Copertina

TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ding, Zhaoyuan, Yang, Yijing, Shu, Han, Chen, Xinghao
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

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

Tracking and Segmenting Anything in Any Modality
di: Zhang, Tianlu, et al.
Pubblicazione: (2025)

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

RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation
di: Li, Yonglin, et al.
Pubblicazione: (2023)

SAM-Sode: Towards Faithful Explanations for Tiny Bacteria Detection
di: Tan, Wanying, et al.
Pubblicazione: (2026)

SparseSAM: Structured Sparsification of Activations in Segment Anything Models
di: Tran, Hoai-Chau, et al.
Pubblicazione: (2026)

SAM 3D: 3Dfy Anything in Images
di: SAM 3D Team, et al.
Pubblicazione: (2025)

CamSAM2: Segment Anything Accurately in Camouflaged Videos
di: Zhou, Yuli, et al.
Pubblicazione: (2025)

MedSAM3: Delving into Segment Anything with Medical Concepts
di: Liu, Anglin, et al.
Pubblicazione: (2025)

Annolid: Annotate, Segment, and Track Anything You Need
di: Yang, Chen, et al.
Pubblicazione: (2024)

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

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

The SAM2-to-SAM3 Gap in the Segment Anything Model Family: Why Prompt-Based Expertise Fails in Concept-Driven Image Segmentation
di: Sapkota, Ranjan, et al.
Pubblicazione: (2025)

Region-Guided Attack on the Segment Anything Model (SAM)
di: Liu, Xiaoliang, et al.
Pubblicazione: (2024)

Med-PerSAM: One-Shot Visual Prompt Tuning for Personalized Segment Anything Model in Medical Domain
di: Yoon, Hangyul, et al.
Pubblicazione: (2024)

Context-Aware Weakly Supervised Image Manipulation Localization with SAM Refinement
di: Wang, Xinghao, et al.
Pubblicazione: (2025)

WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition
di: Zhu, Lianghui, et al.
Pubblicazione: (2024)

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

SGP-SAM: Self-Gated Prompting for Transferring 3D Segment Anything Models to Lesion Segmentation
di: Tang, Zixuan, et al.
Pubblicazione: (2026)

Eye image segmentation using visual and concept prompts with Segment Anything Model 3 (SAM3)
di: Niehorster, Diederick C., et al.
Pubblicazione: (2026)

GeoSAM2: Unleashing the Power of SAM2 for 3D Part Segmentation
di: Deng, Ken, et al.
Pubblicazione: (2025)

MGD-SAM2: Multi-view Guided Detail-enhanced Segment Anything Model 2 for High-Resolution Class-agnostic Segmentation
di: Shen, Haoran, et al.
Pubblicazione: (2025)

Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
di: Chen, Junyu, et al.
Pubblicazione: (2024)

Track Anything Rapter(TAR)
di: Puthanveettil, Tharun V., et al.
Pubblicazione: (2024)

AMA-SAM: Adversarial Multi-Domain Alignment of Segment Anything Model for High-Fidelity Histology Nuclei Segmentation
di: Qian, Jiahe, et al.
Pubblicazione: (2025)

MedSAM2: Segment Anything in 3D Medical Images and Videos
di: Ma, Jun, et al.
Pubblicazione: (2025)

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers
di: Wang, Guoxin, et al.
Pubblicazione: (2025)

Towards Lossless Ultimate Vision Token Compression for VLMs
di: Zheng, Dehua, et al.
Pubblicazione: (2025)

RobustSAM: Segment Anything Robustly on Degraded Images
di: Chen, Wei-Ting, et al.
Pubblicazione: (2024)

Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting
di: Zou, Shu, et al.
Pubblicazione: (2025)

Zero-Shot Segmentation of Eye Features Using the Segment Anything Model (SAM)
di: Maquiling, Virmarie, et al.
Pubblicazione: (2023)

ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation
di: Li, Shengze, et al.
Pubblicazione: (2024)

Underwater Camouflaged Object Tracking Meets Vision-Language SAM2
di: Zhang, Chunhui, et al.
Pubblicazione: (2024)

When Tracking Fails: Analyzing Failure Modes of SAM2 for Point-Based Tracking in Surgical Videos
di: Jang, Woowon, et al.
Pubblicazione: (2025)

SAM 2++: Tracking Anything at Any Granularity
di: Zhang, Jiaming, et al.
Pubblicazione: (2025)

Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T Videos
di: Xu, Qingyu, et al.
Pubblicazione: (2024)

BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments
di: Wang, Xinghao, et al.
Pubblicazione: (2024)