mlsanityData to 7 Oct 2026

Analyzing Compression Techniques for Computer Vision

arXiv 2305.08075 ↗First posted 14 May 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Compressing deep networks is highly desirable for practical use-cases in computer vision applications. Several techniques have been explored in the literature, and research has been done in finding efficient strategies for combining them. For this project, we aimed to explore three different basic compression techniques - knowledge distillation, pruning, and quantization for small-scale recognition tasks. Along with the basic methods, we also test the efficacy of combining them in a sequential manner. We analyze them using MNIST and CIFAR-10 datasets and present the results along with few observations inferred from them.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 26 references that are in the map. First posted on arXiv 14 May 2023.

Builds on

16 of 26 references.

References · 16

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  3. 2014FitNets: Hints for Thin Deep Netscited by 1,619
  4. 2016Group Equivariant Convolutional Networkscited by 1,154
  5. 2016Deep Networks with Stochastic Depthcited by 973
  6. 2019Improved Knowledge Distillation via Teacher Assistantcited by 567
  7. 2021Carbon Emissions and Large Neural Network Trainingcited by 561
  8. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  9. 2013Do Deep Nets Really Need to be Deep?cited by 466
  10. 2014Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluationcited by 304
  11. 2013Predicting Parameters in Deep Learningcited by 223
  12. 2015Compressing Neural Networks with the Hashing Trickcited by 150
4 more
  1. 2016Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1cited by 102
  2. 2020An Overview of Neural Network Compressioncited by 59
  3. 2015Bayesian Dark Knowledgecited by 45
  4. 2014Training deep neural networks with low precision multiplicationscited by 3

Built on by

Not cited yet.