mlsanityData to 7 Oct 2026

An Empirical Study of Adder Neural Networks for Object Detection

arXiv 2112.13608 ↗First posted 27 Dec 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Adder neural networks (AdderNets) have shown impressive performance on image classification with only addition operations, which are more energy efficient than traditional convolutional neural networks built with multiplications. Compared with classification, there is a strong demand on reducing the energy consumption of modern object detectors via AdderNets for real-world applications such as autonomous driving and face detection. In this paper, we present an empirical study of AdderNets for object detection. We first reveal that the batch normalization statistics in the pre-trained adder backbone should not be frozen, since the relatively large feature variance of AdderNets. Moreover, we insert more shortcut connections in the neck part and design a new feature fusion architecture for avoiding the sparse features of adder layers. We present extensive ablation studies to explore several design choices of adder detectors. Comparisons with state-of-the-arts are conducted on COCO and PASCAL VOC benchmarks. Specifically, the proposed Adder FCOS achieves a 37.8% AP on the COCO val set, demonstrating comparable performance to that of the convolutional counterpart with an about 1.4× energy reduction.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 43 of its 54 references that are in the map. First posted on arXiv 27 Dec 2021.

Builds on

43 of 54 references.

References · 43

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  3. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  6. 2018YOLOv3: An Incremental Improvementcited by 2,652
  7. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  8. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  9. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  10. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  11. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  12. 2018Path Aggregation Network for Instance Segmentationcited by 796
31 more
  1. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
  2. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  3. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  4. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  5. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  6. 2017ThiNet: A Filter Level Pruning Method for Deep Neural Network Compressioncited by 438
  7. 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 427
  8. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 408
  9. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  10. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 289
  11. 2019RepPoints: Point Set Representation for Object Detectioncited by 264
  12. 2019Libra R-CNN: Towards Balanced Learning for Object Detectioncited by 255
  13. 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 233
  14. 2020VarifocalNet: An IoU-aware Dense Object Detectorcited by 230
  15. 2019Distilling Object Detectors with Fine-grained Feature Imitationcited by 188
  16. 2020FCOS: A simple and strong anchor-free object detectorcited by 171
  17. 2019Feature Selective Anchor-Free Module for Single-Shot Object Detectioncited by 139
  18. 2018Gradient Harmonized Single-stage Detectorcited by 114
  19. 2019AdderNet: Do We Really Need Multiplications in Deep Learning?cited by 82
  20. 2018Pelee: A Real-Time Object Detection System on Mobile Devicescited by 56
  21. 2019Prime Sample Attention in Object Detectioncited by 55
  22. 2020ShiftAddNet: A Hardware-Inspired Deep Networkcited by 52
  23. 2021Manifold Regularized Dynamic Network Pruningcited by 43
  24. 2019ThunderNet: Towards Real-time Generic Object Detectioncited by 42
  25. 2020Hit-Detector: Hierarchical Trinity Architecture Search for Object Detectioncited by 32
  26. 2020AdderSR: Towards Energy Efficient Image Super-Resolutioncited by 32
  27. 2017RON: Reverse Connection with Objectness Prior Networks for Object Detectioncited by 27
  28. 2020YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Designcited by 24
  29. 2018Quantization Mimic: Towards Very Tiny CNN for Object Detectioncited by 20
  30. 2020Kernel Based Progressive Distillation for Adder Neural Networkscited by 19
  31. 2019MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devicescited by 18

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2; 2024: 1.

5 papers.

  1. 2023DFormer: Rethinking RGBD Representation Learning for Semantic Segmentationcited by 58
  2. 2022MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentationcited by 29
  3. 2023ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformercited by 15
  4. 2022Redistribution of Weights and Activations for AdderNet Quantizationcited by 3
  5. 2024Moo-ving Beyond Tradition: Revolutionizing Cattle Behavioural Phenotyping with Pose Estimation Techniquescited by 0