# Deep Roto-Translation Scattering for Object Classification

arXiv: https://arxiv.org/abs/1412.8659 · HTML: https://mlsanity.com/paper/1412.8659/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Dec 2014.

## Built on by (most cited first, 30 of 50)

- [Unlocking High-Accuracy Differentially Private Image Classification through Scale](https://mlsanity.com/paper/2204.13650/) (2022)
- [Wavelet-Packets for Deepfake Image Analysis and Detection](https://mlsanity.com/paper/2106.09369/) (2021)
- [Arbitrary Decisions are a Hidden Cost of Differentially Private Training](https://mlsanity.com/paper/2302.14517/) (2023)
- [Differentially Private Image Classification by Learning Priors from Random Processes](https://mlsanity.com/paper/2306.06076/) (2023)
- [A Rainbow in Deep Network Black Boxes](https://mlsanity.com/paper/2305.18512/) (2023)
- [Privacy-Aware Compression for Federated Data Analysis](https://mlsanity.com/paper/2203.08134/) (2022)
- [Leveraging Equivariant Features for Absolute Pose Regression](https://mlsanity.com/paper/2204.02163/) (2022)
- [Parametric Scattering Networks](https://mlsanity.com/paper/2107.09539/) (2021)
- [Unlocking Accuracy and Fairness in Differentially Private Image Classification](https://mlsanity.com/paper/2308.10888/) (2023)
- [DPMLBench: Holistic Evaluation of Differentially Private Machine Learning](https://mlsanity.com/paper/2305.05900/) (2023)
- [Conflicting Interactions Among Protection Mechanisms for Machine Learning Models](https://mlsanity.com/paper/2207.01991/) (2022)
- [Spectral Leakage and Rethinking the Kernel Size in CNNs](https://mlsanity.com/paper/2101.10143/) (2021)
- [The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methods](https://mlsanity.com/paper/2101.07528/) (2021)
- [Analysis of (sub-)Riemannian PDE-G-CNNs](https://mlsanity.com/paper/2210.00935/) (2022)
- [Attack-Aware Noise Calibration for Differential Privacy](https://mlsanity.com/paper/2407.02191/) (2024)
- [Deformation Robust Roto-Scale-Translation Equivariant CNNs](https://mlsanity.com/paper/2111.10978/) (2021)
- [Equivariant Wavelets: Fast Rotation and Translation Invariant Wavelet Scattering Transforms](https://mlsanity.com/paper/2104.11244/) (2021)
- [Towards Understanding Theoretical Advantages of Complex-Reaction Networks](https://mlsanity.com/paper/2108.06711/) (2021)
- [Minimalistic Unsupervised Learning with the Sparse Manifold Transform](https://mlsanity.com/paper/2209.15261/) (2022)
- [Spectral-DP: Differentially Private Deep Learning through Spectral Perturbation and Filtering](https://mlsanity.com/paper/2307.13231/) (2023)
- [Self-Supervised Pretraining for Differentially Private Learning](https://mlsanity.com/paper/2206.07125/) (2022)
- [Riesz feature representation: scale equivariant scattering network for classification tasks](https://mlsanity.com/paper/2307.08467/) (2023)
- [Adversarial Audio Synthesis with Complex-valued Polynomial Networks](https://mlsanity.com/paper/2206.06811/) (2022)
- [Convolutional Networks with Oriented 1D Kernels](https://mlsanity.com/paper/2309.15812/) (2023)
- [NeuroMixGDP: A Neural Collapse-Inspired Random Mixup for Private Data Release](https://mlsanity.com/paper/2202.06467/) (2022)
- [On the Shift Invariance of Max Pooling Feature Maps in Convolutional Neural Networks](https://mlsanity.com/paper/2209.11740/) (2022)
- [A Simple Strategy to Provable Invariance via Orbit Mapping](https://mlsanity.com/paper/2209.11916/) (2022)
- [Equivariant and Steerable Neural Networks: A review with special emphasis on the symmetric group](https://mlsanity.com/paper/2301.03019/) (2023)
- [Wavelets Beat Monkeys at Adversarial Robustness](https://mlsanity.com/paper/2304.09403/) (2023)
- [H-NeXt: The next step towards roto-translation invariant networks](https://mlsanity.com/paper/2311.01111/) (2023)

## Abstract (arXiv)

Dictionary learning algorithms or supervised deep convolution networks have considerably improved the efficiency of predefined feature representations such as SIFT. We introduce a deep scattering convolution network, with predefined wavelet filters over spatial and angular variables. This representation brings an important improvement to results previously obtained with predefined features over object image databases such as Caltech and CIFAR. The resulting accuracy is comparable to results obtained with unsupervised deep learning and dictionary based representations. This shows that refining image representations by using geometric priors is a promising direction to improve image classification and its understanding.