Repaint: Improving the Generalization of Down-Stream Visual Tasks by Generating Multiple Instances of Training Examples
Convolutional Neural Networks (CNNs) for visual tasks are believed to learn both the low-level textures and high-level object attributes, throughout the network depth. This paper further investigates the texture bias' in CNNs. To this end, we regenerate multiple instances of training examples from each original image, through a process we call repainting'. The repainted examples preserve the shape and structure of the regions and objects within the scenes, but diversify their texture and color. Our method can regenerate a same image at different daylight, season, or weather conditions, can have colorization or de-colorization effects, or even bring back some texture information from blacked-out areas. The in-place repaint allows us to further use these repainted examples for improving the generalization of CNNs. Through an extensive set of experiments, we demonstrate the usefulness of the repainted examples in training, for the tasks of image classification (ImageNet) and object detection (COCO), over several state-of-the-art network architectures at different capacities, and across different data availability regimes.
Code (1)
Tasks
Colorizationimage-classificationImage Classificationobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
REPAINT: Knowledge Transfer in Deep Reinforcement Learning
Accelerating learning processes for complex tasks by leveraging previously learned tasks has been one of the most challenging problems in reinforcement learning, especially when the similarity between source and target t…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1Prune and Repaint: Content-Aware Image Retargeting for any Ratio
Image retargeting is the task of adjusting the aspect ratio of images to suit different display devices or presentation environments. However, existing retargeting methods often struggle to balance the preservation of ke…
Image RetargetingVIRES: Video Instance Repainting via Sketch and Text Guided Generation
We introduce VIRES, a video instance repainting method with sketch and text guidance, enabling video instance repainting, replacement, generation, and removal. Existing approaches struggle with temporal consistency and a…
text-guided-generationOn the Generalization of Multi-modal Contrastive Learning
Multi-modal contrastive learning (MMCL) has recently garnered considerable interest due to its superior performance in visual tasks, achieved by embedding multi-modal data, such as visual-language pairs. However, there s…
Contrastive LearningUniCoRN: A Unified Conditional Image Repainting Network
Conditional image repainting (CIR) is an advanced image editing task, which requires the model to generate visual content in user-specified regions conditioned on multiple cross-modality constraints, and composite th…