Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and Beyond
We propose 'Hide-and-Seek' a general purpose data augmentation technique, which is complementary to existing data augmentation techniques and is beneficial for various visual recognition tasks. The key idea is to hide patches in a training image randomly, in order to force the network to seek other relevant content when the most discriminative content is hidden. Our approach only needs to modify the input image and can work with any network to improve its performance. During testing, it does not need to hide any patches. The main advantage of Hide-and-Seek over existing data augmentation techniques is its ability to improve object localization accuracy in the weakly-supervised setting, and we therefore use this task to motivate the approach. However, Hide-and-Seek is not tied only to the image localization task, and can generalize to other forms of visual input like videos, as well as other recognition tasks like image classification, temporal action localization, semantic segmentation, emotion recognition, age/gender estimation, and person re-identification. We perform extensive experiments to showcase the advantage of Hide-and-Seek on these various visual recognition problems.
Code (2)
Tasks
Action LocalizationData AugmentationEmotion Recognitionimage-classificationImage ClassificationObject LocalizationPerson Re-IdentificationSemantic SegmentationTemporal Action LocalizationSimilar Papers 제목 키워드 기반
Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization
We propose `Hide-and-Seek', a weakly-supervised framework that aims to improve object localization in images and action localization in videos. Most existing weakly-supervised methods localize only the most discriminativ…
Action LocalizationObjectObject LocalizationWeakly Supervised Action Localization+1Hide-and-Seek Attribution: Weakly Supervised Segmentation of Vertebral Metastases in CT
Accurate segmentation of vertebral metastasis in CT is clinically important yet difficult to scale, as voxel-level annotations are scarce and both lytic and blastic lesions often resemble benign degenerative changes. We …
Hide-and-Seek Privacy Challenge
The clinical time-series setting poses a unique combination of challenges to data modeling and sharing. Due to the high dimensionality of clinical time series, adequate de-identification to preserve privacy while retaini…
De-identificationSynthetic Data GenerationTime SeriesTime Series AnalysisHide&Seek: Learning to Explain in an End-to-End Differentiable Network
Instance-wise feature selection is a valuable tool for interpreting labeled data and the predictions of black-box models. In contrast to global feature selection techniques, instance-wise methods dynamically identify imp…
A Fusion-Denoising Attack on InstaHide with Data Augmentation
InstaHide is a state-of-the-art mechanism for protecting private training images, by mixing multiple private images and modifying them such that their visual features are indistinguishable to the naked eye. In recent wor…
Data AugmentationDenoising