Image de couverture de livre

Segment-Anything Models Achieve Zero-shot Robustness in Autonomous Driving

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yan, Jun, Wang, Pengyu, Wang, Danni, Huang, Weiquan, Watzenig, Daniel, Yin, Huilin
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MAP: End-to-End Autonomous Driving with Map-Assisted Planning
par: Yin, Huilin, et autres
Publié: (2025)

WS-DETR: Robust Water Surface Object Detection through Vision-Radar Fusion with Detection Transformer
par: Yin, Huilin, et autres
Publié: (2025)

On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving
par: Rossolini, Giulio, et autres
Publié: (2022)

X-SAM: From Segment Anything to Any Segmentation
par: Wang, Hao, et autres
Publié: (2025)

Segment Anything for Videos: A Systematic Survey
par: Zhang, Chunhui, et autres
Publié: (2024)

Semantic Localization Guiding Segment Anything Model For Reference Remote Sensing Image Segmentation
par: Li, Shuyang, et autres
Publié: (2025)

RobustSAM: Segment Anything Robustly on Degraded Images
par: Chen, Wei-Ting, et autres
Publié: (2024)

Learning Segmented 3D Gaussians via Efficient Feature Unprojection for Zero-shot Neural Scene Segmentation
par: Dou, Bin, et autres
Publié: (2024)

ALPS: An Auto-Labeling and Pre-training Scheme for Remote Sensing Segmentation With Segment Anything Model
par: Zhang, Song, et autres
Publié: (2024)

Segment Anything in Pathology Images with Natural Language
par: Chen, Zhixuan, et autres
Publié: (2025)

SAMAug: Point Prompt Augmentation for Segment Anything Model
par: Dai, Haixing, et autres
Publié: (2023)

Compress Any Segment Anything Model (SAM)
par: Fan, Juntong, et autres
Publié: (2025)

Segment and Matte Anything in a Unified Model
par: Fan, Zezhong, et autres
Publié: (2026)

Zero-Shot Segmentation of Eye Features Using the Segment Anything Model (SAM)
par: Maquiling, Virmarie, et autres
Publié: (2023)

WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition
par: Zhu, Lianghui, et autres
Publié: (2024)

SAM 3: Segment Anything with Concepts
par: Carion, Nicolas, et autres
Publié: (2025)

Hierarchically Robust Zero-shot Vision-language Models
par: Dong, Junhao, et autres
Publié: (2026)

StarFT: Robust Fine-tuning of Zero-shot Models via Spuriosity Alignment
par: Kim, Younghyun, et autres
Publié: (2025)

TopoStreamer: Temporal Lane Segment Topology Reasoning in Autonomous Driving
par: Yang, Yiming, et autres
Publié: (2025)

Transient Fault Tolerant Semantic Segmentation for Autonomous Driving
par: Iurada, Leonardo, et autres
Publié: (2024)

Zero-shot World Models Are Developmentally Efficient Learners
par: Aw, Khai Loong, et autres
Publié: (2026)

Promoting Segment Anything Model towards Highly Accurate Dichotomous Image Segmentation
par: Liu, Xianjie, et autres
Publié: (2023)

Cross-Model Transferability of Adversarial Patches in Real-time Segmentation for Autonomous Driving
par: Shekhar, Prashant, et autres
Publié: (2025)

Uncertainty-Encoded Multi-Modal Fusion for Robust Object Detection in Autonomous Driving
par: Lou, Yang, et autres
Publié: (2023)

LENS: Learning to Segment Anything with Unified Reinforced Reasoning
par: Zhu, Lianghui, et autres
Publié: (2025)

Zeus: Zero-shot LLM Instruction for Union Segmentation in Multimodal Medical Imaging
par: Dai, Siyuan, et autres
Publié: (2025)

DFVEdit: Conditional Delta Flow Vector for Zero-shot Video Editing
par: Cai, Lingling, et autres
Publié: (2025)

SparseSAM: Structured Sparsification of Activations in Segment Anything Models
par: Tran, Hoai-Chau, et autres
Publié: (2026)

Visual Space Optimization for Zero-shot Learning
par: Wang, Xinsheng, et autres
Publié: (2019)

MoECLIP: Patch-Specialized Experts for Zero-shot Anomaly Detection
par: Park, Jun Yeong, et autres
Publié: (2026)

RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation
par: Li, Yonglin, et autres
Publié: (2023)

Zero-shot High-fidelity and Pose-controllable Character Animation
par: Zhu, Bingwen, et autres
Publié: (2024)

Towards Robust Unsupervised Attention Prediction in Autonomous Driving
par: Qi, Mengshi, et autres
Publié: (2025)

DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving
par: Li, Yingyan, et autres
Publié: (2025)

Red-Teaming Segment Anything Model
par: Jankowski, Krzysztof, et autres
Publié: (2024)

Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation
par: Aleem, Sidra, et autres
Publié: (2024)

Q-SAM2: Accurate Quantization for Segment Anything Model 2
par: Farronato, Nicola, et autres
Publié: (2025)

Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges
par: Jiang, Yidong
Publié: (2025)

InstantID: Zero-shot Identity-Preserving Generation in Seconds
par: Wang, Qixun, et autres
Publié: (2024)

Customize Segment Anything Model for Multi-Modal Semantic Segmentation with Mixture of LoRA Experts
par: Zhu, Chenyang, et autres
Publié: (2024)