# Convolutional Neural Networks at Constrained Time Cost

arXiv: https://arxiv.org/abs/1412.1710 · HTML: https://mlsanity.com/paper/1412.1710/

## Key facts

- Cited by 81 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2014.

## Built on by (most cited first, 30 of 81)

- [DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging](https://mlsanity.com/paper/2402.02622/) (2024)
- [A Voxel Graph CNN for Object Classification with Event Cameras](https://mlsanity.com/paper/2106.00216/) (2021)
- [A Law of Data Separation in Deep Learning](https://mlsanity.com/paper/2210.17020/) (2022)
- [Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances](https://mlsanity.com/paper/2209.13131/) (2022)
- [Augmenting Deep Classifiers with Polynomial Neural Networks](https://mlsanity.com/paper/2104.07916/) (2021)
- [A Systematic Survey of Deep Learning-based Single-Image Super-Resolution](https://mlsanity.com/paper/2109.14335/) (2021)
- [Learning Optimal Multimodal Information Bottleneck Representations](https://mlsanity.com/paper/2505.19996/) (2025)
- [Automatic Change-Point Detection in Time Series via Deep Learning](https://mlsanity.com/paper/2211.03860/) (2022)
- [Design Smells in Deep Learning Programs: An Empirical Study](https://mlsanity.com/paper/2107.02279/) (2021)
- [ZippyPoint: Fast Interest Point Detection, Description, and Matching through Mixed Precision Discretization](https://mlsanity.com/paper/2203.03610/) (2022)
- [Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Survey](https://mlsanity.com/paper/2405.01725/) (2024)
- [Automatic Fault Detection for Deep Learning Programs Using Graph Transformations](https://mlsanity.com/paper/2105.08095/) (2021)
- [Resource Allocation of Federated Learning for the Metaverse with Mobile Augmented Reality](https://mlsanity.com/paper/2211.08705/) (2022)
- [Deep Learning Approximation of Diffeomorphisms via Linear-Control Systems](https://mlsanity.com/paper/2110.12393/) (2021)
- [Stride and Translation Invariance in CNNs](https://mlsanity.com/paper/2103.10097/) (2021)
- [Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning](https://mlsanity.com/paper/2105.05838/) (2021)
- [ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees](https://mlsanity.com/paper/2111.05496/) (2021)
- [Structure-Enhanced DRL for Optimal Transmission Scheduling](https://mlsanity.com/paper/2212.12704/) (2022)
- [BA^2M: A Batch Aware Attention Module for Image Classification](https://mlsanity.com/paper/2103.15099/) (2021)
- [Over-the-Air Design of GAN Training for mmWave MIMO Channel Estimation](https://mlsanity.com/paper/2205.12445/) (2022)
- [FreeGaze: Resource-efficient Gaze Estimation via Frequency Domain Contrastive Learning](https://mlsanity.com/paper/2209.06692/) (2022)
- [Transfer Learning-based State of Health Estimation for Lithium-ion Battery with Cycle Synchronization](https://mlsanity.com/paper/2208.11204/) (2022)
- [A Transferable Multi-stage Model with Cycling Discrepancy Learning for Lithium-ion Battery State of Health Estimation](https://mlsanity.com/paper/2209.00190/) (2022)
- [Distributed Reinforcement Learning for Flexible and Efficient UAV Swarm Control](https://mlsanity.com/paper/2103.04666/) (2021)
- [Bio-Inspired Representation Learning for Visual Attention Prediction](https://mlsanity.com/paper/2103.05310/) (2021)
- [Analytically Tractable Inference in Deep Neural Networks](https://mlsanity.com/paper/2103.05461/) (2021)
- [Transformed ROIs for Capturing Visual Transformations in Videos](https://mlsanity.com/paper/2106.03162/) (2021)
- [Recurrent Inference Machines as inverse problem solvers for MR relaxometry](https://mlsanity.com/paper/2106.07379/) (2021)
- [Unifying Nonlocal Blocks for Neural Networks](https://mlsanity.com/paper/2108.02451/) (2021)
- [Adapting to Dynamic LEO-B5G Systems: Meta-Critic Learning Based Efficient Resource Scheduling](https://mlsanity.com/paper/2110.06787/) (2021)

## Abstract (arXiv)

Though recent advanced convolutional neural networks (CNNs) have been improving the image recognition accuracy, the models are getting more complex and time-consuming. For real-world applications in industrial and commercial scenarios, engineers and developers are often faced with the requirement of constrained time budget. In this paper, we investigate the accuracy of CNNs under constrained time cost. Under this constraint, the designs of the network architectures should exhibit as trade-offs among the factors like depth, numbers of filters, filter sizes, etc. With a series of controlled comparisons, we progressively modify a baseline model while preserving its time complexity. This is also helpful for understanding the importance of the factors in network designs. We present an architecture that achieves very competitive accuracy in the ImageNet dataset (11.8% top-5 error, 10-view test), yet is 20% faster than "AlexNet" (16.0% top-5 error, 10-view test).