Weakly Supervised Learning for Target Detection in Remote Sensing Images

By Dingwen Zhang, Junwei Han, Gong Cheng, Zhenbao Liu, Shuhui Bu, Lei Guo. 2015

99 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

1. Junwei Han
2. Gong Cheng
3. Liangpei Zhang
4. Peicheng Zhou
5. Xiaoqiang Lu
6. Xiwen Yao
7. Lei Guo
8. Bo Du

In Media Technology

1. Gong Cheng
2. Junwei Han
3. Liangpei Zhang
4. Xiaoqiang Lu
5. Peicheng Zhou
6. Lei Guo
7. Xiwen Yao
8. Xuelong Li

Citations in the corpus

• Feature significance-based multibag-of-visual-words model for remote sensing image scene classification (2016, methodology): “HRRS image scene classification aims to narrow the gap between low-level visual features and high-level semantic information to interpret HRRS images and is widely used for many applications, such as detection of areas of interest and urban planning.(13,14) Among the existing studies on HRRS image s”
• 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.”
• Hierarchical and Robust Convolutional Neural Network for Very High-Resolution Remote Sensing Object Detection (2019, methodology): “Consequently, the BoW model and its variants have been widely adopted by the community and have shown good performance for RSI object detection [10], [28]–[31].”
• A Survey on Object Detection in Optical Remote Sensing Images (2016, unknown): “…(Chen et al., 2011a, 2013; Qian et al., 2013; Tao et al., 2012), and object detection in RSIs (Chen et al., 2011b, c; Cheng et al., 2014c; Du and Zhang, 2014; Han et al., 2014; Liu and Shi, 2014; Yokoya and Iwasaki, 2015; Zhang et al., 2014a; Zhang et al., 2015c; Zhang et al., 2015d).”
• A Self-Paced Multiple-Instance Learning Framework for Co-Saliency Detection (2015, methodology): “For future work, we plan to apply the proposed method to more extensive real applications, such as image/video co-segmentation [5], co-localization [6], and weakly supervised learning [47].”
• Weakly Supervised Learning Based on Coupled Convolutional Neural Networks for Aircraft Detection (2016, methodology): “In [31], weakly supervised learning was adopted and heuris-”
• 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].”
• Semantic Annotation of High-Resolution Satellite Images via Weakly Supervised Learning (2016, methodology): “[25] leveraged WSL for object detection in HR images, which only needs to indicate whether the images in the training set contain targets or not.”
• Cosaliency Detection Based on Intrasaliency Prior Transfer and Deep Intersaliency Mining (2016, background): “framework [50], [51] for helping the object selecting with weakly labeled images.”
• Weakly supervised target detection in remote sensing images based on transferred deep features and negative bootstrapping (2015, methodology): “To detect targets in RSIs efficiently and accurately, we adopt a candidate-patch-based target detection scheme (Zhang et al. 2015), which results in about 10 times speed gain compared with conventional sliding window-based methods.”
• 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].”
• Learning Rotation-Invariant Convolutional Neural Networks for Object Detection in VHR Optical Remote Sensing Images (2016, methodology): “They are two standard and widely used measures in many object detection works such as those in [1], [7], [8], [16], and [22].”
• Object Detection in Optical Remote Sensing Images Based on Weakly Supervised Learning and High-Level Feature Learning (2015, unknown): “It also improves the performance of the previous WSL based approach [23] significantly, i.e., 0.088 (8.88%), 0.1499 (14.99%), and 0.024 (2.4”
• Two-Stage Learning to Predict Human Eye Fixations via SDAEs (2016, background): “The saliency models have benefited a wide range of multimedia applications such as image segmentation [2], image collage [3], image categorization [4], weakly supervised learning [5]–[7], object retrieval/detection [8]–[10], and video summarization [11], [12].”