Related papers: Environment Inference for Learning Generalizable D…

Modern learning systems increasingly rely on amortized learning - the idea of reusing computation or inductive biases shared across tasks to enable rapid generalization to novel problems. This principle spans a range of approaches,…

An open problem in Machine Learning is how to avoid models to exploit spurious correlations in the data; a famous example is the background-label shortcut in the Waterbirds dataset. A common remedy is to train a model across multiple…

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…

Investigation of machine learning algorithms robust to changes between the training and test distributions is an active area of research. In this paper we explore a special type of dataset shift which we call class-dependent domain shift.…

Label noise will degenerate the performance of deep learning algorithms because deep neural networks easily overfit label errors. Let X and Y denote the instance and clean label, respectively. When Y is a cause of X, according to which many…

This paper investigates deploying semantic edge inference systems for performing a common image clarification task. In particular, each system consists of multiple Internet of Things (IoT) devices that first locally encode the sensing data…

Universal domain adaptation (UniDA) has been proposed to transfer knowledge learned from a label-rich source domain to a label-scarce target domain without any constraints on the label sets. In practice, however, it is difficult to obtain a…

Computer-aided diagnosis systems must make critical decisions from medical images that are often noisy, ambiguous, or conflicting, yet today's models are trained on overly simplistic labels that ignore diagnostic uncertainty. One-hot labels…

Using massive datasets to train large-scale models has emerged as a dominant approach for broad generalization in natural language and vision applications. In reinforcement learning, however, a key challenge is that available data of…

Recently, a number of image-mixing-based augmentation techniques have been introduced to improve the generalization of deep neural networks. In these techniques, two or more randomly selected natural images are mixed together to generate an…

Generalization of machine learning models trained on a set of source domains on unseen target domains with different statistics, is a challenging problem. While many approaches have been proposed to solve this problem, they only utilize…

Embodied perception systems face severe challenges of dynamic environment distribution drift when they continuously interact in open physical spaces. However, the existing domain incremental awareness methods often rely on the domain id…

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…

We consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset. This is a common scenario in many important applications. Existing related methods either exclusively…

Datasets with significant proportions of noisy (incorrect) class labels present challenges for training accurate Deep Neural Networks (DNNs). We propose a new perspective for understanding DNN generalization for such datasets, by…

We present a novel online learning algorithm for a class of unknown and uncertain dynamical environments that are fully observable. First, we obtain a novel probabilistic characterization of systems whose mean behavior is known but which…

The standard closed-set domain adaptation approaches seek to mitigate distribution discrepancies between two domains under the constraint of both sharing identical label sets. However, in realistic scenarios, finding an optimal source…

Over-parameterized deep neural networks trained by simple first-order methods are known to be able to fit any labeling of data. Such over-fitting ability hinders generalization when mislabeled training examples are present. On the other…

This paper introduces an ensemble of discriminators that improves the accuracy of a domain adaptation technique for the localization of multiple sound sources. Recently, deep neural networks have led to promising results for this task, yet…

Unsupervised domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Previous methods focus on learning domain-invariant features to decrease the discrepancy between the feature distributions…