mlsanityData to 14 Oct 2026

Data-Side Efficiencies for Lightweight Convolutional Neural Networks

arXiv 2308.13057 ↗First posted 24 Aug 2023cs.CVcited by 3

Not on the map. Why?

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.

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

25 of 48 references.

References · 25

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  7. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  8. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  9. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  10. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
  11. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  12. 2020What is the State of Neural Network Pruning?cited by 583
13 more
  1. 2017A Survey of Model Compression and Acceleration for Deep Neural Networkscited by 301
  2. 2020Resolution Adaptive Networks for Efficient Inferencecited by 146
  3. 2015End-to-end Learning of Action Detection from Frame Glimpses in Videoscited by 101
  4. 2020AR-Net: Adaptive Frame Resolution for Efficient Action Recognitioncited by 88
  5. 2017Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMMcited by 61
  6. 2018Learning Type-Aware Embeddings for Fashion Compatibilitycited by 61
  7. 2016Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenescited by 50
  8. 2020PANDA: A Gigapixel-level Human-centric Video Datasetcited by 45
  9. 2022Structural Pruning via Latency-Saliency Knapsackcited by 41
  10. 2019Learning Similarity Conditions Without Explicit Supervisioncited by 36
  11. 2020HoughNet: Integrating near and long-range evidence for bottom-up object detectioncited by 20
  12. 2021Effectively Leveraging Attributes for Visual Similaritycited by 9
  13. 2022Do Different Deep Metric Learning Losses Lead to Similar Learned Features?cited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2024Few-Class Arena: A Benchmark for Efficient Selection of Vision Models and Dataset Difficulty Measurementcited by 2
  2. 2025StatsMerging: Statistics-Guided Model Merging via Task-Specific Teacher Distillationcited by 1
  3. 2026Efficient Neural Network Model Selection for Few-Class Application Datasetscited by 0