Weakly supervised target detection in remote sensing images based on transferred deep features and negative bootstrapping

By Peicheng Zhou, Gong Cheng, Zhenbao Liu, Shuhui Bu, Xintao Hu. 2015

91 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Remote Sensing Image Scene Classification: Benchmark and State of the Art (2017, background): “models have shown impressive feature representation capability for a wide range of applications including remote sensing image scene classification [13, 17, 45, 50, 82, 143-158].”
Deep learning in remote sensing: a review (2017, methodology): “[99] presented a weakly supervised learning framework to train an object detector; here, a pretrained CNN model is transferred to extract high-level features of objects, and the negative bootstrapping scheme is incorporated into the detector training process to provide faster convergence of the dete”
Scene classification of high resolution remote sensing images using convolutional neural networks (2016, background): “Scene classification of high resolution remote sensing images plays an important role for a wide range of applications, such as land-use determination, natural hazards detection, urban planning, geospatial object detection and so on [4-17].”
Weakly Supervised Object Localization and Detection: A Survey (2021, unknown): “…existing algorithms only learn weakly supervised object detectors for one or several certain object categories, such as vehicles [12], trafﬁc signs [82], [191], pedestrians [9], [165], faces [42], [59], tuberculosis bacilli [68], aircrafts [56], [194], [217], [218], and human actions [59], [102].”
Learning Rotation-Invariant Convolutional Neural Networks for Object Detection in VHR Optical Remote Sensing Images (2016, background): “can be performed by learning a classifier, such as support vector machine (SVM) [1], [7], [8], [12], [13], [20]–[24], AdaBoost [2]–[5], k-nearest neighbors [15], [17], conditional random field [6], [19], and sparse-coding-based classifier [9]–[11], [14], [16], which captures the variation in object ”
Object detection in VHR optical remote sensing images via learning rotation-invariant HOG feature (2016, methodology): “We therefore adopt a simple and widely-used non-maximum suppression (NMS) strategy as the work of [1, 3, 4, 6, 7, 9] to eliminate the repeated detections.”
A Survey on Object Detection in Optical Remote Sensing Images (2016, unknown): “…methods (Cheng et al., 2013b; Cheng et al., 2014a, b; Zhang et al., 2014b; Zhang et al., 2015b) and the sparelets work (Cheng et al., 2015a; Cheng et al., 2015b; Cheng et al., 2015c) -norm: , -norm: ‹ where x is a small constant and the results are insensitive to the value of x over a…”
Deep Learning for Change Detection in Remote Sensing Images: Comprehensive Review and Meta-Analysis (2020, background): “Recent progress in the geospatial object detection field [128], [129] has shown the feasibility of using weakly supervised learning.”