# Data-Side Efficiencies for Lightweight Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2308.13057 · HTML: https://mlsanity.com/paper/2308.13057/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 48 references that are in the map.
- First posted on arXiv 24 Aug 2023.

## Builds on (most cited first, 25 of 25)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [A Survey of Model Compression and Acceleration for Deep Neural Networks](https://mlsanity.com/paper/1710.09282/) (2017)
- [Resolution Adaptive Networks for Efficient Inference](https://mlsanity.com/paper/2003.07326/) (2020)
- [End-to-end Learning of Action Detection from Frame Glimpses in Videos](https://mlsanity.com/paper/1511.06984/) (2015)
- [AR-Net: Adaptive Frame Resolution for Efficient Action Recognition](https://mlsanity.com/paper/2007.15796/) (2020)
- [Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM](https://mlsanity.com/paper/1707.09870/) (2017)
- [Learning Type-Aware Embeddings for Fashion Compatibility](https://mlsanity.com/paper/1803.09196/) (2018)
- [Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenes](https://mlsanity.com/paper/1609.00866/) (2016)
- [PANDA: A Gigapixel-level Human-centric Video Dataset](https://mlsanity.com/paper/2003.04852/) (2020)
- [Structural Pruning via Latency-Saliency Knapsack](https://mlsanity.com/paper/2210.06659/) (2022)
- [Learning Similarity Conditions Without Explicit Supervision](https://mlsanity.com/paper/1908.08589/) (2019)
- [HoughNet: Integrating near and long-range evidence for bottom-up object detection](https://mlsanity.com/paper/2007.02355/) (2020)
- [Effectively Leveraging Attributes for Visual Similarity](https://mlsanity.com/paper/2105.01695/) (2021)
- [Do Different Deep Metric Learning Losses Lead to Similar Learned Features?](https://mlsanity.com/paper/2205.02698/) (2022)

## Built on by (most cited first, 3 of 3)

- [Few-Class Arena: A Benchmark for Efficient Selection of Vision Models and Dataset Difficulty Measurement](https://mlsanity.com/paper/2411.01099/) (2024)
- [StatsMerging: Statistics-Guided Model Merging via Task-Specific Teacher Distillation](https://mlsanity.com/paper/2506.04567/) (2025)
- [Efficient Neural Network Model Selection for Few-Class Application Datasets](https://mlsanity.com/paper/2606.19712/) (2026)

## Abstract (arXiv)

We examine how the choice of data-side attributes for two important visual tasks of image classification and object detection can aid in the choice or design of lightweight convolutional neural networks. We show by experimentation how four data attributes - number of classes, object color, image resolution, and object scale affect neural network model size and efficiency. Intra- and inter-class similarity metrics, based on metric learning, are defined to guide the evaluation of these attributes toward achieving lightweight models. Evaluations made using these metrics are shown to require 30x less computation than running full inference tests. We provide, as an example, applying the metrics and methods to choose a lightweight model for a robot path planning application and achieve computation reduction of 66% and accuracy gain of 3.5% over the pre-method model.