Related papers: Unsupervised Deraining: Where Asymmetric Contrasti…

Removing rain effects from an image is of importance for various applications such as autonomous driving, drone piloting, and photo editing. Conventional methods rely on some heuristics to handcraft various priors to remove or separate the…

It is challenging to remove rain-steaks from a single rainy image because the rain steaks are spatially varying in the rainy image. Although the CNN based methods have reported promising performance recently, there are still some defects,…

Recently, large-scale Contrastive Language-Image Pre-training (CLIP) has attracted unprecedented attention for its impressive zero-shot recognition ability and excellent transferability to downstream tasks. However, CLIP is quite…

This paper introduces a novel unsupervised approach for image deblurring that utilizes a simple process for training data collection, thereby enhancing the applicability and effectiveness of deblurring methods. Our technique does not…

Existing deep-learning-based methods for nighttime video deraining rely on synthetic data due to the absence of real-world paired data. However, the intricacies of the real world, particularly with the presence of light effects and…

Removing rain streaks from a single image has been drawing considerable attention as rain streaks can severely degrade the image quality and affect the performance of existing outdoor vision tasks. While recent CNN-based derainers have…

Self-training and contrastive learning have emerged as leading techniques for incorporating unlabeled data, both under distribution shift (unsupervised domain adaptation) and when it is absent (semi-supervised learning). However, despite…

A prominent technique for self-supervised representation learning has been to contrast semantically similar and dissimilar pairs of samples. Without access to labels, dissimilar (negative) points are typically taken to be randomly sampled…

Noise contrastive learning is a popular technique for unsupervised representation learning. In this approach, a representation is obtained via reduction to supervised learning, where given a notion of semantic similarity, the learner tries…

Distance-based anomaly detection methods rely on compact in-distribution (ID) embeddings that are well separated from anomalies. However, conventional contrastive learning strategies often struggle to achieve this balance, either promoting…

Self-supervised contrastive learning (CL) has achieved remarkable empirical success, often producing representations that rival supervised pre-training on downstream tasks. Recent theory explains this by showing that the CL loss closely…

We propose Graph Contrastive Learning (GraphCL), a general framework for learning node representations in a self supervised manner. GraphCL learns node embeddings by maximizing the similarity between the representations of two randomly…

Contrastive representation learning has been recently proved to be very efficient for self-supervised training. These methods have been successfully used to train encoders which perform comparably to supervised training on downstream…

Shadows are frequently encountered natural phenomena that significantly hinder the performance of computer vision perception systems in practical settings, e.g., autonomous driving. A solution to this would be to eliminate shadow regions…

Contrastive learning has recently emerged as a promising approach for learning data representations that discover and disentangle the explanatory factors of the data. Previous analyses of such approaches have largely focused on individual…

Self-supervised learning (SSL) approaches have brought tremendous success across many tasks and domains. It has been argued that these successes can be attributed to a link between SSL and identifiable representation learning: Temporal…

We propose RainyScape, an unsupervised framework for reconstructing clean scenes from a collection of multi-view rainy images. RainyScape consists of two main modules: a neural rendering module and a rain-prediction module that incorporates…

We introduce in this paper a new statistical perspective, exploiting the Jaccard similarity metric, as a measure-based metric to effectively invoke non-linear features in the loss of self-supervised contrastive learning. Specifically, our…

Differentially private (DP) contrastive learning aims to learn general-purpose representations from sensitive data, alleviating the privacy leakage concerns of organizations deploying or sharing embedding models trained on private user…

Satellite imagery is being leveraged for many societally critical tasks across climate, economics, and public health. Yet, because of heterogeneity in landscapes (e.g. how a road looks in different places), models can show disparate…