When frequency domain classification is superior to spatial
cs.CV, cs.CL
Submitted: 2026-10-15
Updated: 2026-10-15
Terminology
Sources
- DCT-CompCNN: A Novel Image Classification Network Using JPEG Compressed DCT Coefficients
- Learning in the Frequency Domain
- Global Filter Networks for Image Classification
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Attention Is All You Need
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Escaping the Big Data Paradigm with Compact Transformers
- ImageNet Large Scale Visual Recognition Challenge
- Recurrent neural networks that generalize from examples and optimize by dreaming
- The mechanism underlying successful deep learning
- Going Deeper with Convolutions
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- SGDR: Stochastic Gradient Descent with Warm Restarts
- Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates
- Cyclical Learning Rates for Training Neural Networks
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