Copertina

Rethinking Vision Transformer Depth via Structural Reparameterization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhou, Chengwei, Chaudhary, Vipin, Datta, Gourav
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Toward Guarantees for Clinical Reasoning in Vision Language Models via Formal Verification
di: Singh, Vikash, et al.
Pubblicazione: (2026)

LE-NeuS: Latency-Efficient Neuro-Symbolic Video Understanding via Adaptive Temporal Verification
di: Liang, Shawn, et al.
Pubblicazione: (2026)

LRD-Net: A Lightweight Real-Centered Detection Network for Cross-Domain Face Forgery Detection
di: Zhang, Xuecen, et al.
Pubblicazione: (2026)

FaceLiVT: Face Recognition using Linear Vision Transformer with Structural Reparameterization For Mobile Device
di: Setyawan, Novendra, et al.
Pubblicazione: (2025)

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers
di: Xu, Xuwei, et al.
Pubblicazione: (2025)

Energy-Efficient & Real-Time Computer Vision with Intelligent Skipping via Reconfigurable CMOS Image Sensors
di: Kaiser, Md Abdullah-Al, et al.
Pubblicazione: (2024)

Interpretable Vision Transformers in Monocular Depth Estimation via SVDA
di: Arampatzakis, Vasileios, et al.
Pubblicazione: (2026)

Fast-COS: A Fast One-Stage Object Detector Based on Reparameterized Attention Vision Transformer for Autonomous Driving
di: Setyawan, Novendra, et al.
Pubblicazione: (2025)

RepControlNet: ControlNet Reparameterization
di: Deng, Zhaoli, et al.
Pubblicazione: (2024)

VAT: Vision Action Transformer by Unlocking Full Representation of ViT
di: Li, Wenhao, et al.
Pubblicazione: (2025)

Improved Implicit Neural Representation with Fourier Reparameterized Training
di: Shi, Kexuan, et al.
Pubblicazione: (2024)

Visual Concept Networks: A Graph-Based Approach to Detecting Anomalous Data in Deep Neural Networks
di: Ganguly, Debargha, et al.
Pubblicazione: (2024)

FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers
di: Su, Haisheng, et al.
Pubblicazione: (2025)

RepSFNet : A Single Fusion Network with Structural Reparameterization for Crowd Counting
di: Achmadiah, Mas Nurul, et al.
Pubblicazione: (2026)

Differentiable Rendering with Reparameterized Volume Sampling
di: Morozov, Nikita, et al.
Pubblicazione: (2023)

Two-Stage Vision Transformer for Image Restoration: Colorization Pretraining + Residual Upsampling
di: Chaudhary, Aditya, et al.
Pubblicazione: (2025)

Dynamic Mode Decomposition along Depth in Vision Transformers
di: Aswani, Nishant Suresh, et al.
Pubblicazione: (2026)

RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization
di: Zhao, Mingshu, et al.
Pubblicazione: (2024)

Rethinking Overlooked Aspects in Vision-Language Models
di: Liu, Yuan, et al.
Pubblicazione: (2024)

Detecting Lip-Syncing Deepfakes: Vision Temporal Transformer for Analyzing Mouth Inconsistencies
di: Datta, Soumyya Kanti, et al.
Pubblicazione: (2025)

VPNeXt -- Rethinking Dense Decoding for Plain Vision Transformer
di: Tang, Xikai, et al.
Pubblicazione: (2025)

Boosting Neural Video Representation via Online Structural Reparameterization
di: Li, Ziyi, et al.
Pubblicazione: (2025)

DRNet: All-in-One Image Restoration via Prior-Guided Dynamic Reparameterization
di: Li, Ao, et al.
Pubblicazione: (2026)

NEBULA: Do We Evaluate Vision-Language-Action Agents Correctly?
di: Peng, Jierui, et al.
Pubblicazione: (2025)

Neural BRDF Importance Sampling by Reparameterization
di: Wu, Liwen, et al.
Pubblicazione: (2025)

Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small Datasets
di: Zhang, Tianxiao, et al.
Pubblicazione: (2024)

Structured Initialization for Vision Transformers
di: Zheng, Jianqiao, et al.
Pubblicazione: (2025)

Structural Attention: Rethinking Transformer for Unpaired Medical Image Synthesis
di: Phan, Vu Minh Hieu, et al.
Pubblicazione: (2024)

Sign-In to the Lottery: Reparameterizing Sparse Training From Scratch
di: Gadhikar, Advait, et al.
Pubblicazione: (2025)

Dynamic Granularity Matters: Rethinking Vision Transformers Beyond Fixed Patch Splitting
di: Yu, Qiyang, et al.
Pubblicazione: (2025)

RD-ViT: Recurrent-Depth Vision Transformer for Semantic Segmentation with Reduced Data Dependence Extending the Recurrent-Depth Transformer Architecture to Dense Prediction
di: He, Renjie
Pubblicazione: (2026)

SepRep-Net: Multi-source Free Domain Adaptation via Model Separation And Reparameterization
di: Jin, Ying, et al.
Pubblicazione: (2024)

LABELING COPILOT: A Deep Research Agent for Automated Data Curation in Computer Vision
di: Ganguly, Debargha, et al.
Pubblicazione: (2025)

Rethinking Transparent Object Grasping: Depth Completion with Monocular Depth Estimation and Instance Mask
di: Cheng, Yaofeng, et al.
Pubblicazione: (2025)

Enhancing Implicit Neural Representations via Symmetric Power Transformation
di: Zhang, Weixiang, et al.
Pubblicazione: (2024)

Height-Guided Projection Reparameterization for Camera-LiDAR Occupancy
di: Wu, Yuan, et al.
Pubblicazione: (2026)

Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation
di: Xu, Zhen, et al.
Pubblicazione: (2025)

Towards Accurate Post-training Quantization for Reparameterized Models
di: Zhang, Luoming, et al.
Pubblicazione: (2024)

Structured Initialization for Attention in Vision Transformers
di: Zheng, Jianqiao, et al.
Pubblicazione: (2024)

Learning Correlation Structures for Vision Transformers
di: Kim, Manjin, et al.
Pubblicazione: (2024)