Self-Supervised Dense Consistency Regularization for Image-to-Image Translation
Unsupervised image-to-image translation has gained considerable attention due to the recent impressive progress based on generative adversarial networks (GANs). In this paper, we present a simple but effective regularization technique for improving GAN-based image-to-image translation. To generate images with realistic local semantics and structures, we suggest to use an auxiliary self-supervised loss, enforcing point-wise consistency of the overlapped region between a pair of patches cropped from a single real image during training discriminators of GAN. Our experiment shows that the dense consistency regularization improves performance substantially on various image-to-image translation scenarios. It also achieves extra performance gains by using jointly with recent instance-level regularization methods. Furthermore, we verify that the proposed model captures domain-specific characteristics more effectively with only small fraction of training data.
Code (0)
등록된 구현이 없습니다.
Tasks
Image-to-Image TranslationTranslationUnsupervised Image-To-Image TranslationSimilar Papers 제목 키워드 기반
Self-supervised 360$^{\circ}$ Room Layout Estimation
We present the first self-supervised method to train panoramic room layout estimation models without any labeled data. Unlike per-pixel dense depth that provides abundant correspondence constraints, layout representation…
Active LearningRoom Layout EstimationConsistency Regularization for Deep Face Anti-Spoofing
Face anti-spoofing (FAS) plays a crucial role in securing face recognition systems. Empirically, given an image, a model with more consistent output on different views of this image usually performs better, as shown in F…
Face Anti-SpoofingFace RecognitionIDEAL: Improved DEnse locAL Contrastive Learning for Semi-Supervised Medical Image Segmentation
Due to the scarcity of labeled data, Contrastive Self-Supervised Learning (SSL) frameworks have lately shown great potential in several medical image analysis tasks. However, the existing contrastive mechanisms are sub-o…
Contrastive LearningImage SegmentationMedical Image AnalysisMedical Image Segmentation+6Adaptively Weighted Data Augmentation Consistency Regularization for Robust Optimization under Concept Shift
Concept shift is a prevailing problem in natural tasks like medical image segmentation where samples usually come from different subpopulations with variant correlations between features and labels. One common type of co…
Data AugmentationImage SegmentationMedical Image SegmentationSegmentation+2Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation
Inferring geometrically consistent dense 3D scenes across a tuple of temporally consecutive images remains challenging for self-supervised monocular depth prediction pipelines. This paper explores how the increasingly po…
Depth EstimationDepth PredictionMonocular Depth Estimation