• Home
  • Search
  • SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network
  • Cite Icon486
  • https://doi.org/10.1007/978-3-030-01261-8_13Copy DOI Icon

SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network

  • Jan 1, 2018
  • Yancheng Bai +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Object detection is a fundamental and important problem in computer vision. Although impressive results have been achieved on large/medium sized objects in large-scale detection benchmarks (e.g. the COCO dataset), the performance on small objects is far from satisfactory. The reason is that small objects lack sufficient detailed appearance information, which can distinguish them from the background or similar objects. To deal with the small object detection problem, we propose an end-to-end multi-task generative adversarial network (MTGAN). In the MTGAN, the generator is a super-resolution network, which can up-sample small blurred images into fine-scale ones and recover detailed information for more accurate detection. The discriminator is a multi-task network, which describes each super-resolved image patch with a real/fake score, object category scores, and bounding box regression offsets. Furthermore, to make the generator recover more details for easier detection, the classification and regression losses in the discriminator are back-propagated into the generator during training. Extensive experiments on the challenging COCO dataset demonstrate the effectiveness of the proposed method in restoring a clear super-resolved image from a blurred small one, and show that the detection performance, especially for small sized objects, improves over state-of-the-art methods.

Similar Papers
  • Conference Article
  • Citations4

Boosting Fashion Image Attributes Classification Performance with MT-GAN Training Technique

  • Oct 01, 2020
  • Qun Li +3
  • Conference Article
  • Citations2

Fusion Network for Super Resolution of UAVs Visible and Thermal Images

  • May 24, 2022
  • Hedi Fkih +3
  • Conference Article
  • Citations93

Where do emotions come from? Predicting the Emotion Stimuli Map

  • Sep 01, 2016
  • Kuan-Chuan Peng +3
  • PDF
  • Research Article

Efficient Object Detection in Images Using YOLO Algorithm: A Performance Evaluation

  • Oct 23, 2025
  • ICCK Transactions on Emerging Topics in Artificial Intelligence
  • Chandra Sekhar Koppireddy +2
  • Research Article

FDA-DETR: A frequency-aware DETR with dynamic query and adaptive multi-task optimization for oriented small object detection

  • Aug 29, 2025
  • PLOS One
  • Cheng Ju +6
  • Research Article
  • Citations22

ASAYAR: A Dataset for Arabic-Latin Scene Text Localization in Highway Traffic Panels

  • Apr 01, 2022
  • IEEE Transactions on Intelligent Transportation Systems
  • Mohammed Akallouch +4
  • Research Article
  • Citations1

A Survey of Object Detection Models Based on Deep Learning

  • Apr 25, 2023
  • Computer Science and Technology
  • Weng Chengkang +1
  • Research Article
  • Citations191

Deep learning-based detection from the perspective of small or tiny objects: A survey

  • Jul 01, 2022
  • Image and Vision Computing
  • Kang Tong +1
  • PDF
  • Research Article
  • Citations57

Detection of Small Ship Objects Using Anchor Boxes Cluster and Feature Pyramid Network Model for SAR Imagery

  • Feb 12, 2020
  • Journal of Marine Science and Engineering
  • Peng Chen +4
  • Research Article
  • Citations10

Enhanced Abandoned Object Detection through Adaptive Dual-Background Modeling and SAO-YOLO Integration

  • Oct 12, 2024
  • Sensors
  • Lei Zhou +1
  • Research Article
  • Citations82

The bimodal colors of Centaurs and small Kuiper belt objects

  • Oct 01, 2012
  • Astronomy & Astrophysics
  • N Peixinho +4
  • Research Article
  • Citations78

Dense and Small Object Detection in UAV-Vision Based on a Global-Local Feature Enhanced Network

  • Jan 01, 2022
  • IEEE Transactions on Instrumentation and Measurement
  • Tao Ye +5
  • Research Article
  • Citations6

Deep multi-scale feature mixture model for image super-resolution with multiple-focal-length degradation

  • May 10, 2024
  • Signal Processing: Image Communication
  • Jun Xiao +4
  • Research Article
  • Citations2

Application of Modern Object Tracking Technologies to the Task of Aortography Key Point Detection in Transcatheter Aortic Valve Implantation

  • May 01, 2024
  • Scientific Visualization
  • V.V Laptev +1
  • Research Article
  • Citations37

Object detection in hyperspectral images

  • Sep 26, 2022
  • Digital Signal Processing
  • Zubair Ahmad Lone +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.