# Exploring Image Representation with Decoupled Classical Visual Descriptors

arXiv: https://arxiv.org/abs/2510.14536 · HTML: https://mlsanity.com/paper/2510.14536/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction](https://mlsanity.com/paper/1611.09842/) (2016)
- [PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers](https://mlsanity.com/paper/2111.12710/) (2021)
- [ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback](https://mlsanity.com/paper/2404.07987/) (2024)
- [Improving Semantic Segmentation via Decoupled Body and Edge Supervision](https://mlsanity.com/paper/2007.10035/) (2020)
- [Image-to-image Translation via Hierarchical Style Disentanglement](https://mlsanity.com/paper/2103.01456/) (2021)
- [Semantics Disentangling for Text-to-Image Generation](https://mlsanity.com/paper/1904.01480/) (2019)
- [BayeSeg: Bayesian Modeling for Medical Image Segmentation with Interpretable Generalizability](https://mlsanity.com/paper/2303.01710/) (2023)
- [Domain-Size Pooling in Local Descriptors: DSP-SIFT](https://mlsanity.com/paper/1412.8556/) (2014)
- [Multi-view Self-supervised Disentanglement for General Image Denoising](https://mlsanity.com/paper/2309.05049/) (2023)
- [Domain Game: Disentangle Anatomical Feature for Single Domain Generalized Segmentation](https://mlsanity.com/paper/2406.02125/) (2024)

## Abstract (arXiv)

Exploring and understanding efficient image representations is a long-standing challenge in computer vision. While deep learning has achieved remarkable progress across image understanding tasks, its internal representations are often opaque, making it difficult to interpret how visual information is processed. In contrast, classical visual descriptors (e.g. edge, colour, and intensity distribution) have long been fundamental to image analysis and remain intuitively understandable to humans. Motivated by this gap, we ask a central question: Can modern learning benefit from these classical cues? In this paper, we answer it with VisualSplit, a framework that explicitly decomposes images into decoupled classical descriptors, treating each as an independent but complementary component of visual knowledge. Through a reconstruction-driven pre-training scheme, VisualSplit learns to capture the essence of each visual descriptor while preserving their interpretability. By explicitly decomposing visual attributes, our method inherently facilitates effective attribute control in various advanced visual tasks, including image generation and editing, extending beyond conventional classification and segmentation, suggesting the effectiveness of this new learning approach for visual understanding. Project page: https://chenyuanqu.com/VisualSplit/.