicado: (2024)

Memorizing SAM: 3D Medical Segment Anything Model with Memorizing Transformer
por: Shao, Xinyuan, et al.
Publicado: (2024)

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

The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models
por: Nguyen, Phuc Minh, et al.
Publicado: (2025)

SegMaFormer: A Hybrid State-Space and Transformer Model for Efficient Segmentation
por: Nguyen, Duy D., et al.
Publicado: (2026)

WriteViT: Handwritten Text Generation with Vision Transformer
por: Nam, Dang Hoai, et al.
Publicado: (2025)

FW-GAN: Frequency-Driven Handwriting Synthesis with Wave-Modulated MLP Generator
por: Khoa, Huynh Tong Dang, et al.
Publicado: (2025)

Venomancer: Towards Imperceptible and Target-on-Demand Backdoor Attacks in Federated Learning
por: Nguyen, Son, et al.
Publicado: (2024)

Amodal Instance Segmentation with Diffusion Shape Prior Estimation
por: Tran, Minh, et al.
Publicado: (2024)

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

The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation
por: Nguyen, Thanh-Danh, 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)

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

BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model
por: Song, Yiran, et al.
Publicado: (2024)

SAM Struggles in Concealed Scenes -- Empirical Study on Segment Anything
por: Ji, Ge-Peng, et al.
Publicado: (2023)

SAM3D: Segment Anything Model in Volumetric Medical Images
por: Bui, Nhat-Tan, et al.
Publicado: (2023)

PlaneSAM: Multimodal Plane Instance Segmentation Using the Segment Anything Model
por: Deng, Zhongchen, et al.
Publicado: (2024)

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)

SAM 3: Segment Anything with Concepts
por: Carion, Nicolas, et al.
Publicado: (2025)

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)

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)

ShapeFormer: Shape Prior Visible-to-Amodal Transformer-based Amodal Instance Segmentation
por: Tran, Minh, et al.
Publicado: (2024)

MoBind: Motion Binding for Fine-Grained IMU-Video Pose Alignment
por: Nguyen, Duc Duy, et al.
Publicado: (2026)

SAM Audio: Segment Anything in Audio
por: Shi, Bowen, et al.
Publicado: (2025)

WSI-SAM: Multi-resolution Segment Anything Model (SAM) for histopathology whole-slide images
por: Liu, Hong, et al.
Publicado: (2024)

Boosting Few-Shot Semantic Segmentation Via Segment Anything Model
por: Feng, Chen-Bin, et al.
Publicado: (2024)

X-SAM: From Segment Anything to Any Segmentation
por: Wang, Hao, et al.
Publicado: (2025)

PosSAM: Panoptic Open-vocabulary Segment Anything
por: VS, Vibashan, et al.
Publicado: (2024)

TS-SAM: Fine-Tuning Segment-Anything Model for Downstream Tasks
por: Yu, Yang, et al.
Publicado: (2024)

PolSAM: Polarimetric Scattering Mechanism Informed Segment Anything Model
por: Wang, Yuqing, et al.
Publicado: (2024)

UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model
por: Kaiser, Timo, et al.
Publicado: (2025)

UV-SAM: Adapting Segment Anything Model for Urban Village Identification
por: Zhang, Xin, et al.
Publicado: (2024)

SAM3-UNet: Simplified Adaptation of Segment Anything Model 3
por: Xiong, Xinyu, et al.
Publicado: (2025)