Cover Image

Pruning by Block Benefit: Exploring the Properties of Vision Transformer Blocks during Domain Adaptation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Glandorf, Patrick, Rosenhahn, Bodo
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Video Patch Pruning: Efficient Video Instance Segmentation via Early Token Reduction
by: Glandorf, Patrick, et al.
Published: (2026)

Block-based Symmetric Pruning and Fusion for Efficient Vision Transformers
by: Hsieh, Yi-Kuan, et al.
Published: (2025)

Improving 3D Foot Motion Reconstruction in Markerless Monocular Human Motion Capture
by: Wehrbein, Tom, et al.
Published: (2026)

PARSAC: Accelerating Robust Multi-Model Fitting with Parallel Sample Consensus
by: Kluger, Florian, et al.
Published: (2024)

Exploring the Benefits of Vision Foundation Models for Unsupervised Domain Adaptation
by: Englert, Brunó B., et al.
Published: (2024)

Multi-Flow: Multi-View-Enriched Normalizing Flows for Industrial Anomaly Detection
by: Kruse, Mathis, et al.
Published: (2025)

SPAN: Learning Similarity between Scene Graphs and Images with Transformers
by: Cong, Yuren, et al.
Published: (2023)

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

HydraMix: Multi-Image Feature Mixing for Small Data Image Classification
by: Reinders, Christoph, et al.
Published: (2025)

BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detection
by: Schween, Melissa, et al.
Published: (2026)

Cell Tracking according to Biological Needs -- Strong Mitosis-aware Multi-Hypothesis Tracker with Aleatoric Uncertainty
by: Kaiser, Timo, et al.
Published: (2024)

CHOTA: A Higher Order Accuracy Metric for Cell Tracking
by: Kaiser, Timo, et al.
Published: (2024)

Block Pruning for Enhanced Efficiency in Convolutional Neural Networks
by: Wu, Cheng-En, et al.
Published: (2023)

Interpretable Decision-Making for End-to-End Autonomous Driving
by: Mirzaie, Mona, et al.
Published: (2025)

Adaptively Bypassing Vision Transformer Blocks for Efficient Visual Tracking
by: Yang, Xiangyang, et al.
Published: (2024)

Q-SENN: Quantized Self-Explaining Neural Networks
by: Norrenbrock, Thomas, et al.
Published: (2023)

Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery
by: Wehrbein, Tom, et al.
Published: (2024)

Personalized 3D Human Pose and Shape Refinement
by: Wehrbein, Tom, et al.
Published: (2024)

When Does Pruning Benefit Vision Representations?
by: Cassano, Enrico, et al.
Published: (2025)

Entropy Reveals Block Importance in Masked Self-Supervised Vision Transformers
by: Xiang, Peihao, et al.
Published: (2026)

Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptation
by: Yu, Yeonguk, et al.
Published: (2024)

Block-Recurrent Dynamics in Vision Transformers
by: Jacobs, Mozes, et al.
Published: (2025)

Block Selective Reprogramming for On-device Training of Vision Transformers
by: Sarkar, Sreetama, et al.
Published: (2024)

MABViT -- Modified Attention Block Enhances Vision Transformers
by: Ramesh, Mahesh, et al.
Published: (2023)

Robust Shape Fitting for 3D Scene Abstraction
by: Kluger, Florian, et al.
Published: (2024)

DINO-QPM: Adapting Visual Foundation Models for Globally Interpretable Image Classification
by: Zimmermann, Robert, et al.
Published: (2026)

From Gameplay Traces to Game Mechanics: Causal Induction with Large Language Models
by: Jiwatode, Mohit, et al.
Published: (2026)

Separate, Dynamic and Differentiable (SMART) Pruner for Block/Output Channel Pruning on Computer Vision Tasks
by: Ding, Guanhua, et al.
Published: (2024)

GM-Skip: Metric-Guided Transformer Block Skipping for Efficient Vision-Language Models
by: Huang, Lianming, et al.
Published: (2025)

SplatPose & Detect: Pose-Agnostic 3D Anomaly Detection
by: Kruse, Mathis, et al.
Published: (2024)

Partial Forward Blocking: A Novel Data Pruning Paradigm for Lossless Training Acceleration
by: Wu, Dongyue, et al.
Published: (2025)

FDSG: Forecasting Dynamic Scene Graphs
by: Yang, Yi, et al.
Published: (2025)

Dynamic Relation Transformer for Contextual Text Block Detection
by: Wang, Jiawei, et al.
Published: (2024)

Vision Transformer-based Adversarial Domain Adaptation
by: Li, Yahan, et al.
Published: (2024)

TransAdapter: Vision Transformer for Feature-Centric Unsupervised Domain Adaptation
by: Doruk, A. Enes, et al.
Published: (2024)

bViT: Investigating Single-Block Recurrence in Vision Transformers for Image Recognition
by: Byra, Michal, et al.
Published: (2026)

The Effects of Grouped Structural Global Pruning of Vision Transformers on Domain Generalisation
by: Riaz, Hamza, et al.
Published: (2025)

Improved Convex Decomposition with Ensembling and Negative Primitives
by: Vavilala, Vaibhav, et al.
Published: (2024)

Multi-Dimensional Pruning: Joint Channel, Layer and Block Pruning with Latency Constraint
by: Sun, Xinglong, et al.
Published: (2024)

Adaptive MLP Pruning for Large Vision Transformers
by: Shen, Chengchao
Published: (2026)