mlsanityData to 7 Oct 2026

Evaluating Supervision Levels Trade-Offs for Infrared-Based People Counting

arXiv 2311.11974 ↗First posted 20 Nov 2023cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Object detection models are commonly used for people counting (and localization) in many applications but require a dataset with costly bounding box annotations for training. Given the importance of privacy in people counting, these models rely more and more on infrared images, making the task even harder. In this paper, we explore how weaker levels of supervision can affect the performance of deep person counting architectures for image classification and point-level localization. Our experiments indicate that counting people using a CNN Image-Level model achieves competitive results with YOLO detectors and point-level models, yet provides a higher frame rate and a similar amount of model parameters.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 51 references that are in the map. First posted on arXiv 20 Nov 2023.

Builds on

33 of 51 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  8. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  9. 2022A ConvNet for the 2020scited by 3,545
  10. 2018YOLOv3: An Incremental Improvementcited by 2,652
  11. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  12. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
21 more
  1. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  2. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  3. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  4. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
  5. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 486
  6. 2021High-Performance Large-Scale Image Recognition Without Normalizationcited by 359
  7. 2021LLVIP: A Visible-infrared Paired Dataset for Low-light Visioncited by 229
  8. 2021VOLO: Vision Outlooker for Visual Recognitioncited by 164
  9. 2021Rethinking Counting and Localization in Crowds:A Purely Point-Based Frameworkcited by 152
  10. 2018Context-Aware Crowd Countingcited by 150
  11. 2020Distribution Matching for Crowd Countingcited by 143
  12. 2021Dive into Deep Learningcited by 111
  13. 2022Rethinking Spatial Invariance of Convolutional Networks for Object Countingcited by 54
  14. 2023Point-Query Quadtree for Crowd Counting, Localization, and Morecited by 40
  15. 2020A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowdscited by 36
  16. 2019FishNet: A Versatile Backbone for Image, Region, and Pixel Level Predictioncited by 16
  17. 2022FusionCount: Efficient Crowd Counting via Multiscale Feature Fusioncited by 13
  18. 2022Privacy-Preserving Person Detection Using Low-Resolution Infrared Camerascited by 7
  19. 2019Deep Density-aware Count Regressorcited by 6
  20. 2019Metamorphic Testing for Object Detection Systemscited by 6
  21. 2016Fast On-Line Kernel Density Estimation for Active Object Localizationcited by 4

Built on by

Not cited yet.