Related papers: CSP: Self-Supervised Contrastive Spatial Pre-Train…

Contrastive representation learning has proven to be an effective self-supervised learning method for images and videos. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as…

Semi-supervised learning is attracting blooming attention, due to its success in combining unlabeled data. However, pseudo-labeling-based semi-supervised approaches suffer from two problems in image classification: (1) Existing methods…

Video scene parsing incorporates temporal information, which can enhance the consistency and accuracy of predictions compared to image scene parsing. The added temporal dimension enables a more comprehensive understanding of the scene,…

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…

Training convolutional networks for semantic segmentation with strong (per-pixel) and weak (per-bounding-box) supervision requires a large amount of weakly labeled data. We propose two methods for selecting the most relevant data with weak…

Supervised deep learning-based methods yield accurate results for medical image segmentation. However, they require large labeled datasets for this, and obtaining them is a laborious task that requires clinical expertise.…

Contrastive learning has delivered impressive results for various tasks in the self-supervised regime. However, existing approaches optimize for learning representations specific to downstream scenarios, i.e., \textit{global}…

Self-supervised learning has emerged as a powerful way to pre-train generalizable machine learning models on large amounts of unlabeled data. It is particularly compelling in the music domain, where obtaining labeled data is time-consuming,…

Self-supervised contrastive representation learning has proved incredibly successful in the vision and natural language domains, enabling state-of-the-art performance with orders of magnitude less labeled data. However, such methods are…

Semantic segmentation models struggle to generalize in the presence of domain shift. In this paper, we introduce contrastive learning for feature alignment in cross-domain adaptation. We assemble both in-domain contrastive pairs and…

Fine-grained image classification involves identifying different subcategories of a class which possess very subtle discriminatory features. Fine-grained datasets usually provide bounding box annotations along with class labels to aid the…

Contemporary transfer learning-based methods to alleviate the data insufficiency in change detection (CD) are mainly based on ImageNet pre-training. Self-supervised learning (SSL) has recently been introduced to remote sensing (RS) for…

Self-supervised pre-training based on next-token prediction has enabled large language models to capture the underlying structure of text, and has led to unprecedented performance on a large array of tasks when applied at scale. Similarly,…

Vision-language models such as CLIP are capable of mapping the different modality data into a unified feature space, enabling zero/few-shot inference by measuring the similarity of given images and texts. However, most existing methods…

In standard supervised machine learning, it is necessary to provide a label for every input in the data. While raw data in many application domains is easily obtainable on the Internet, manual labelling of this data is prohibitively…

Stochastic neighbor embedding (SNE) methods $t$-SNE, UMAP are two most popular dimensionality reduction methods for data visualization. Contrastive learning, especially self-supervised contrastive learning (SSCL), has showed great success…

Learning representations for individual instances when only bag-level labels are available is a fundamental challenge in multiple instance learning (MIL). Recent works have shown promising results using contrastive self-supervised learning…

Learning Based Robot Grasping currently involves the use of labeled data. This approach has two major disadvantages. Firstly, labeling data for grasp points and angles is a strenuous process, so the dataset remains limited. Secondly, human…

With the rapid development of artificial intelligence, multimodal learning has become an important research area. For intelligent agents, the state is a crucial modality to convey precise information alongside common modalities like images,…

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…