mlsanityData to 14 Oct 2026

DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors

arXiv 2311.17098 ↗First posted 28 Nov 2023cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Achieving constant accuracy in object detection is challenging due to the inherent variability of object sizes. One effective approach to this problem involves optimizing input resolution, referred to as a multi-resolution strategy. Previous approaches to resolution optimization have often been based on pre-defined resolutions with manual selection. However, there is a lack of study on run-time resolution optimization for existing architectures. This paper introduces DyRA, a dynamic resolution adjustment network providing an image-specific scale factor for existing detectors. This network is co-trained with detectors utilizing specially designed loss functions, namely ParetoScaleLoss and BalanceLoss. ParetoScaleLoss determines an adaptive scale factor for robustness, while BalanceLoss optimizes overall scale factors according to the localization performance of the detector. The loss function is devised to minimize the accuracy drop across contrasting objectives of different-sized objects for scaling. Our proposed network can improve accuracy across various models, including RetinaNet, Faster-RCNN, FCOS, DINO, and H-Deformable-DETR. The code is available at https://github.com/DaEunFullGrace/DyRA.git.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 57 of its 71 references that are in the map. First posted on arXiv 28 Nov 2023.

Builds on

57 of 71 references.

References · 57

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2020End-to-End Object Detection with Transformerscited by 7,414
  7. 2017Mask R-CNNcited by 7,277
  8. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  9. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  10. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  11. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  12. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
38 more
  1. 2017Squeeze-and-Excitation Networkscited by 4,789
  2. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  3. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  4. 2015Fast R-CNNcited by 2,933
  5. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  6. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  7. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
  8. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  9. 2017Deformable Convolutional Networkscited by 1,488
  10. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  11. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,228
  12. 2017Mixed Precision Trainingcited by 1,156
  13. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  14. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  15. 2018Path Aggregation Network for Instance Segmentationcited by 798
  16. 2018AutoAugment: Learning Augmentation Policies from Datacited by 730
  17. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 670
  18. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 623
  19. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 540
  20. 2021Dynamic Neural Networks: A Surveycited by 408
  21. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 291
  22. 2019RepPoints: Point Set Representation for Object Detectioncited by 264
  23. 2020Scaled-YOLOv4: Scaling Cross Stage Partial Networkcited by 211
  24. 2021ReDet: A Rotation-equivariant Detector for Aerial Object Detectioncited by 203
  25. 2021Dynamic Head: Unifying Object Detection Heads with Attentionscited by 187
  26. 2017Adaptive Neural Networks for Efficient Inferencecited by 163
  27. 2019Scale-Aware Trident Networks for Object Detectioncited by 159
  28. 2022FlexiViT: One Model for All Patch Sizescited by 152
  29. 2022DETRs with Hybrid Matchingcited by 150
  30. 2017An Analysis of Scale Invariance in Object Detection - SNIPcited by 120
  31. 2019FreeAnchor: Learning to Match Anchors for Visual Object Detectioncited by 90
  32. 2018SNIPER: Efficient Multi-Scale Trainingcited by 88
  33. 2019Region Proposal by Guided Anchoringcited by 87
  34. 2018Channel Gating Neural Networkscited by 80
  35. 2019SRM : A Style-based Recalibration Module for Convolutional Neural Networkscited by 66
  36. 2020Dynamic ReLUcited by 55
  37. 2017IDK Cascades: Fast Deep Learning by Learning not to Overthinkcited by 48
  38. 2022ResFormer: Scaling ViTs with Multi-Resolution Trainingcited by 34

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Scale-Gest: Scalable Model-Space Synthesis and Runtime Selection for On-Device Gesture Detectioncited by 0