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

By Yancheng Bai, Yongqiang Zhang, Ming Ding, Bernard Ghanem. 2018

429 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

In Generative Models

Citations in the corpus

Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection (2019, neutral): “2 SOD-MTGAN [1] trainval35k ResNet-101 41.”
Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection (2021, neutral): “In the task of image-based object detection, object detectors are trained on large-scale datasets and then deployed on real-world applications [9, 11, 8, 24, 5, 15, 23, 17, 16, 1, 2, 39, 33, 34, 38, 36, 37, 35, 32].”
Towards Large-Scale Small Object Detection: Survey and Benchmarks (2022, methodology): “ClusDet [135] CDMNet [136] DMNet [137] CRENet [138] EdgeDuet [139] F&D [140] EFPN [112] Edge-Enhanced GAN [114] MTGAN [117] Precise Supervision [120] PerceptualGAN [122]”
Video Self-Stitching Graph Network for Temporal Action Localization (2020, background): “Multiple methods have been proposed to deal with small objects specifically [3, 28] or object scale variation in general [4, 21] in images.”
KGSNet: Key-Point-Guided Super-Resolution Network for Pedestrian Detection in the Wild (2020, background): “2, the backbone of the super-resolution network is a deep CNN architecture, which has shown effectiveness for image deblur-ring [65], tiny face detection [66], [67], and small general object detection [68].”
Learning Rich Features at High-Speed for Single-Shot Object Detection (2019, background): “Despite showing impressive results on large and medium sized objects, these detectors achieve belowexpected performance on small objects [1].”
Deep Learning for Image Super-Resolution: A Survey (2019, background): “Other than improving image perceptual quality, it also helps to improve other computer vision tasks [6], [7], [8], [9].”
Extended Feature Pyramid Network for Small Object Detection (2020, background): “Instead of super-resolving the whole image, SOD-MTGAN [10] only super-resolves the area of RoIs, but large quantities of RoIs still need considerable computation.”
Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network (2020, methodology): “Simultaneous CNN-based image enhancement with object detection using single-shot multibox detector (SSD) [10] was done in [59].”
A Normalized Gaussian Wasserstein Distance for Tiny Object Detection (2021, neutral): “Recent advances for tiny object detection (TOD) mainly focus on improving the feature discrimination [14, 37, 20, 12, 1, 19].”
A Deep Journey into Super-resolution (2019, background): “Furthermore, super-resolution has important applications in many other domains e.g. object detection in scenes [6] (particularly small objects [7]), face recognition in surveillance videos [8], medical imaging [9], improving interpretation of images in remote sensing [10], astronomical images [11],…”
FloW: A Dataset and Benchmark for Floating Waste Detection in Inland Waters (2021, background): “For object detection based on deep neural network, compared to large objects, small objects usually lack appearance information and the high-level features of small objects are not discriminative, making it hard to distinguish them from the background and achieve accurate localization [2, 22].”
Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark (2022, neutral): “While the Generative Adversarial Network (GAN) is proposed to directly generate super-resolved representations for small objects (Li et al., 2017; Bai et al., 2018; Noh et al., 2019).”
Multi-task Generative Adversarial Network for Detecting Small Objects in the Wild (2020, methodology): “2, we adopt a deep CNN architecture which has shown effectiveness for image de-blurring in (Hradiš et al. 2015), general object detection in (Bai et al. 2018b) and face detection in (Bai et al. 2018a).”
Object Detection in 20 Years: A Survey (2019, positive): “For small object detection, GAN can be used to enhance the features of small objects by narrowing the representations between small and large ones [198], [199].”
A Survey on Generative Adversarial Networks: Variants, Applications, and Training (2020, methodology): “Inspired by [94], Disentangled Makeup Transfer GAN (DMT-GAN) [96] model proposed for facial makeup transformation where the input image first decomposed into two independents parts, the makeup-style, and personal identity parts, and then two encoders-one decoder mechanism is applied (one encoder for”