Related papers: Propagate Yourself: Exploring Pixel-Level Consiste…

To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and…

Recent advances in self-supervised contrastive learning yield good image-level representation, which favors classification tasks but usually neglects pixel-level detailed information, leading to unsatisfactory transfer performance to dense…

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…

Unsupervised contrastive learning achieves great success in learning image representations with CNN. Unlike most recent methods that focused on improving accuracy of image classification, we present a novel contrastive learning approach,…

Image-level contrastive representation learning has proven to be highly effective as a generic model for transfer learning. Such generality for transfer learning, however, sacrifices specificity if we are interested in a certain downstream…

Self-supervised pretraining has been shown to yield powerful representations for transfer learning. These performance gains come at a large computational cost however, with state-of-the-art methods requiring an order of magnitude more…

The prior self-supervised learning researches mainly select image-level instance discrimination as pretext task. It achieves a fantastic classification performance that is comparable to supervised learning methods. However, with degraded…

Unsupervised learning methods based on contrastive learning have drawn increasing attention and achieved promising results. Most of them aim to learn representations invariant to instance-level variations, which are provided by different…

Tremendous progress has been made in visual representation learning, notably with the recent success of self-supervised contrastive learning methods. Supervised contrastive learning has also been shown to outperform its cross-entropy…

In this work, we present Multi-Level Contrastive Learning for Dense Prediction Task (MCL), an efficient self-supervised method for learning region-level feature representation for dense prediction tasks. Our method is motivated by the three…

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…

Contrastive self-supervised learning has emerged as a promising approach to unsupervised visual representation learning. In general, these methods learn global (image-level) representations that are invariant to different views (i.e.,…

Self-supervised representation learning for visual pre-training has achieved remarkable success with sample (instance or pixel) discrimination and semantics discovery of instance, whereas there still exists a non-negligible gap between…

Feature representation via self-supervised learning has reached remarkable success in image-level contrastive learning, which brings impressive performances on image classification tasks. While image-level feature representation mainly…

The goal of self-supervised visual representation learning is to learn strong, transferable image representations, with the majority of research focusing on object or scene level. On the other hand, representation learning at part level has…

Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this…

Visual domain gaps often impact object detection performance. Image-to-image translation can mitigate this effect, where contrastive approaches enable learning of the image-to-image mapping under unsupervised regimes. However, existing…

The use of pretrained deep neural networks represents an attractive way to achieve strong results with few data available. When specialized in dense problems such as object detection, learning local rather than global information in images…

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 existing visual pre-training methods, which solve a proxy…

We present a new self-supervised pre-training of Vision Transformers for dense prediction tasks. It is based on a contrastive loss across views that compares pixel-level representations to global image representations. This strategy…