# Convolutional Neural Fabrics

arXiv: https://arxiv.org/abs/1606.02492 · HTML: https://mlsanity.com/paper/1606.02492/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2016.

## Built on by (most cited first, 30 of 32)

- [HRFormer: High-Resolution Transformer for Dense Prediction](https://mlsanity.com/paper/2110.09408/) (2021)
- [Neural Architecture Search: Insights from 1000 Papers](https://mlsanity.com/paper/2301.08727/) (2023)
- [BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search](https://mlsanity.com/paper/2103.12424/) (2021)
- [DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning](https://mlsanity.com/paper/2509.16105/) (2025)
- [HyperSegNAS: Bridging One-Shot Neural Architecture Search with 3D Medical Image Segmentation using HyperNet](https://mlsanity.com/paper/2112.10652/) (2021)
- [Local-to-Global Self-Attention in Vision Transformers](https://mlsanity.com/paper/2107.04735/) (2021)
- [Neural Architecture Search for Dense Prediction Tasks in Computer Vision](https://mlsanity.com/paper/2202.07242/) (2022)
- [A Survey on Computationally Efficient Neural Architecture Search](https://mlsanity.com/paper/2206.01520/) (2022)
- [Quantifying Task Priority for Multi-Task Optimization](https://mlsanity.com/paper/2406.02996/) (2024)
- [IRLAS: Inverse Reinforcement Learning for Architecture Search](https://mlsanity.com/paper/1812.05285/) (2018)
- [Topological Measurement of Deep Neural Networks Using Persistent Homology](https://mlsanity.com/paper/2106.03016/) (2021)
- [Whole Brain Segmentation with Full Volume Neural Network](https://mlsanity.com/paper/2110.15601/) (2021)
- [MixSearch: Searching for Domain Generalized Medical Image Segmentation Architectures](https://mlsanity.com/paper/2102.13280/) (2021)
- [Single Person Pose Estimation: A Survey](https://mlsanity.com/paper/2109.10056/) (2021)
- [Towards Less Constrained Macro-Neural Architecture Search](https://mlsanity.com/paper/2203.05508/) (2022)
- [Small but Mighty: Enhancing 3D Point Clouds Semantic Segmentation with U-Next Framework](https://mlsanity.com/paper/2304.00749/) (2023)
- [Towards Searching Efficient and Accurate Neural Network Architectures in Binary Classification Problems](https://mlsanity.com/paper/2101.06511/) (2021)
- [Towards a Robust Differentiable Architecture Search under Label Noise](https://mlsanity.com/paper/2110.12197/) (2021)
- [A Deep Learning Approach for the solution of Probability Density Evolution of Stochastic Systems](https://mlsanity.com/paper/2207.01907/) (2022)
- [Conceptual Expansion Neural Architecture Search (CENAS)](https://mlsanity.com/paper/2110.03144/) (2021)
- [DAS: Neural Architecture Search via Distinguishing Activation Score](https://mlsanity.com/paper/2212.12132/) (2022)
- [Multi-objective Differentiable Neural Architecture Search](https://mlsanity.com/paper/2402.18213/) (2024)
- [Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost](https://mlsanity.com/paper/2405.05695/) (2024)
- [Differentiable Prompt Learning for Vision Language Models](https://mlsanity.com/paper/2501.00457/) (2024)
- [GPNAS: A Neural Network Architecture Search Framework Based on Graphical Predictor](https://mlsanity.com/paper/2103.11820/) (2021)
- [BraidNet: procedural generation of neural networks for image classification problems using braid theory](https://mlsanity.com/paper/2104.10010/) (2021)
- [Balancing Accuracy and Latency in Multipath Neural Networks](https://mlsanity.com/paper/2104.12040/) (2021)
- [MS-DARTS: Mean-Shift Based Differentiable Architecture Search](https://mlsanity.com/paper/2108.09996/) (2021)
- [Convolutional Network Fabric Pruning With Label Noise](https://mlsanity.com/paper/2202.07268/) (2022)
- [Braid-based architecture search](https://mlsanity.com/paper/2207.04121/) (2022)

## Abstract (arXiv)

Despite the success of CNNs, selecting the optimal architecture for a given task remains an open problem. Instead of aiming to select a single optimal architecture, we propose a "fabric" that embeds an exponentially large number of architectures. The fabric consists of a 3D trellis that connects response maps at different layers, scales, and channels with a sparse homogeneous local connectivity pattern. The only hyper-parameters of a fabric are the number of channels and layers. While individual architectures can be recovered as paths, the fabric can in addition ensemble all embedded architectures together, sharing their weights where their paths overlap. Parameters can be learned using standard methods based on back-propagation, at a cost that scales linearly in the fabric size. We present benchmark results competitive with the state of the art for image classification on MNIST and CIFAR10, and for semantic segmentation on the Part Labels dataset.