mlsanityData to 7 Oct 2026

Selective Multi-Scale Learning for Object Detection

arXiv 2206.08206 ↗First posted 16 Jun 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Pyramidal networks are standard methods for multi-scale object detection. Current researches on feature pyramid networks usually adopt layer connections to collect features from certain levels of the feature hierarchy, and do not consider the significant differences among them. We propose a better architecture of feature pyramid networks, named selective multi-scale learning (SMSL), to address this issue. SMSL is efficient and general, which can be integrated in both single-stage and two-stage detectors to boost detection performance, with nearly no extra inference cost. RetinaNet combined with SMSL obtains 1.8% improvement in AP (from 39.1% to 40.9%) on COCO dataset. When integrated with SMSL, two-stage detectors can get around 1.0% improvement in AP.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 30 references that are in the map. First posted on arXiv 16 Jun 2022.

Builds on

23 of 30 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2017Mask R-CNNcited by 7,259
  5. 2016Layer Normalizationcited by 5,579
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2017Non-local Neural Networkscited by 2,290
  8. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  9. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  10. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  11. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  12. 2018Path Aggregation Network for Instance Segmentationcited by 796
11 more
  1. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  2. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  3. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 289
  4. 2019Libra R-CNN: Towards Balanced Learning for Object Detectioncited by 255
  5. 2019Scale-Aware Trident Networks for Object Detectioncited by 159
  6. 2019Bottom-up Object Detection by Grouping Extreme and Center Pointscited by 156
  7. 2019Feature Selective Anchor-Free Module for Single-Shot Object Detectioncited by 139
  8. 2019FoveaBox: Beyond Anchor-based Object Detectorcited by 37
  9. 2017Light-Head R-CNN: In Defense of Two-Stage Object Detectorcited by 30
  10. 2018Deep Feature Pyramid Reconfiguration for Object Detectioncited by 23
  11. 2019Dense RepPoints: Representing Visual Objects with Dense Point Setscited by 16

Built on by

Not cited yet.