相关论文: PIE: Physics-inspired Low-light Enhancement

Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training vision encoders to generate image/text representations facilitating various applications. Recently, CLIP has been widely adopted as the vision backbone…

Light adaptation or brightness correction is a key step in improving the contrast and visual appeal of an image. There are multiple light-related tasks (for example, low-light enhancement and exposure correction) and previous studies have…

Due to the nature of enhancement--the absence of paired ground-truth information, high-level vision tasks have been recently employed to evaluate the performance of low-light image enhancement. A widely-used manner is to see how accurately…

Contrast enhancement and noise removal are coupled problems for low-light image enhancement. The existing Retinex based methods do not take the coupling relation into consideration, resulting in under or over-smoothing of the enhanced…

As one of the most effective self-supervised representation learning methods, contrastive learning (CL) relies on multiple negative pairs to contrast against each positive pair. In the standard practice of contrastive learning, data…

The discriminability of feature representation is the key to open-set face recognition. Previous methods rely on the learnable weights of the classification layer that represent the identities. However, the evaluation process learns no…

Low-light image enhancement (LLIE) is a fundamental yet challenging task due to the presence of noise, loss of detail, and poor contrast in images captured under insufficient lighting conditions. Recent methods often rely solely on…

Contrastive Language-Image Pre-training (CLIP) represents the latest incarnation of pre-trained vision-language models. Although CLIP has recently shown its superior power on a wide range of downstream vision-language tasks like Visual…

Current semantic segmentation methods focus only on mining "local" context, i.e., dependencies between pixels within individual images, by context-aggregation modules (e.g., dilated convolution, neural attention) or structure-aware…

Contrastive learning has revolutionized the field of computer vision, learning rich representations from unlabeled data, which generalize well to diverse vision tasks. Consequently, it has become increasingly important to explain these…

On-orbit service is important for maintaining the sustainability of space environment. Space-based visible camera is an economical and lightweight sensor for situation awareness during on-orbit service. However, it can be easily affected by…

Autonomous vehicles and robots often struggle with reliable visual perception at night due to the low illumination and motion blur caused by the long exposure time of RGB cameras. Existing methods address this challenge by sequentially…

Absence of nearby light sources while capturing an image will degrade the visibility and quality of the captured image, making computer vision tasks difficult. In this paper, a color-wise attention network (CWAN) is proposed for low-light…

Contrastive pretraining can substantially increase model generalisation and downstream performance. However, the quality of the learned representations is highly dependent on the data augmentation strategy applied to generate positive…

Large-scale contrastive vision-language pre-training has shown significant progress in visual representation learning. Unlike traditional visual systems trained by a fixed set of discrete labels, a new paradigm was introduced in…

Recent self-supervised models have demonstrated equal or better performance than supervised methods, opening for AI systems to learn visual representations from practically unlimited data. However, these methods are typically…

In computer vision, correcting the exposure level is a fundamental task for enhancing the visual quality of observations with inappropriate lightness. However, existing methodologies tend to be impractical because they lack adaptability to…

Contrastive learning, which aims to capture general representation from unlabeled images to initialize the medical analysis models, has been proven effective in alleviating the high demand for expensive annotations. Current methods mainly…

Existing contrastive language-image pre-training aims to learn a joint representation by matching abundant image-text pairs. However, the number of image-text pairs in medical datasets is usually orders of magnitude smaller than that in…

Recent self-supervised contrastive learning methods greatly benefit from the Siamese structure that aims to minimizing distances between positive pairs. These methods usually apply random data augmentation to input images, expecting the…