mlsanityData to 7 Oct 2026

Chosen methods of improving small object recognition with weak recognizable features

arXiv 2208.13591 ↗First posted 29 Aug 2022cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Many object detection models struggle with several problematic aspects of small object detection including the low number of samples, lack of diversity and low features representation. Taking into account that GANs belong to generative models class, their initial objective is to learn to mimic any data distribution. Using the proper GAN model would enable augmenting low precision data increasing their amount and diversity. This solution could potentially result in improved object detection results. Additionally, incorporating GAN-based architecture inside deep learning model can increase accuracy of small objects recognition. In this work the GAN-based method with augmentation is presented to improve small object detection on VOC Pascal dataset. The method is compared with different popular augmentation strategies like object rotations, shifts etc. The experiments are based on FasterRCNN model.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 35 references that are in the map. First posted on arXiv 29 Aug 2022.

Builds on

25 of 35 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2022Generative Adversarial Networkscited by 5,603
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  9. 2014Going Deeper with Convolutionscited by 4,231
  10. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  11. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  12. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
13 more
  1. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  2. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  3. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  4. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  5. 2018GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classificationcited by 242
  6. 2016Speed/accuracy trade-offs for modern convolutional object detectorscited by 198
  7. 2018Constructing Unrestricted Adversarial Examples with Generative Modelscited by 135
  8. 2017Perceptual Generative Adversarial Networks for Small Object Detectioncited by 76
  9. 2019Augmentation for small object detectioncited by 73
  10. 2016Finding Tiny Facescited by 72
  11. 2019Small Object Detection using Context and Attentioncited by 21
  12. 2019AT-GAN: An Adversarial Generator Model for Non-constrained Adversarial Examplescited by 17
  13. 2019Improve Object Detection by Data Enhancement based on Generative Adversarial Netscited by 1

Built on by

Not cited yet.