mlsanityData to 7 Oct 2026

Compressive Feature Selection for Remote Visual Multi-Task Inference

arXiv 2405.09077 ↗First posted 15 May 2024eess.IV cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep models produce a number of features in each internal layer. A key problem in applications such as feature compression for remote inference is determining how important each feature is for the task(s) performed by the model. The problem is especially challenging in the case of multi-task inference, where the same feature may carry different importance for different tasks. In this paper, we examine how effective is mutual information (MI) between a feature and a model's task output as a measure of the feature's importance for that task. Experiments involving hard selection and soft selection (unequal compression) based on MI are carried out to compare the MI-based method with alternative approaches. Multi-objective analysis is provided to offer further insight.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 43 references that are in the map. First posted on arXiv 15 May 2024.

Builds on

25 of 43 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2018YOLOv3: An Incremental Improvementcited by 2,652
  5. 2016Pruning Filters for Efficient ConvNetscited by 1,129
  6. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 685
  7. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  8. 2017ThiNet: A Filter Level Pruning Method for Deep Neural Network Compressioncited by 438
  9. 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 374
  10. 2018Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Accelerationcited by 365
  11. 2019Multi-Task Deep Neural Networks for Natural Language Understandingcited by 349
  12. 2018Soft Filter Pruning for Accelerating Deep Convolutional Neural Networkscited by 313
13 more
  1. 2020HRank: Filter Pruning using High-Rank Feature Mapcited by 291
  2. 2018Formal Limitations on the Measurement of Mutual Informationcited by 189
  3. 2021Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challengescited by 114
  4. 2015A Review of Feature Selection Methods Based on Mutual Informationcited by 67
  5. 2018Deep feature compression for collaborative object detectioncited by 48
  6. 2018Leveraging Filter Correlations for Deep Model Compressioncited by 23
  7. 2019Feature Selection via Mutual Information: New Theoretical Insightscited by 17
  8. 2022Collaborative Inference for AI-Empowered IoT Devicescited by 14
  9. 2020Bit Allocation for Multi-Task Collaborative Intelligencecited by 13
  10. 2020MINT: Deep Network Compression via Mutual Information-based Neuron Trimmingcited by 11
  11. 2020Feature Statistics Guided Efficient Filter Pruningcited by 11
  12. 2018SCSP: Spectral Clustering Filter Pruning with Soft Self-adaption Mannerscited by 7
  13. 2018PCAS: Pruning Channels with Attention Statistics for Deep Network Compressioncited by 7

Built on by

Not cited yet.