Related papers: Learning Maritime Obstacle Detection from Weak Ann…

Deployment of deep learning models in robotics as sensory information extractors can be a daunting task to handle, even using generic GPU cards. Here, we address three of its most prominent hurdles, namely, i) the adaptation of a single…

Weakly supervised semantic segmentation receives much research attention since it alleviates the need to obtain a large amount of dense pixel-wise ground-truth annotations for the training images. Compared with other forms of weak…

The recent mainstream reinforcement learning control for quadruped robots often relies on privileged information, demanding meticulous selection and precise estimation, thereby imposing constraints on the development process. This work…

Self-training is a simple yet effective method for semi-supervised learning, during which pseudo-label selection plays an important role for handling confirmation bias. Despite its popularity, applying self-training to landmark detection…

Mobile robots navigating in indoor and outdoor environments must be able to identify and avoid unsafe terrain. Although a significant amount of work has been done on the detection of standing obstacles (solid obstructions), not much work…

With basic Semi-Supervised Object Detection (SSOD) techniques, one-stage detectors generally obtain limited promotions compared with two-stage clusters. We experimentally find that the root lies in two kinds of ambiguities: (1) Selection…

With the rise of Machine Learning as a Service (MLaaS) platforms,safeguarding the intellectual property of deep learning models is becoming paramount. Among various protective measures, trigger set watermarking has emerged as a flexible and…

Successful navigation in outdoor environments requires accurate prediction of the physical interactions between the robot and the terrain. Many prior methods rely on geometric or semantic labels to classify traversable surfaces. However,…

In many manufacturing settings, annotating data for machine learning and computer vision is costly, but synthetic data can be generated at significantly lower cost. Substituting the real-world data with synthetic data is therefore appealing…

You can have your cake and eat it too. Microvessel segmentation in optical coherence tomography angiography (OCTA) images remains challenging. Skeleton-level segmentation shows clear topology but without diameter information, while…

As the demand for autonomous navigation in off-road environments increases, the need for effective solutions to understand these surroundings becomes essential. In this study, we confront the inherent complexities of semantic segmentation…

We present a graph-based semi-supervised learning (SSL) method for learning edge flows defined on a graph. Specifically, given flow measurements on a subset of edges, we want to predict the flows on the remaining edges. To this end, we…

Semi-Supervised Learning (SSL) is a framework that utilizes both labeled and unlabeled data to enhance model performance. Conventional SSL methods operate under the assumption that labeled and unlabeled data share the same label space.…

Nowadays, supervised deep learning techniques yield the best state-of-the-art prediction performances for a wide variety of computer vision tasks. However, such supervised techniques generally require a large amount of manually labeled…

Large training datasets almost always contain examples with inaccurate or incorrect labels. Deep Neural Networks (DNNs) tend to overfit training label noise, resulting in poorer model performance in practice. To address this problem, we…

Geological interpretation of seismic images is a visual task that can be automated by training neural networks. While neural networks have shown to be effective at various interpretation tasks, a fundamental challenge is the lack of labeled…

Human decision-making errors cause a majority of globally reported marine accidents. As a result, automation in the marine industry has been gaining more attention in recent years. Obstacle avoidance becomes very challenging for an…

As one of the most challenging and practical segmentation tasks, open-world semantic segmentation requires the model to segment the anomaly regions in the images and incrementally learn to segment out-of-distribution (OOD) objects,…

Self-Supervised Learning (SSL) is a valuable and robust training methodology for contemporary Deep Neural Networks (DNNs), enabling unsupervised pretraining on a 'pretext task' that does not require ground-truth labels/annotation. This…

Camera-equipped unmanned vehicles (UVs) have received a lot of attention in data collection for construction monitoring applications. To develop an autonomous platform, the UV should be able to process multiple modules (e.g.,…