Related papers: CoNe: Contrast Your Neighbours for Supervised Imag…

Image colourisation is an ill-posed problem, with multiple correct solutions which depend on the context and object instances present in the input datum. Previous approaches attacked the problem either by requiring intense user interactions…

Supervised contrastive learning (SupCon) is widely used to shape representations, but has seen limited targeted study for audio deepfake detection. Existing work typically combines contrastive terms with broader pipelines; however, the…

Recently, contrastive learning attracts increasing interests in neural text generation as a new solution to alleviate the exposure bias problem. It introduces a sequence-level training signal which is crucial to generation tasks that always…

Convolutional Neural Networks (CNNs) have advanced significantly in visual representation learning and recognition. However, they face notable challenges in performance and computational efficiency when dealing with real-world, multi-scale…

The objective of this paper is visual-only self-supervised video representation learning. We make the following contributions: (i) we investigate the benefit of adding semantic-class positives to instance-based Info Noise Contrastive…

We consider the problem of obtaining image quality representations in a self-supervised manner. We use prediction of distortion type and degree as an auxiliary task to learn features from an unlabeled image dataset containing a mixture of…

An increasing number of applications in computer vision, specially, in medical imaging and remote sensing, become challenging when the goal is to classify very large images with tiny informative objects. Specifically, these classification…

Previous endeavors in self-supervised learning have enlightened the research of deep clustering from an instance discrimination perspective. Built upon this foundation, recent studies further highlight the importance of grouping…

Unsupervised image representations have significantly reduced the gap with supervised pretraining, notably with the recent achievements of contrastive learning methods. These contrastive methods typically work online and rely on a large…

Neural network compression empowers the effective yet unwieldy deep convolutional neural networks (CNN) to be deployed in resource-constrained scenarios. Most state-of-the-art approaches prune the model in filter-level according to the…

The deep learning technique was used to increase the performance of single image super-resolution (SISR). However, most existing CNN-based SISR approaches primarily focus on establishing deeper or larger networks to extract more significant…

Convolutional Neural Networks have achieved significant success across multiple computer vision tasks. However, they are vulnerable to carefully crafted, human-imperceptible adversarial noise patterns which constrain their deployment in…

Face manipulation techniques develop rapidly and arouse widespread public concerns. Despite that vanilla convolutional neural networks achieve acceptable performance, they suffer from the overfitting issue. To relieve this issue, there is a…

Self-supervised learning has been widely used to obtain transferrable representations from unlabeled images. Especially, recent contrastive learning methods have shown impressive performances on downstream image classification tasks. While…

Contrastive learning predicts whether two images belong to the same category by training a model to make their feature representations as close or as far away as possible. In this paper, we rethink how to mine samples in contrastive…

Chromosome recognition is an essential task in karyotyping, which plays a vital role in birth defect diagnosis and biomedical research. However, existing classification methods face significant challenges due to the inter-class similarity…

Standard deep learning models for image segmentation cannot guarantee topology accuracy, failing to preserve the correct number of connected components or structures. This, in turn, affects the quality of the segmentations and compromises…

We propose Cos R-CNN, a simple exemplar-based R-CNN formulation that is designed for online few-shot object detection. That is, it is able to localise and classify novel object categories in images with few examples without fine-tuning. Cos…

In contemporary self-supervised contrastive algorithms like SimCLR, MoCo, etc., the task of balancing attraction between two semantically similar samples and repulsion between two samples of different classes is primarily affected by the…

We study the problem of user segmentation: given a set of users and one or more predefined groups or segments, assign users to their corresponding segments. As an example, for a segment indicating particular interest in a certain area of…