Related papers: Curricular Contrastive Regularization for Physics-…

Single-image haze-removal is challenging due to limited information contained in one single image. Previous solutions largely rely on handcrafted priors to compensate for this deficiency. Recent convolutional neural network (CNN) models…

Federated learning is widely used to perform decentralized training of a global model on multiple devices while preserving the data privacy of each device. However, it suffers from heterogeneous local data on each training device which…

Real-scene image super-resolution aims to restore real-world low-resolution images into their high-quality versions. A typical RealSR framework usually includes the optimization of multiple criteria which are designed for different image…

Pursuing realistic results according to human visual perception is the central concern in the image transformation tasks. Perceptual learning approaches like perceptual loss are empirically powerful for such tasks but they usually rely on…

What matters for contrastive learning? We argue that contrastive learning heavily relies on informative features, or "hard" (positive or negative) features. Early works include more informative features by applying complex data…

Supervised neural networks are known to achieve excellent results in various image restoration tasks. However, such training requires datasets composed of pairs of corrupted images and their corresponding ground truth targets.…

Contrastive representation learning has been outstandingly successful in practice. In this work, we identify two key properties related to the contrastive loss: (1) alignment (closeness) of features from positive pairs, and (2) uniformity…

Dense correspondence across semantically related images has been extensively studied, but still faces two challenges: 1) large variations in appearance, scale and pose exist even for objects from the same category, and 2) labeling…

Microscopy images often suffer from high levels of noise, which can hinder further analysis and interpretation. Content-aware image restoration (CARE) methods have been proposed to address this issue, but they often require large amounts of…

This paper presents a whitening-based contrastive learning method for sentence embedding learning (WhitenedCSE), which combines contrastive learning with a novel shuffled group whitening. Generally, contrastive learning pulls distortions of…

We develop a new physical model for the rain effect and show that the well-known atmosphere scattering model (ASM) for the haze effect naturally emerges as its homogeneous continuous limit. Via depth-aware fusion of multi-layer rain streaks…

Detecting critical transitions in complex, noisy time-series data is a fundamental challenge across science and engineering. Such transitions may be anticipated by the emergence of a low-dimensional order parameter, whose signature is often…

Batch normalization (BN) is a ubiquitous technique for training deep neural networks that accelerates their convergence to reach higher accuracy. However, we demonstrate that BN comes with a fundamental drawback: it incentivizes the model…

Recently, the contrastive learning paradigm has achieved remarkable success in high-level tasks such as classification, detection, and segmentation. However, contrastive learning applied in low-level tasks, like image restoration, is…

Contrastive learning between different views of the data achieves outstanding success in the field of self-supervised representation learning and the learned representations are useful in broad downstream tasks. Since all supervision…

We present a comprehensive study and evaluation of existing single image dehazing algorithms, using a new large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single Image DEhazing (RESIDE). RESIDE…

Modeling statistical regularity plays an essential role in ill-posed image processing problems. Recently, deep learning based methods have been presented to implicitly learn statistical representation of pixel distributions in natural…

Model-based single image dehazing algorithms restore haze-free images with sharp edges and rich details for real-world hazy images at the expense of low PSNR and SSIM values for synthetic hazy images. Data-driven ones restore haze-free…

Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. However, these methods implicitly assume a particular set of…

The high efficiency in computation and storage makes hashing (including binary hashing and quantization) a common strategy in large-scale retrieval systems. To alleviate the reliance on expensive annotations, unsupervised deep hashing…