Automatic Weakly Supervised Object Detection From High Spatial Resolution Remote Sensing Images via Dynamic Curriculum Learning

Yao, Xiwen; Feng, Xiao; Han, Junwei; Cheng, Gong; Guo, Lei

doi:10.1109/tgrs.2020.2991407

Cited by 129 publications

(57 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cheng et al [31] proposed a unified framework to generate and select high-quality proposals, which combines selective search [32] and a Gradient-weighted Class Activation Mapping [33] to generate more proposals with higher quality, and then chooses many confident positive proposals and only class-specific hard negatives to train more effective by upweighting the losses of discriminative negative proposals. To provide high-quality initial samples and obtain optimal object detectors with only image-level annotations, Yao et al [34] proposed a dynamic curriculum learning strategy with an entropy-based criterion and designed an effective instanceaware focal loss function, which can progressively learn the object detectors by feeding training images with increasing difficulty that matches current detection ability. To avoid selecting only one top-scoring proposal that usually results in learning a suboptimal object detector, Feng et al [35]proposed a novel end-to-end progressive contextual instance refinement method by leveraging both local and global context information for weakly supervised object detection.…”

Section: Semi-supervised Semantic Segmentationmentioning

confidence: 99%

BAS$^{4}$Net: Boundary-Aware Semi-Supervised Semantic Segmentation Network for Very High Resolution Remote Sensing Images

Sun

Shi

Huang

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Semantic segmentation is a fundamental task in remote sensing image understanding. Recently, Deep Convolutional Neural Networks (DCNNs) have considerably improved the performance of the semantic segmentation of natural scenes. However, it is still challenging for Very High Resolution (VHR) remote sensing images. Due to the large and complex scenes as well as the influence of illumination and imaging angle, it is particularly difficult for the existing methods to accurately obtain the category of pixels at object boundaries-the so-called boundary blur. We propose a framework called Boundary-Aware Semi-Supervised Semantic Segmentation Network (BAS 4 Net), which obtains more accurate segmentation results without additional annotation workload, especially at the object boundaries. The Channel-weighted Multi-scale Feature (CMF) module balances semantic and spatial information and the Boundary Attention Module (BAM) weights the features with rich semantic boundary information to alleviate the boundary blur. Additionally, to decrease the amount of difficult and tedious manual labeling of remote sensing images, a discriminator network infers pseudolabels from unlabeled images to assist semi-supervised learning and further improves the performance of the segmentation network. To validate the effectiveness of the proposed framework, extensive experiments have been performed on both the ISPRS Vaihingen dataset and the novel remote sensing dataset AIR-SEG with more categories and complex boundaries. The results demonstrate a significant improvement of accuracy especially on boundaries and for small objects.

show abstract

Section: Semi-supervised Semantic Segmentationmentioning

confidence: 99%

BAS$^{4}$Net: Boundary-Aware Semi-Supervised Semantic Segmentation Network for Very High Resolution Remote Sensing Images

Sun

Shi

Huang

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The latest works on WSL based object detection from RSIs are [46,47]. In [46], Yao et al propose a dynamic curriculum learning strategy to perform weakly supervised object detection from high-resolution RSIs.…”

Section: B Weakly Supervised Learningmentioning

confidence: 99%

“…This work can progressively learn the object detectors by feeding training images with increasing difficulty that matches current detection ability. The work [47] designs a dual-contextual instance refinement strategy to divert the focus of detection network from local distinct part to the object and further to other potential instances by leveraging both local and global context information. With this, it can significantly boost object detection accuracy compared with the state of the arts.…”

Section: B Weakly Supervised Learningmentioning

confidence: 99%

Convolutional Neural Network Based Weakly Supervised Learning for Aircraft Detection From Remote Sensing Image

Weise

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Object detection methods based on Convolutional Neural Networks (CNNs) require a large number of images with annotation information to train. In aircraft detection from remote sensing images (RSIs), aircraft targets are usually small and the cost of manual annotation is very high. In this paper, we tackle the problem of weakly supervised aircraft detection from RSIs, which aims to learn detectors with only image-level annotations, i.e., without bounding-box labeled data during the training stage. Based on the fact that the feature maps learned from the CNN network are localizable, we propose a simple yet efficient aircraft detection algorithm called Weakly Supervised Learning in AlexNet (AlexNet-WSL). In AlexNet-WSL, we utilize the AlexNet CNN as backbone network, but replace the last two fully connected layers with a Global Average Pooling (GAP) and two convolutional layers. Based on the class activation maps, we generate heat maps via reverse weighting for locating the target object. Unlike object detection methods that require object location data for training, our proposal only needs image-level labelled data. We furthermore build a set of remote sensing aircraft images, the Weakly Supervised Aircraft Detection Dataset (WSADD) for algorithm benchmarking. The experimental results on the WSADD show that AlexNet-WSL effectively detects the aircraft and achieves a detection effect equivalent to the Faster R-CNN method and the YOLOv3 method, which both require bounding-box labelled data for training, with a lower false alarm rate and a shorter training time.

show abstract

“…For example, several weakly supervised object detection (WSOD) methods for remote sensing images have been proposed, e.g. the progressive contextual instance refinement method [33], and the dynamic curriculum learning method [34]. As to image-level WSSS for remote sensing images, it needs more spatial prior information for training a segmentation model compared with WSOD, and several pioneering works have also been proposed [20].…”

Section: Introductionmentioning

confidence: 99%

On the Effectiveness of Weakly Supervised Semantic Segmentation for Building Extraction From High-Resolution Remote Sensing Imagery

Zhang

Xiao

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

A critical obstacle to achieve semantic segmentation of remote sensing images by the deep convolutional neural network is the requirement of huge pixel-level labels. Taking building extraction as an example, this study focuses on how to effectively apply weakly supervised semantic segmentation (WSSS) to highresolution remote sensing (HR) images with image-level labels, which is a prominent solution for the huge labeling challenge. The widely-used two-step WSSS framework is adopted, in which the pseudo-masks are first produced from image-level labels and followed by a segmentation network trained by the pseudo-masks. In addition, the fully connected conditional random field (CRF) is utilized to explore spatial context in both training and prediction stages. Detailed analyses are implemented on applying WSSS on HR images in terms of producing pseudo-masks, training segmentation network, and optimizing predictions. We show that the trade-off between precision and recall of pseudo-masks, as well as the boundary accuracy and the background, needs to be carefully considered. The benefits of the segmentation network in the two-step framework are demonstrated in comparison to using classification network only for WSSS, and the effects of CRF-loss are identified to be powerful for improving the segmentation network while not appropriate for dense buildings. An overlapping strategy and CRF post-processing are further demonstrated to be effective for optimizing the segmentation results during inferencing. Through deliberate settings, we can generate results comparable to fully supervised on the ISPRS Potsdam and Vaihingen dataset, which is meaningful for promoting WSSS applications for extracting geographic information from HR images.

show abstract

Automatic Weakly Supervised Object Detection From High Spatial Resolution Remote Sensing Images via Dynamic Curriculum Learning

Cited by 129 publications

References 35 publications

BAS$^{4}$Net: Boundary-Aware Semi-Supervised Semantic Segmentation Network for Very High Resolution Remote Sensing Images

BAS$^{4}$Net: Boundary-Aware Semi-Supervised Semantic Segmentation Network for Very High Resolution Remote Sensing Images

Convolutional Neural Network Based Weakly Supervised Learning for Aircraft Detection From Remote Sensing Image

On the Effectiveness of Weakly Supervised Semantic Segmentation for Building Extraction From High-Resolution Remote Sensing Imagery

Contact Info

Product

Resources

About