K He, H Fan, Y Wu, S Xie… - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
Abstract We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning as dictionary look-up, we build a …
Self-supervised learning aims to learn representations from the data itself without explicit manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning-the …
S Tukra, F Hoffman, K Chatfield - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
We present an extension to masked autoencoders (MAE) which improves on the representations learnt by the model by explicitly encouraging the learning of higher scene …
Fine-grained and instance-level recognition methods are commonly trained and evaluated on specific domains, in a model per domain scenario. Such an approach, however, is …
The success of deep neural networks often relies on a large amount of labeled examples, which can be difficult to obtain in many real scenarios. To address this challenge …
Contrastive self-supervised learning has emerged as a promising approach to unsupervised visual representation learning. In general, these methods learn global (image-level) …
Self-supervised learning based on instance discrimination has shown remarkable progress. In particular, contrastive learning, which regards each image as well as its augmentations as …
Representation learning promises to unlock deep learning for the long tail of vision tasks without expensive labelled datasets. Yet, the absence of a unified evaluation for general …
We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra-and inter-modal similarity preservation objectives. Unlike …