相关论文: Learning Image Relations with Contrast Association…

We introduce a novel method for representation learning that uses an artificial supervision signal based on counting visual primitives. This supervision signal is obtained from an equivariance relation, which does not require any manual…

Contrastive learning relies on an assumption that positive pairs contain related views, e.g., patches of an image or co-occurring multimodal signals of a video, that share certain underlying information about an instance. But what if this…

Graph-level contrastive learning, aiming to learn the representations for each graph by contrasting two augmented graphs, has attracted considerable attention. Previous studies usually simply assume that a graph and its augmented graph as a…

Ensembles of Convolutional neural networks have shown remarkable results in learning discriminative semantic features for image classification tasks. Though, the models in the ensemble often concentrate on similar regions in images. This…

Recent methods for deep metric learning have been focusing on designing different contrastive loss functions between positive and negative pairs of samples so that the learned feature embedding is able to pull positive samples of the same…

We introduce a new family of neural network models called Convolutional Dynamic Alignment Networks (CoDA Nets), which are performant classifiers with a high degree of inherent interpretability. Their core building blocks are Dynamic…

Rich semantic relations are important in a variety of visual recognition problems. As a concrete example, group activity recognition involves the interactions and relative spatial relations of a set of people in a scene. State of the art…

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…

We capitalize on large amounts of readily-available, synchronous data to learn a deep discriminative representations shared across three major natural modalities: vision, sound and language. By leveraging over a year of sound from video and…

Self-supervised representation learning is a critical problem in computer vision, as it provides a way to pretrain feature extractors on large unlabeled datasets that can be used as an initialization for more efficient and effective…

Self-supervised pre-training of deep learning models with contrastive learning is a widely used technique in image analysis. Current findings indicate a strong potential for contrastive pre-training on medical images. However, further…

Facial expressions are combinations of basic components called Action Units (AU). Recognizing AUs is key for developing general facial expression analysis. In recent years, most efforts in automatic AU recognition have been dedicated to…

Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and…

In image-to-image translation, each patch in the output should reflect the content of the corresponding patch in the input, independent of domain. We propose a straightforward method for doing so -- maximizing mutual information between the…

Various state-of-the-art self-supervised visual representation learning approaches take advantage of data from multiple sensors by aligning the feature representations across views and/or modalities. In this work, we investigate how…

Visual interest & affect prediction is a very interesting area of research in the area of computer vision. In this paper, we propose a transfer learning and attention mechanism based neural network model to predict visual interest &…

Machine unlearning (MU) aims to remove the influence of specific "forget" data from a trained model while preserving its knowledge of the remaining "retain" data. Existing MU methods based on label manipulation or model weight perturbations…

Instance-level Image Retrieval (IIR), or simply Instance Retrieval, deals with the problem of finding all the images within an dataset that contain a query instance (e.g. an object). This paper makes the first attempt that tackles this…

Representation learning has significantly been developed with the advance of contrastive learning methods. Most of those methods have benefited from various data augmentations that are carefully designated to maintain their identities so…

Understanding convergent learning -- the degree to which independently trained neural systems -- whether multiple artificial networks or brains and models -- arrive at similar internal representations -- is crucial for both neuroscience and…