mlsanityData to 7 Oct 2026

Expanding-and-Shrinking Binary Neural Networks

arXiv 2503.23709 ↗First posted 31 Mar 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

While binary neural networks (BNNs) offer significant benefits in terms of speed, memory and energy, they encounter substantial accuracy degradation in challenging tasks compared to their real-valued counterparts. Due to the binarization of weights and activations, the possible values of each entry in the feature maps generated by BNNs are strongly constrained. To tackle this limitation, we propose the expanding-and-shrinking operation, which enhances binary feature maps with negligible increase of computation complexity, thereby strengthening the representation capacity. Extensive experiments conducted on multiple benchmarks reveal that our approach generalizes well across diverse applications ranging from image classification, object detection to generative diffusion model, while also achieving remarkable improvement over various leading binarization algorithms based on different architectures including both CNNs and Transformers.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 42 of its 55 references that are in the map. First posted on arXiv 31 Mar 2025.

Builds on

42 of 55 references.

References · 42

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  6. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  7. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  8. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  9. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  10. 2019Learned Step Size Quantizationcited by 604
  11. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  12. 2015Sketch-based Manga Retrieval using Manga109 Datasetcited by 326
30 more
  1. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 234
  2. 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 233
  3. 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 226
  4. 2020ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functionscited by 183
  5. 2019Forward and Backward Information Retention for Accurate Binary Neural Networkscited by 169
  6. 2021Focal and Global Knowledge Distillation for Detectorscited by 138
  7. 2020Training Binary Neural Networks with Real-to-Binary Convolutionscited by 111
  8. 2019XNOR-Net++: Improved Binary Neural Networkscited by 94
  9. 2020Rotated Binary Neural Networkcited by 77
  10. 2023Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstructioncited by 60
  11. 2021ReCU: Reviving the Dead Weights in Binary Neural Networkscited by 51
  12. 2022Revisiting Random Channel Pruning for Neural Network Compressioncited by 50
  13. 2021How Do Adam and Training Strategies Help BNNs Optimization?cited by 46
  14. 2023DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillationcited by 41
  15. 2018Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?cited by 38
  16. 2022AdaBin: Improving Binary Neural Networks with Adaptive Binary Setscited by 38
  17. 2018Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentationcited by 37
  18. 2020BiDet: An Efficient Binarized Object Detectorcited by 33
  19. 2023GEDepth: Ground Embedding for Monocular Depth Estimationcited by 26
  20. 2022Basic Binary Convolution Unit for Binarized Image Restoration Networkcited by 22
  21. 2023Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotioncited by 21
  22. 2023HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understandingcited by 21
  23. 2023Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Trainingcited by 19
  24. 2021SiMaN: Sign-to-Magnitude Network Binarizationcited by 18
  25. 2024Binarized Diffusion Model for Image Super-Resolutioncited by 18
  26. 2023BinaryViT: Pushing Binary Vision Transformers Towards Convolutional Modelscited by 17
  27. 2022Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticketcited by 13
  28. 2022INSTA-BNN: Binary Neural Network with INSTAnce-aware Thresholdcited by 9
  29. 2023Transcendental Idealism of Planner: Evaluating Perception from Planning Perspective for Autonomous Drivingcited by 9
  30. 2024QN-Mixer: A Quasi-Newton MLP-Mixer Model for Sparse-View CT Reconstructioncited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Binary Early-Exit Network for Adaptive Inference on Low-Resource Devices
  2. 2023Binary Latent Diffusion
  3. 2023BRICS: Bi-level feature Representation of Image CollectionS
  4. 2024ReDistill: Residual Encoded Distillation for Peak Memory Reduction of CNNs
  5. 2024BiDM: Pushing the Limit of Quantization for Diffusion Models
  6. 2024An Efficient Framework for Enhancing Discriminative Models via Diffusion Techniques
  7. 2025ERDE: Entropy-Regularized Distillation for Early-exit
  8. 2024A Decade of Deep Learning: A Survey on The Magnificent Seven