mlsanityData to 7 Oct 2026

Lightweight Alpha Matting Network Using Distillation-Based Channel Pruning

arXiv 2210.07760 ↗First posted 14 Oct 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Recently, alpha matting has received a lot of attention because of its usefulness in mobile applications such as selfies. Therefore, there has been a demand for a lightweight alpha matting model due to the limited computational resources of commercial portable devices. To this end, we suggest a distillation-based channel pruning method for the alpha matting networks. In the pruning step, we remove channels of a student network having fewer impacts on mimicking the knowledge of a teacher network. Then, the pruned lightweight student network is trained by the same distillation loss. A lightweight alpha matting model from the proposed method outperforms existing lightweight methods. To show superiority of our algorithm, we provide various quantitative and qualitative experiments with in-depth analyses. Furthermore, we demonstrate the versatility of the proposed distillation-based channel pruning method by applying it to semantic segmentation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 55 references that are in the map. First posted on arXiv 14 Oct 2022.

Builds on

25 of 55 references.

References · 25

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  5. 2016Pyramid Scene Parsing Networkcited by 2,472
  6. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  7. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  8. 2016Pruning Filters for Efficient ConvNetscited by 1,129
  9. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  10. 2018Rethinking the Value of Network Pruningcited by 595
  11. 2016Learning Structured Sparsity in Deep Neural Networkscited by 538
  12. 2019Similarity-Preserving Knowledge Distillationcited by 507
13 more
  1. 2020Pruning neural networks without any data by iteratively conserving synaptic flowcited by 475
  2. 2019A Comprehensive Overhaul of Feature Distillationcited by 341
  3. 2017Variational Dropout Sparsifies Deep Neural Networkscited by 265
  4. 2017Deep Image Mattingcited by 150
  5. 2018Dynamic Channel Pruning: Feature Boosting and Suppressioncited by 129
  6. 2019Indices Matter: Learning to Index for Deep Image Mattingcited by 93
  7. 2020Mask Guided Matting via Progressive Refinement Networkcited by 84
  8. 2020Natural Image Matting via Guided Contextual Attentioncited by 78
  9. 2017Information-Flow Mattingcited by 59
  10. 2018Low-resolution Face Recognition in the Wild via Selective Knowledge Distillationcited by 55
  11. 2021Semantic Image Mattingcited by 55
  12. 2018AlphaGAN: Generative adversarial networks for natural image mattingcited by 50
  13. 2019Disentangled Image Mattingcited by 47

Built on by

Not cited yet.