# RADAM: Texture Recognition through Randomized Aggregated Encoding of Deep Activation Maps

arXiv: https://arxiv.org/abs/2303.04554 · HTML: https://mlsanity.com/paper/2303.04554/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 54 references that are in the map.
- First posted on arXiv 8 Mar 2023.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Exact solutions to the nonlinear dynamics of learning in deep linear neural networks](https://mlsanity.com/paper/1312.6120/) (2013)
- [Bilinear CNNs for Fine-grained Visual Recognition](https://mlsanity.com/paper/1504.07889/) (2015)
- [Deep TEN: Texture Encoding Network](https://mlsanity.com/paper/1612.02844/) (2016)
- [From BoW to CNN: Two Decades of Texture Representation for Texture Classification](https://mlsanity.com/paper/1801.10324/) (2018)
- [Deep Texture Manifold for Ground Terrain Recognition](https://mlsanity.com/paper/1803.10896/) (2018)
- [Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy](https://mlsanity.com/paper/2203.07845/) (2022)
- [A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems](https://mlsanity.com/paper/2209.07326/) (2022)
- [Fusion of complex networks and randomized neural networks for texture analysis](https://mlsanity.com/paper/1806.09170/) (2018)
- [Differential Viewpoints for Ground Terrain Material Recognition](https://mlsanity.com/paper/2009.11072/) (2020)
- [Spatio-spectral networks for color-texture analysis](https://mlsanity.com/paper/1909.06446/) (2019)
- [Multilayer Complex Network Descriptors for Color-Texture Characterization](https://mlsanity.com/paper/1804.00501/) (2018)
- [Multilayer deep feature extraction for visual texture recognition](https://mlsanity.com/paper/2208.10044/) (2022)

## Built on by (most cited first, 12 of 12)

- [A Comparative Survey of Vision Transformers for Feature Extraction in Texture Analysis](https://mlsanity.com/paper/2406.06136/) (2024)
- [Hierarchical Material Recognition from Local Appearance](https://mlsanity.com/paper/2505.22911/) (2025)
- [Advanced wood species identification based on multiple anatomical sections and using deep feature transfer and fusion](https://mlsanity.com/paper/2404.08585/) (2024)
- [VORTEX: Challenging CNNs at Texture Recognition by using Vision Transformers with Orderless and Randomized Token Encodings](https://mlsanity.com/paper/2503.06368/) (2025)
- [Neighborhood Feature Pooling for Remote Sensing Image Classification](https://mlsanity.com/paper/2510.25077/) (2025)
- [MIXER: Mixed Hyperspherical Random Embedding Neural Network for Texture Recognition](https://mlsanity.com/paper/2510.03228/) (2025)
- [TwistNet-2D: Learning Second-Order Channel Interactions via Spiral Twisting for Texture Recognition](https://mlsanity.com/paper/2602.07262/) (2026)
- [Deep neural networks with Fisher vector encoding for medical image classification](https://mlsanity.com/paper/2605.01667/) (2026)
- [Chaotic Contrastive Learning for Robust Texture Classification](https://mlsanity.com/paper/2605.05012/) (2026)
- [A self-supervised learning approach to deep filter banks for texture recognition](https://mlsanity.com/paper/2605.27843/) (2026)
- [Leveraging Extragradient for Effective Sharpness-Aware Minimization in Deep Learning](https://mlsanity.com/paper/2607.06151/) (2026)
- [HiPerViT: A Hierarchical Perceiver-Vision Transformer Architecture for Multi-Scale Texture Recognition](https://mlsanity.com/paper/2609.10917/) (2026)

## Abstract (arXiv)

Texture analysis is a classical yet challenging task in computer vision for which deep neural networks are actively being applied. Most approaches are based on building feature aggregation modules around a pre-trained backbone and then fine-tuning the new architecture on specific texture recognition tasks. Here we propose a new method named Random encoding of Aggregated Deep Activation Maps (RADAM) which extracts rich texture representations without ever changing the backbone. The technique consists of encoding the output at different depths of a pre-trained deep convolutional network using a Randomized Autoencoder (RAE). The RAE is trained locally to each image using a closed-form solution, and its decoder weights are used to compose a 1-dimensional texture representation that is fed into a linear SVM. This means that no fine-tuning or backpropagation is needed. We explore RADAM on several texture benchmarks and achieve state-of-the-art results with different computational budgets. Our results suggest that pre-trained backbones may not require additional fine-tuning for texture recognition if their learned representations are better encoded.