Related papers: Self-Supervised Pre-Training Boosts Semantic Scene…

Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own. This is particularly…

Satellite image time series (SITS) segmentation is crucial for many applications like environmental monitoring, land cover mapping and agricultural crop type classification. However, training models for SITS segmentation remains a…

Outdoor scene completion is a challenging issue in 3D scene understanding, which plays an important role in intelligent robotics and autonomous driving. Due to the sparsity of LiDAR acquisition, it is far more complex for 3D scene…

There are two challenges presented in parsing road scenes from UAV images: the complexity of processing high-resolution images and the dependency on extensive manual annotations required by traditional supervised deep learning methods to…

Self-supervised learning (SSL) can be used to solve complex visual tasks without human labels. Self-supervised representations encode useful semantic information about images, and as a result, they have already been used for tasks such as…

In training machine learning models for land cover semantic segmentation there is a stark contrast between the availability of satellite imagery to be used as inputs and ground truth data to enable supervised learning. While thousands of…

Whilst the availability of 3D LiDAR point cloud data has significantly grown in recent years, annotation remains expensive and time-consuming, leading to a demand for semi-supervised semantic segmentation methods with application domains…

In many real-world scenarios, labeled data for a specific machine learning task is costly to obtain. Semi-supervised training methods make use of abundantly available unlabeled data and a smaller number of labeled examples. We propose a new…

Optical aerial images change detection is an important task in earth observation and has been extensively investigated in the past few decades. Generally, the supervised change detection methods with superior performance require a large…

Semantic segmentation networks are usually pre-trained once and not updated during deployment. As a consequence, misclassifications commonly occur if the distribution of the training data deviates from the one encountered during the robot's…

Self-supervised learning models have been shown to learn rich visual representations without requiring human annotations. However, in many real-world scenarios, labels are partially available, motivating a recent line of work on…

We present a novel unsupervised learning approach to automatically segment and label images in astronomical surveys. Automation of this procedure will be essential as next-generation surveys enter the petabyte scale: data volumes will…

Future advancements in robot autonomy and sophistication of robotics tasks rest on robust, efficient, and task-dependent semantic understanding of the environment. Semantic segmentation is the problem of simultaneous segmentation and…

In many critical computer vision scenarios unlabeled data is plentiful, but labels are scarce and difficult to obtain. As a result, semi-supervised learning which leverages unlabeled data to boost the performance of supervised classifiers…

As the exorbitant expense of labeling autopilot datasets and the growing trend of utilizing unlabeled data, semi-supervised segmentation on point clouds becomes increasingly imperative. Intuitively, finding out more ``unspoken words''…

Planetary rover systems need to perform terrain segmentation to identify drivable areas as well as identify specific types of soil for sample collection. The latest Martian terrain segmentation methods rely on supervised learning which is…

Pretraining has been shown to improve performance in many domains, including semantic segmentation, especially in domains with limited labelled data. In this work, we perform a large-scale evaluation and benchmarking of various pretraining…

Though deep learning based scene text detection has achieved great progress, well-trained detectors suffer from severe performance degradation for different domains. In general, a tremendous amount of data is indispensable to train the…

Progress in self-supervised learning has brought strong general image representation learning methods. Yet so far, it has mostly focused on image-level learning. In turn, tasks such as unsupervised image segmentation have not benefited from…

Unsupervised pre-training has led to much recent progress in natural language understanding. In this paper, we study self-training as another way to leverage unlabeled data through semi-supervised learning. To obtain additional data for a…