Related papers: Learning Off-Road Terrain Traversability with Self…

Estimating a depth map from a single RGB image has been investigated widely for localization, mapping, and 3-dimensional object detection. Recent studies on a single-view depth estimation are mostly based on deep Convolutional neural…

While supervised learning is widely used for perception modules in conventional autonomous driving solutions, scalability is hindered by the huge amount of data labeling needed. In contrast, while end-to-end architectures do not require…

Many self-supervised learning (SSL) methods have been successful in learning semantically meaningful visual representations by solving pretext tasks. However, prior work in SSL focuses on tasks like object recognition or detection, which…

We address the problem of learning self-supervised representations from unlabeled image collections. Unlike existing approaches that attempt to learn useful features by maximizing similarity between augmented versions of each input image or…

Deep learning perception models require a massive amount of labeled training data to achieve good performance. While unlabeled data is easy to acquire, the cost of labeling is prohibitive and could create a tremendous burden on companies or…

Self-supervised learning has proved to be a powerful approach to learn image representations without the need of large labeled datasets. For underwater robotics, it is of great interest to design computer vision algorithms to improve…

Compared to supervised deep learning, self-supervision provides remote sensing a tool to reduce the amount of exact, human-crafted geospatial annotations. While image-level information for unsupervised pretraining efficiently works for…

Uncertainty in control and perception poses challenges for autonomous vehicle navigation in unstructured environments, leading to navigation failures and potential vehicle damage. This paper introduces a framework that minimizes control and…

One of the largest problems in medical image processing is the lack of annotated data. Labeling medical images often requires highly trained experts and can be a time-consuming process. In this paper, we evaluate a method of reducing the…

Self-training is an effective approach to semi-supervised learning. The key idea is to let the learner itself iteratively generate "pseudo-supervision" for unlabeled instances based on its current hypothesis. In combination with consistency…

We witnessed a massive growth in the supervised learning paradigm in the past decade. Supervised learning requires a large amount of labeled data to reach state-of-the-art performance. However, labeling the samples requires a lot of human…

Contemporary research in autonomous driving has demonstrated tremendous potential in emulating the traits of human driving. However, they primarily cater to areas with well built road infrastructure and appropriate traffic management…

Mobile ground robots operating on unstructured terrain must predict which areas of the environment they are able to pass in order to plan feasible paths. We address traversability estimation as a heightmap classification problem: we build a…

This paper presents a safe, efficient, and agile ground vehicle navigation algorithm for 3D off-road terrain environments. Off-road navigation is subject to uncertain vehicle-terrain interactions caused by different terrain conditions on…

We present a conceptually simple self-supervised method for saliency detection. Our method generates and uses pseudo-ground truth labels for training. The generated pseudo-GT labels don't require any kind of human annotations (e.g.,…

Traditional supervised learning methods are hitting a bottleneck because of their dependency on expensive manually labeled data and their weaknesses such as limited generalization ability and vulnerability to adversarial attacks. A…

Effectively utilizing the vast amounts of ego-centric navigation data that is freely available on the internet can advance generalized intelligent systems, i.e., to robustly scale across perspectives, platforms, environmental conditions,…

Imitation learning holds the promise to address challenging robotic tasks such as autonomous navigation. It however requires a human supervisor to oversee the training process and send correct control commands to robots without feedback,…

Deep neural networks are typically trained under a supervised learning framework where a model learns a single task using labeled data. Instead of relying solely on labeled data, practitioners can harness unlabeled or related data to…

Obtaining labelled data to train deep learning methods for estimating animal pose is challenging. Recently, synthetic data has been widely used for pose estimation tasks, but most methods still rely on supervised learning paradigms…