Decoder-Agnostic Token Merging for Vision Transformers: A Systematic Study of G2TM
cs.CV
Submitted: 2026-09-16
Updated: 2026-09-16
Terminology
Sources
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- DINOv2: Learning Robust Visual Features without Supervision
- Token Merging: Your ViT But Faster
- AiluRus: A Scalable ViT Framework for Dense Prediction
- Learned Thresholds Token Merging and Pruning for Vision Transformers
- DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
- Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers
- Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth
- Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice
- Vision Transformers Need Registers
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models