Patch Rebirth: Fast and Transferable Model Inversion of Vision Transformers

arXiv:2509.23235 · cs.CV, cs.AI · Submitted 2025-09-27 · Read on arXiv

cs.CV, cs.AI

Submitted: 2025-09-27

Updated: 2026-09-30

Code: https://github.com/rwightman/pytorch-image-models

Terminology

• Sparsity — 55× in this paper · explained in 4 episodes
• Quantization — 37× in this paper · explained in 12 episodes
• Distillation — 30× in this paper · explained in 2 episodes
• Accuracy — 25× in this paper · explained in 1 episode
• Transformer — 20× in this paper · explained in 2 episodes
• Knowledge Distillation — 16× in this paper · explained in 11 episodes
• Pruning — 15× in this paper · explained in 4 episodes
• Patch Rebirth Inversion — 11× in this paper
• Sparse Model Inversion — 8× in this paper
• Regularization — 7× in this paper · explained in 3 episodes
• Embeddings — 6× in this paper · explained in 2 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Generalization — 5× in this paper · explained in 13 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Attention Mechanism — 4× in this paper · explained in 3 episodes
• Core — 4× in this paper · explained in 2 episodes
• Computational overhead — 3× in this paper · explained in 2 episodes
• Dense Model Inversion — 3× in this paper
• Downstream Tasks — 3× in this paper · explained in 2 episodes
• Transferability — 3× in this paper · explained in 4 episodes
• Convolutional Neural Networks (CNNs) — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Differential Privacy — 1× in this paper · explained in 4 episodes
• Objective Function — 1× in this paper · explained in 2 episodes
• Quantization-Aware Training — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes

Sources

• Data-Free Adversarial Distillation
• Contrastive Model Inversion for Data-Free Knowledge Distillation
• Class-Specific Attention (CSA) for Time-Series Classification
• Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations
• Data-Free Knowledge Distillation for Deep Neural Networks
• Learning Class Regularized Features for Action Recognition
• Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition
• Adversarial Neural Network Inversion via Auxiliary Knowledge Alignment
• CA2: Class-Agnostic Adaptive Feature Adaptation for One-class Classification

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