相关论文: Cycle Contrastive Adversarial Learning for Unsuper…

Image deraining is a typical low-level image restoration task, which aims at decomposing the rainy image into two distinguishable layers: the clean image layer and the rain layer. Most of the existing learning-based deraining methods are…

Most of the existing learning-based deraining methods are supervisedly trained on synthetic rainy-clean pairs. The domain gap between the synthetic and real rain makes them less generalized to complex real rainy scenes. Moreover, the…

Learning single image deraining (SID) networks from an unpaired set of clean and rainy images is practical and valuable as acquiring paired real-world data is almost infeasible. However, without the paired data as the supervision, learning…

Getting rid of the fundamental limitations in fitting to the paired training data, recent unsupervised low-light enhancement methods excel in adjusting illumination and contrast of images. However, for unsupervised low light enhancement,…

Single image deraining (SID) is an important and challenging topic in emerging vision applications, and most of emerged deraining methods are supervised relying on the ground truth (i.e., paired images) in recent years. However, in practice…

We present Cycle-Contrastive Learning (CCL), a novel self-supervised method for learning video representation. Following a nature that there is a belong and inclusion relation of video and its frames, CCL is designed to find correspondences…

Generative Adversarial Networks (GANs) have facilitated a new direction to tackle the image-to-image transformation problem. Different GANs use generator and discriminator networks with different losses in the objective function. Still…

Convolutional neural networks (CNNs) have achieved superhuman performance in multiple vision tasks, especially image classification. However, unlike humans, CNNs leverage spurious features, such as background information to make decisions.…

Severe weather conditions such as rain and snow adversely affect the visual quality of images captured under such conditions thus rendering them useless for further usage and sharing. In addition, such degraded images drastically affect…

Ensuring the realism of computer-generated synthetic images is crucial to deep neural network (DNN) training. Due to different semantic distributions between synthetic and real-world captured datasets, there exists semantic mismatch between…

Recently, deep image deraining models based on paired datasets have made a series of remarkable progress. However, they cannot be well applied in real-world applications due to the difficulty of obtaining real paired datasets and the poor…

Recently, the cycle-consistent generative adversarial networks (CycleGAN) has been widely used for synthesis of multi-domain medical images. The domain-specific nonlinear deformations captured by CycleGAN make the synthesized images…

Existing approaches for restoring weather-degraded images follow a fully-supervised paradigm and they require paired data for training. However, collecting paired data for weather degradations is extremely challenging, and existing methods…

Rain streaks significantly decrease the visibility of captured images and are also a stumbling block that restricts the performance of subsequent computer vision applications. The existing deep learning-based image deraining methods employ…

Disentanglement, a critical concern in interpretable machine learning, has also garnered significant attention from the computer vision community. Many existing GAN-based class disentanglement (unsupervised) approaches, such as InfoGAN and…

Deep Neural Networks have recently demonstrated promising performance in binary change detection (CD) problems in remote sensing (RS), requiring a large amount of labeled multitemporal training samples. Since collecting such data is…

While the wisdom of training an image dehazing model on synthetic hazy data can alleviate the difficulty of collecting real-world hazy/clean image pairs, it brings the well-known domain shift problem. From a different yet new perspective,…

Most existing single image deraining methods require learning supervised models from a large set of paired synthetic training data, which limits their generality, scalability and practicality in real-world multimedia applications. Besides,…

Contrastive learning (CL) is a popular technique for self-supervised learning (SSL) of visual representations. It uses pairs of augmentations of unlabeled training examples to define a classification task for pretext learning of a deep…

Removing the rain streaks from single image is still a challenging task, since the shapes and directions of rain streaks in the synthetic datasets are very different from real images. Although supervised deep deraining networks have…