mlsanityData to 7 Oct 2026

CondenseNet V2: Sparse Feature Reactivation for Deep Networks

arXiv 2104.04382 ↗First posted 9 Apr 2021cs.CVcited by 34

Not on the map. Why?

Abstract (arXiv)

Reusing features in deep networks through dense connectivity is an effective way to achieve high computational efficiency. The recent proposed CondenseNet has shown that this mechanism can be further improved if redundant features are removed. In this paper, we propose an alternative approach named sparse feature reactivation (SFR), aiming at actively increasing the utility of features for reusing. In the proposed network, named CondenseNetV2, each layer can simultaneously learn to 1) selectively reuse a set of most important features from preceding layers; and 2) actively update a set of preceding features to increase their utility for later layers. Our experiments show that the proposed models achieve promising performance on image classification (ImageNet and CIFAR) and object detection (MS COCO) in terms of both theoretical efficiency and practical speed.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 40 of its 47 references that are in the map. First posted on arXiv 9 Apr 2021.

Builds on

40 of 47 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  7. 2016Densely Connected Convolutional Networkscited by 6,691
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  9. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  10. 2017Squeeze-and-Excitation Networkscited by 4,763
  11. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  12. 2016Wide Residual Networkscited by 3,057
28 more
  1. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  2. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  3. 2019Searching for MobileNetV3cited by 1,984
  4. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  5. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  6. 2016Pruning Filters for Efficient ConvNetscited by 1,129
  7. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  8. 2020Designing Network Design Spacescited by 954
  9. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  10. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  11. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
  12. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  13. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 666
  14. 2017Progressive Neural Architecture Searchcited by 483
  15. 2019GhostNet: More Features from Cheap Operationscited by 410
  16. 2021Dynamic Neural Networks: A Surveycited by 405
  17. 2018Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Accelerationcited by 365
  18. 2017NISP: Pruning Networks using Neuron Importance Score Propagationcited by 228
  19. 2020Resolution Adaptive Networks for Efficient Inferencecited by 146
  20. 2017CondenseNet: An Efficient DenseNet using Learned Group Convolutionscited by 121
  21. 2020Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classificationcited by 99
  22. 2018ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Networkcited by 90
  23. 2019Pruning from Scratchcited by 72
  24. 2020Rethinking Bottleneck Structure for Efficient Mobile Network Designcited by 54
  25. 2019All You Need is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image Classificationcited by 38
  26. 2019Fully Learnable Group Convolution for Acceleration of Deep Neural Networkscited by 16
  27. 2018IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networkscited by 14
  28. 2020Filter Grafting for Deep Neural Networkscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 9; 2023: 6; 2024: 12; 2025: 4; 2026: 1.

34 papers.

Sort:

By area:

  1. 2021Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognitioncited by 143
  2. 2023Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networkscited by 129
  3. 2024DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Executioncited by 116
  4. 2022Learning to Weight Samples for Dynamic Early-exiting Networkscited by 44
  5. 2022EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbonescited by 42
  6. 2022Glance and Focus Networks for Dynamic Visual Recognitioncited by 41
  7. 2024Lightweight Deep Learning for Resource-Constrained Environments: A Surveycited by 38
  8. 2022Pseudo-Q: Generating Pseudo Language Queries for Visual Groundingcited by 33
  9. 2023Dynamic Perceiver for Efficient Visual Recognitioncited by 33
  10. 2023Latency-aware Unified Dynamic Networks for Efficient Image Recognitioncited by 26
  11. 2024Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Networkcited by 26
  12. 2024Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptationcited by 25
22 more
  1. 2024Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Modelcited by 22
  2. 2023DAT++: Spatially Dynamic Vision Transformer with Deformable Attentioncited by 21
  3. 2022GhostNets on Heterogeneous Devices via Cheap Operationscited by 14
  4. 2023Computation-efficient Deep Learning for Computer Vision: A Surveycited by 14
  5. 2024Cardiac Copilot: Automatic Probe Guidance for Echocardiography with World Modelcited by 14
  6. 2022RepGhost: A Hardware-Efficient Ghost Module via Re-parameterizationcited by 13
  7. 2024AdaNAT: Exploring Adaptive Policy for Token-Based Image Generationcited by 13
  8. 2024Strengthening Layer Interaction via Dynamic Layer Attentioncited by 10
  9. 2024ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesiscited by 8
  10. 2022A Lightweight, Efficient and Explainable-by-Design Convolutional Neural Network for Internet Traffic Classificationcited by 6
  11. 2024Structure-aware World Model for Probe Guidance via Large-scale Self-supervised Pre-traincited by 6
  12. 2022Class Based Thresholding in Early Exit Semantic Segmentation Networkscited by 5
  13. 2024Fine-grained Dynamic Network for Generic Event Boundary Detectioncited by 4
  14. 2024OStr-DARTS: Differentiable Neural Architecture Search based on Operation Strengthcited by 4
  15. 2021Full-attention based Neural Architecture Search using Context Auto-regressioncited by 2
  16. 2025Exploring Structured Semantic Priors Underlying Diffusion Score for Test-time Adaptationcited by 2
  17. 2022Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Surveycited by 1
  18. 2023Gaining the Sparse Rewards by Exploring Lottery Tickets in Spiking Neural Networkcited by 1
  19. 2025A Novel Trustworthy Video Summarization Algorithm Through a Mixture of LoRA Expertscited by 0
  20. 2025Compound and Parallel Modes of Tropical Convolutional Neural Networkscited by 0
  21. 2025DynaNav: Dynamic Feature and Layer Selection for Efficient Visual Navigationcited by 0
  22. 2026Unleashing the Representational Power of Fourier Shapes for Attacking Infrared Object Detectioncited by 0