SAENet: Self-Supervised Adversarial and Equivariant Network for Weakly Supervised Object Detection in Remote Sensing Images

Feng, Xiao; Yao, Xiwen; Cheng, Gong; Han, Jungong; Han, Junwei

doi:10.1109/tgrs.2021.3105575

Cited by 24 publications

(16 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transformation invariant learning applies perturbations to an input image x to obtain x and minimizes the difference between the output predictions f (x) and f (x ). It is widely adopted in semi-supervised learning [34,35,36,37,38,39] and weakly supervised learning [40,41,42]. In the area of FSOD, TIP [21] introduces consistency regularization on predictions from various transformed images.…”

Section: Transformation Invariant Learningmentioning

confidence: 99%

Few-Shot Object Detection on Remote Sensing Images

Deng

Fang

2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Object detection in remote sensing images relies on a large amount of labeled data for training. The growing new categories and class imbalance render exhaustive annotation nonscalable. Few-shot object detection (FSOD) tackles this issue by meta-learning on seen base classes and then fine-tuning on novel classes with few labeled samples. However, the object's scale and orientation variations are particularly large in remote sensing images, thus posing challenges to existing few-shot object detection methods. To tackle these challenges, we first propose to integrate a feature pyramid network and use prototype features to highlight query features to improve upon existing FSOD methods. We refer to the modified FSOD as a Strong Baseline which is demonstrated to perform significantly better than the original baselines. To improve the robustness of orientation variation, we further propose a transformation-invariant network (TINet) to allow the network to be invariant to geometric transformations. Extensive experiments on three widely used remote sensing object detection datasets, i.e., NWPU VHR-10.v2, DIOR, and HRRSD demonstrated the effectiveness of the proposed method. Finally, we reproduced multiple FSOD methods for remote sensing images to create an extensive benchmark for follow-up works.

show abstract

Section: Transformation Invariant Learningmentioning

confidence: 99%

Few-Shot Object Detection on Remote Sensing Images

Deng

Fang

2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The second module captures the instance-level discriminative cues by leveraging the semantic discrepancy of the local context, thus distinguishing better adjacent instances and addressing the density problem. This network was further improved with the development of SAENet [49], which exploits an adversarial dropout-activation block to solve the discriminative region problem. The authors address the fact that most state-of-the-art methods ignore the consistency across different spatial transformations of the same image, causing them to be labeled differently.…”

Section: Mil-basedmentioning

confidence: 99%

Weakly Supervised Object Detection for Remote Sensing Images: A Survey

et al. 2022

View full text Add to dashboard Cite

The rapid development of remote sensing technologies and the availability of many satellite and aerial sensors have boosted the collection of large volumes of high-resolution images, promoting progress in a wide range of applications. As a consequence, Object detection (OD) in aerial images has gained much interest in the last few years. However, the development of object detectors requires a massive amount of carefully labeled data. Since annotating datasets is very time-consuming and may require expert knowledge, a consistent number of weakly supervised object localization (WSOL) and detection (WSOD) methods have been developed. These approaches exploit only coarse-grained metadata, typically whole image labels, to train object detectors. However, many challenges remain open due to the missing location information in the training process of WSOD approaches and to the complexity of remote sensing images. Furthermore, methods studied for natural images may not be directly applicable to remote sensing images (RSI) and may require carefully designed adaptations. This work provides a comprehensive survey of the recent achievements of remote sensing weakly supervised object detection (RSWSOD). An analysis of the challenges related to RSWSOD is presented, the advanced techniques developed to improve WSOD are summarized, the available benchmarking datasets are described and a discussion of future directions of RSWSOD research is provided.

show abstract

“…Inaccurate supervision means that the training data only gives coarse-grained object labels, which is inconsistent with the task. Feng et al [56] provides a robust self-supervised adversarial and equivariant network (SAENet) to learn complementary and consistent visual patterns for weakly supervised object detector. Differing from fine-grained object interpretation, inaccurate supervision refers to multi-instance learning [57]- [59] which takes a multi-instance package as the training unit.…”

Section: Weakly Supervised Learning Algorithmmentioning

confidence: 99%

Weakly Supervised Part-Based Method for Combined Object Detection in Remote Sensing Imagery

Qian

Yan

Zhu

et al. 2022

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

View full text Add to dashboard Cite

Deep learning methods have reached considerable achievement on remote sensing object detection in recent years. However, most methods are designed for single object detection, such as vehicles and ships, and have limited detection capabilities for the combined object with large scale and complex part structure. In this paper, we propose a Part-based Topology Distillation Network (PTDNet) for accurate and efficient combined object detection in remote sensing imagery. Specifically, a Part-based Feature Module (PFM) is designed to extract the key parts information of combined object in a weakly supervised manner. Besides, to balance the accuracy and efficiency of the model, with considering the topology structure of multiple parts in combined objects, a lightweight network training method based on partial topological feature distillation is proposed to improve the model performance without additional parameters. Experiments show that the PTDNet outperforms the state-of-the-art methods and achieves 65.4% mAP and 84.1% accuracy for combined object detection.

show abstract

SAENet: Self-Supervised Adversarial and Equivariant Network for Weakly Supervised Object Detection in Remote Sensing Images

Cited by 24 publications

References 44 publications

Few-Shot Object Detection on Remote Sensing Images

Few-Shot Object Detection on Remote Sensing Images

Weakly Supervised Object Detection for Remote Sensing Images: A Survey

Weakly Supervised Part-Based Method for Combined Object Detection in Remote Sensing Imagery

Contact Info

Product

Resources

About