Towards Democratising Low-Data Medical Image Classification: CPU-Trainable ZACH-ViT and Its Geometric Variants
cs.CV, cs.LG
Submitted: 2026-11-12
Updated: 2026-11-12
Code: https://github.com/Bluesman79/ZACH-ViT
Terminology
Sources
- hZACH-ViT: Curved Latent Geometry for Compact Vision Transformers in Low-Data Medical Imaging
- qZACH-ViT: Quantization-Aware Intrinsic Explanations with Recursive Attribution-Stabilized Optimization
- ZACH-ViT: Regime-Dependent Inductive Bias in Compact Vision Transformers for Medical Imaging
- From ECG Signals to Representative-Morphology Heatmaps for Biometric Recognition
- Curvature Under Attack in hZACH-ViT: Gauge Symmetry, Boundary Saturation, and Adversarial Failure
- Extending ZACH-ViT to Robust Medical Imaging: Corruption and Adversarial Stress Testing in Low-Data Regimes
- A Closer Look at Few-shot Classification
- Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Escaping the Big Data Paradigm with Compact Transformers
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs