Related papers: Multi-Domain Features Guided Supervised Contrastiv…

Point cloud data plays an essential role in robotics and self-driving applications. Yet, annotating point cloud data is time-consuming and nontrivial while they enable learning discriminative 3D representations that empower downstream…

Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting. Contrastive learning has recently shown its promising representation learning capability in…

Semantic overlap among land-cover categories, highly imbalanced label distributions, and complex inter-class co-occurrence patterns constitute significant challenges for multi-label remote-sensing image retrieval. In this article,…

Contrastive learning has emerged as a powerful method in deep learning, excelling at learning effective representations through contrasting samples from different distributions. However, dimensional collapse, where embeddings converge into…

Forward-looking ground-penetrating radar (FLGPR) has recently been investigated as a remote sensing modality for buried target detection (e.g., landmines). In this context, raw FLGPR data is beamformed into images and then computerized…

Supervised contrastive learning (SCL) frameworks treat each class as independent and thus consider all classes to be equally important. This neglects the common scenario in which label hierarchy exists, where fine-grained classes under the…

Real-world data often exhibits long tail distributions with heavy class imbalance, where the majority classes can dominate the training process and alter the decision boundaries of the minority classes. Recently, researchers have…

To alleviate the cost of collecting and annotating large-scale point cloud datasets, we propose an unsupervised learning approach to learn features from unlabeled point cloud "3D object" dataset by using part contrasting and object…

In object re-identification (ReID), the development of deep learning techniques often involves model updates and deployment. It is unbearable to re-embedding and re-index with the system suspended when deploying new models. Therefore,…

During the past decade, deep neural networks have led to fast-paced progress and significant achievements in computer vision problems, for both academia and industry. Yet despite their success, state-of-the-art image classification…

Assigning consistent temporal identifiers to multiple moving objects in a video sequence is a challenging problem. A solution to that problem would have immediate ramifications in multiple object tracking and segmentation problems. We…

Implicit degradation modeling-based blind super-resolution (SR) has attracted more increasing attention in the community due to its excellent generalization to complex degradation scenarios and wide application range. How to extract more…

Medical image segmentation has been widely recognized as a pivot procedure for clinical diagnosis, analysis, and treatment planning. However, the laborious and expensive annotation process lags down the speed of further advances.…

The accurate characterization of the severity of the wildfire event strongly contributes to the characterization of the fuel conditions in fire-prone areas, and provides valuable information for disaster response. The aim of this study is…

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…

Deep learning models are modern tools for spatio-temporal graph (STG) forecasting. Though successful, we argue that data scarcity is a key factor limiting their recent improvements. Meanwhile, contrastive learning has been an effective…

Semi-supervised domain generalization (SSDG) aims to solve the problem of generalizing to out-of-distribution data when only a few labels are available. Due to label scarcity, applying domain generalization methods often underperform.…

Discriminative representation is crucial for the association step in multi-object tracking. Recent work mainly utilizes features in single or neighboring frames for constructing metric loss and empowering networks to extract representation…

Selecting subsets of features that differentiate between two conditions is a key task in a broad range of scientific domains. In many applications, the features of interest form clusters with similar effects on the data at hand. To recover…

To bridge the gap between the source and target domains in unsupervised domain adaptation (UDA), the most common strategy puts focus on matching the marginal distributions in the feature space through adversarial learning. However, such…