# Flattened Convolutional Neural Networks for Feedforward Acceleration

arXiv: https://arxiv.org/abs/1412.5474 · HTML: https://mlsanity.com/paper/1412.5474/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2014.

## Built on by (most cited first, 20 of 20)

- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [A Survey on Green Deep Learning](https://mlsanity.com/paper/2111.05193/) (2021)
- [Hybrid Pixel-Unshuffled Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2203.08921/) (2022)
- [Asymmetric CNN for image super-resolution](https://mlsanity.com/paper/2103.13634/) (2021)
- [Towards energy-efficient Deep Learning: An overview of energy-efficient approaches along the Deep Learning Lifecycle](https://mlsanity.com/paper/2303.01980/) (2023)
- [On the Opportunities of Green Computing: A Survey](https://mlsanity.com/paper/2311.00447/) (2023)
- [Improving thermal state preparation of Sachdev-Ye-Kitaev model with reinforcement learning on quantum hardware](https://mlsanity.com/paper/2501.11454/) (2025)
- [Salient Skin Lesion Segmentation via Dilated Scale-Wise Feature Fusion Network](https://mlsanity.com/paper/2205.10272/) (2022)
- [EqDeepRx: Learning a Scalable and Interference Mitigating MIMO Receiver](https://mlsanity.com/paper/2602.11834/) (2026)
- [Faster Convolution Inference Through Using Pre-Calculated Lookup Tables](https://mlsanity.com/paper/2104.01681/) (2021)
- [Multi-objective Evolutionary Approach for Efficient Kernel Size and Shape for CNN](https://mlsanity.com/paper/2106.14776/) (2021)
- [Top-Tuning: a study on transfer learning for an efficient alternative to fine tuning for image classification with fast kernel methods](https://mlsanity.com/paper/2209.07932/) (2022)
- [Atrous Space Bender U-Net (ASBU-Net/LogiNet)](https://mlsanity.com/paper/2212.08613/) (2022)
- [Time Series Forecasting via Semi-Asymmetric Convolutional Architecture with Global Atrous Sliding Window](https://mlsanity.com/paper/2301.13691/) (2023)
- [Evolution under Length Constraints for CNN Architecture design](https://mlsanity.com/paper/2305.03416/) (2023)
- [Faster Projected GAN: Towards Faster Few-Shot Image Generation](https://mlsanity.com/paper/2403.08778/) (2024)
- [Gamified AI Approch for Early Detection of Dementia](https://mlsanity.com/paper/2405.16538/) (2024)
- [Is 3D Convolution with 5D Tensors Really Necessary for Video Analysis?](https://mlsanity.com/paper/2407.16514/) (2024)
- [Pluggable Style Representation Learning for Multi-Style Transfer](https://mlsanity.com/paper/2503.20368/) (2025)
- [Efficient Human-Contact Representation for Human-Scene Interaction](https://mlsanity.com/paper/2608.09388/) (2026)

## Abstract (arXiv)

We present flattened convolutional neural networks that are designed for fast feedforward execution. The redundancy of the parameters, especially weights of the convolutional filters in convolutional neural networks has been extensively studied and different heuristics have been proposed to construct a low rank basis of the filters after training. In this work, we train flattened networks that consist of consecutive sequence of one-dimensional filters across all directions in 3D space to obtain comparable performance as conventional convolutional networks. We tested flattened model on different datasets and found that the flattened layer can effectively substitute for the 3D filters without loss of accuracy. The flattened convolution pipelines provide around two times speed-up during feedforward pass compared to the baseline model due to the significant reduction of learning parameters. Furthermore, the proposed method does not require efforts in manual tuning or post processing once the model is trained.