Imagen de Portada

Efficient Test-time Adaptive Object Detection via Sensitivity-Guided Pruning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Kunyu, Fu, Xueyang, Lu, Xin, Ge, Chengjie, Cao, Chengzhi, Zhai, Wei, Zha, Zheng-Jun
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Towards Better De-raining Generalization via Rainy Characteristics Memorization and Replay
por: Wang, Kunyu, et al.
Publicado: (2025)

PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation
por: Wang, Kunyu, et al.
Publicado: (2025)

EventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction
por: Ge, Chengjie, et al.
Publicado: (2025)

Leverage Task Context for Object Affordance Ranking
por: Huang, Haojie, et al.
Publicado: (2024)

Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolution
por: Peng, Long, et al.
Publicado: (2024)

TOUCH: Text-guided Controllable Generation of Free-Form Hand-Object Interactions
por: Han, Guangyi, et al.
Publicado: (2025)

LEMON: Learning 3D Human-Object Interaction Relation from 2D Images
por: Yang, Yuhang, et al.
Publicado: (2023)

VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs
por: Zhu, Jiaying, et al.
Publicado: (2025)

Elucidating and Endowing the Diffusion Training Paradigm for General Image Restoration
por: Lu, Xin, et al.
Publicado: (2025)

Iterative Inference-time Scaling with Adaptive Frequency Steering for Image Super-Resolution
por: Zhang, Hexin, et al.
Publicado: (2025)

Reward-Guided Semantic Evolution for Test-time Adaptive Object Detection
por: Zhou, Lihua, et al.
Publicado: (2026)

Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image Restoration
por: Peng, Long, et al.
Publicado: (2025)

End-to-End Spatial-Temporal Transformer for Real-time 4D HOI Reconstruction
por: Zhang, Haoyu, et al.
Publicado: (2026)

Event Stream Filtering via Probability Flux Estimation
por: Chen, Jinze, et al.
Publicado: (2025)

EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views
por: Yang, Yuhang, et al.
Publicado: (2024)

GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding
por: Shao, Yawen, et al.
Publicado: (2024)

FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining
por: Li, Dong, et al.
Publicado: (2024)

Event-Illumination Collaborative Low-light Image Enhancement with a High-resolution Real-world Dataset
por: Xu, Senyan, et al.
Publicado: (2026)

GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting
por: Shi, Mingyu, et al.
Publicado: (2026)

DemosaicFormer: Coarse-to-Fine Demosaicing Network for HybridEVS Camera
por: Xu, Senyan, et al.
Publicado: (2024)

RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions
por: Wu, Anran, et al.
Publicado: (2025)

Visual-Geometric Collaborative Guidance for Affordance Learning
por: Luo, Hongchen, et al.
Publicado: (2024)

HERO: Human Reaction Generation from Videos
por: Yu, Chengjun, et al.
Publicado: (2025)

Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement
por: Liu, Yidi, et al.
Publicado: (2025)

Unbiased Gradient Estimation for Event Binning via Functional Backpropagation
por: Chen, Jinze, et al.
Publicado: (2026)

EventGait: Towards Robust Gait Recognition with Event Streams
por: Xu, Senyan, et al.
Publicado: (2026)

Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning
por: Lu, Fan, et al.
Publicado: (2024)

Decouple to Reconstruct: High Quality UHD Restoration via Active Feature Disentanglement and Reversible Fusion
por: Liu, Yidi, et al.
Publicado: (2025)

Tracking by Detection and Query: An Efficient End-to-End Framework for Multi-Object Tracking
por: Jia, Shukun, et al.
Publicado: (2024)

AdaDeDup: Adaptive Hybrid Data Pruning for Efficient Large-Scale Object Detection Training
por: Kang, Feiyang, et al.
Publicado: (2025)

RAIN: Real-time Animation of Infinite Video Stream
por: Shu, Zhilei, et al.
Publicado: (2024)

Event-based Visual Deformation Measurement
por: Wu, Yuliang, et al.
Publicado: (2026)

Learning Multi-view Anomaly Detection with Efficient Adaptive Selection
por: He, Haoyang, et al.
Publicado: (2024)

Exploring Test-Time Adaptation for Object Detection in Continually Changing Environments
por: Cao, Shilei, et al.
Publicado: (2024)

Gloria: Consistent Character Video Generation via Content Anchors
por: Yang, Yuhang, et al.
Publicado: (2026)

CATP: Confidence-Aware Token Pruning for Camouflaged Object Detection
por: Gao, Yuhan, et al.
Publicado: (2026)

EMoTive: Event-guided Trajectory Modeling for 3D Motion Estimation
por: Wan, Zengyu, et al.
Publicado: (2025)

3D Small Object Detection with Dynamic Spatial Pruning
por: Xu, Xiuwei, et al.
Publicado: (2023)

MATE: Motion-Augmented Temporal Consistency for Event-based Point Tracking
por: Han, Han, et al.
Publicado: (2024)

Chasing Day and Night: Towards Robust and Efficient All-Day Object Detection Guided by an Event Camera
por: Cao, Jiahang, et al.
Publicado: (2023)