Related papers: Towards Generalizing Sensorimotor Control Across W…

In-context learning (ICL) refers to a remarkable capability of pretrained large language models, which can learn a new task given a few examples during inference. However, theoretical understanding of ICL is largely under-explored,…

We propose a novel setting for learning, where the input domain is the image of a map defined on the product of two sets, one of which completely determines the labels. We derive a new risk bound for this setting that decomposes into a bias…

If our models are used in new or unexpected cases, do we know if they will make fair predictions? Previously, researchers developed ways to debias a model for a single problem domain. However, this is often not how models are trained and…

Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distribution, which may not…

Visual perception in autonomous driving is a crucial part of a vehicle to navigate safely and sustainably in different traffic conditions. However, in bad weather such as heavy rain and haze, the performance of visual perception is greatly…

Computer vision based methods have been explored in the past for detection of railway track defects, but full automation has always been a challenge because both traditional image processing methods and deep learning classifiers trained…

Every recent image-to-image translation model inherently requires either image-level (i.e. input-output pairs) or set-level (i.e. domain labels) supervision. However, even set-level supervision can be a severe bottleneck for data collection…

With promising results of machine learning based models in computer vision, applications on medical imaging data have been increasing exponentially. However, generalizations to complex real-world clinical data is a persistent problem. Deep…

The well known domain shift issue causes model performance to degrade when deployed to a new target domain with different statistics to training. Domain adaptation techniques alleviate this, but need some instances from the target domain to…

Traditional place categorization approaches in robot vision assume that training and test images have similar visual appearance. Therefore, any seasonal, illumination and environmental changes typically lead to severe degradation in…

Reliable perception during fast motion maneuvers or in high dynamic range environments is crucial for robotic systems. Since event cameras are robust to these challenging conditions, they have great potential to increase the reliability of…

Domain adaptation (DA) strives to mitigate the domain gap between the source domain where a model is trained, and the target domain where the model is deployed. When a deep learning model is deployed on an aerial platform, it may face…

In autonomous driving scenarios, current object detection models show strong performance when tested in clear weather. However, their performance deteriorates significantly when tested in degrading weather conditions. In addition, even when…

Robots hold promise in many scenarios involving outdoor use, such as search-and-rescue, wildlife management, and collecting data to improve environment, climate, and weather forecasting. However, autonomous navigation of outdoor trails…

Supervised deep learning models require significant amount of labeled data to achieve an acceptable performance on a specific task. However, when tested on unseen data, the models may not perform well. Therefore, the models need to be…

We present an approach to domain adaptation, addressing the case where data from the source domain is abundant, labelled data from the target domain is limited or non-existent, and a small amount of paired source-target data is available.…

Employing machine learning models in the real world requires collecting large amounts of data, which is both time consuming and costly to collect. A common approach to circumvent this is to leverage existing, similar data-sets with large…

In domains such as health care and finance, shortage of labeled data and computational resources is a critical issue while developing machine learning algorithms. To address the issue of labeled data scarcity in training and deployment of…

Deep networks are successfully used as classification models yielding state-of-the-art results when trained on a large number of labeled samples. These models, however, are usually much less suited for semi-supervised problems because of…

This paper presents a study on semi-supervised learning to solve the visual attribute prediction problem. In many applications of vision algorithms, the precise recognition of visual attributes of objects is important but still challenging.…