Weakly- and Self-Supervised Learning for Content-Aware Deep Image Retargeting
This paper proposes a weakly- and self-supervised deep convolutional neural network (WSSDCNN) for content-aware image retargeting. Our network takes a source image and a target aspect ratio, and then directly outputs a retargeted image. Retargeting is performed through a shift map, which is a pixel-wise mapping from the source to the target grid. Our method implicitly learns an attention map, which leads to a content-aware shift map for image retargeting. As a result, discriminative parts in an image are preserved, while background regions are adjusted seamlessly. In the training phase, pairs of an image and its image-level annotation are used to compute content and structure losses. We demonstrate the effectiveness of our proposed method for a retargeting application with insightful analyses.
Code (2)
Tasks
Image RetargetingSelf-Supervised LearningSimilar Papers 제목 키워드 기반
Robust Self-Supervised Cross-Modal Super-Resolution against Real-World Misaligned Observations
Cross-modal super-resolution (SR) on real-world misaligned data is challenging, as only unlabeled low-resolution (LR) source and high-resolution (HR) guide images with complex spatial misalignment are available. Previous…
Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning
As advanced image manipulation techniques emerge, detecting the manipulation becomes increasingly important. Despite the success of recent learning-based approaches for image manipulation detection, they typically requir…
Image ManipulationImage Manipulation DetectionPseudo LabelWeakly and Self-Supervised Class-Agnostic Motion Prediction for Autonomous Driving
Understanding motion in dynamic environments is critical for autonomous driving, thereby motivating research on class-agnostic motion prediction. In this work, we investigate weakly and self-supervised class-agnostic mot…
Self-Supervised LearningAutonomous DrivingScene ParsingPoint CloudsCategory-aware Allocation Transformer for Weakly Supervised Object Localization
Weakly supervised object localization (WSOL) aims to localize objects based on only image-level labels as supervision. Recently, transformers have been introduced into WSOL, yielding impressive results. The self-atte…
ObjectObject LocalizationWeakly-Supervised Object LocalizationEnhancing Weakly Supervised 3D Medical Image Segmentation through Probabilistic-aware Learning
3D medical image segmentation is a challenging task with crucial implications for disease diagnosis and treatment planning. Recent advances in deep learning have significantly enhanced fully supervised medical image segm…
Image SegmentationMedical Image SegmentationPseudo LabelSegmentation+2