mlsanityData to 7 Oct 2026

Why Accuracy Is Not Enough: The Need for Consistency in Object Detection

arXiv 2207.13890 ↗First posted 28 Jul 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Object detectors are vital to many modern computer vision applications. However, even state-of-the-art object detectors are not perfect. On two images that look similar to human eyes, the same detector can make different predictions because of small image distortions like camera sensor noise and lighting changes. This problem is called inconsistency. Existing accuracy metrics do not properly account for inconsistency, and similar work in this area only targets improvements on artificial image distortions. Therefore, we propose a method to use non-artificial video frames to measure object detection consistency over time, across frames. Using this method, we show that the consistency of modern object detectors ranges from 83.2% to 97.1% on different video datasets from the Multiple Object Tracking Challenge. We conclude by showing that applying image distortion corrections like .WEBP Image Compression and Unsharp Masking can improve consistency by as much as 5.1%, with no loss in accuracy.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 28 references that are in the map. First posted on arXiv 28 Jul 2022.

Builds on

14 of 28 references.

References · 14

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Mask R-CNNcited by 7,259
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  7. 2016Universal adversarial perturbationscited by 774
  8. 2019Making Convolutional Networks Shift-Invariant Againcited by 390
  9. 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
  10. 2015MOTChallenge 2015: Towards a Benchmark for Multi-Target Trackingcited by 133
  11. 2016Understanding How Image Quality Affects Deep Neural Networkscited by 118
  12. 2020Sparse PCA: Algorithms, Adversarial Perturbations and Certificatescited by 18
2 more
  1. 2019Using Videos to Evaluate Image Model Robustnesscited by 13
  2. 2018Large-Scale Object Detection of Images from Network Cameras in Variable Ambient Lighting Conditionscited by 2

Built on by

Not cited yet.