Related papers: Incremental Open-set Domain Adaptation

Artificial neural networks, celebrated for their human-like cognitive learning abilities, often encounter the well-known catastrophic forgetting (CF) problem, where the neural networks lose the proficiency in previously acquired knowledge.…

Unsupervised domain adaptation aims to learn a task classifier that performs well on the unlabeled target domain, by utilizing the labeled source domain. Inspiring results have been acquired by learning domain-invariant deep features via…

Deep learning has become the method of choice to tackle real-world problems in different domains, partly because of its ability to learn from data and achieve impressive performance on a wide range of applications. However, its success…

3D object detection networks tend to be biased towards the data they are trained on. Evaluation on datasets captured in different locations, conditions or sensors than that of the training (source) data results in a drop in model…

This work presents an approach for incrementally updating deep neural network (DNN) models in a non-stationary environment. DNN models are sensitive to changes in input data distribution, which limits their application to problem settings…

We tackle the novel problem of incremental unsupervised domain adaptation (IDA) in this paper. We assume that a labeled source domain and different unlabeled target domains are incrementally observed with the constraint that data…

Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain by reducing the cross-domain distribution discrepancy. Most prior DA approaches leverage complicated and powerful deep neural…

In Open Set Domain Adaptation (OSDA), large amounts of target samples are drawn from the implicit categories that never appear in the source domain. Due to the lack of their specific belonging, existing methods indiscriminately regard them…

Domain incremental learning (DIL) poses a significant challenge in real-world scenarios, as models need to be sequentially trained on diverse domains over time, all the while avoiding catastrophic forgetting. Mitigating representation…

In this paper, we address the Online Unsupervised Domain Adaptation (OUDA) problem and propose a novel multi-stage framework to solve real-world situations when the target data are unlabeled and arriving online sequentially in batches. To…

Neural machine translation (NMT) models usually suffer from catastrophic forgetting during continual training where the models tend to gradually forget previously learned knowledge and swing to fit the newly added data which may have a…

Neural networks are achieving state of the art and sometimes super-human performance on learning tasks across a variety of domains. Whenever these problems require learning in a continual or sequential manner, however, neural networks…

Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models. While unsupervised domain adaptation aims to address this challenge, current approaches do not…

Autonomous systems (AS) often use Deep Neural Network (DNN) classifiers to allow them to operate in complex, high-dimensional, non-linear, and dynamically changing environments. Due to the complexity of these environments, DNN classifiers…

Model brittleness is a key concern when deploying deep learning models in real-world medical settings. A model that has high performance at one institution may suffer a significant decline in performance when tested at other institutions.…

In an effort to reduce annotation costs in action recognition, unsupervised video domain adaptation methods have been proposed that aim to adapt a predictive model from a labelled dataset (i.e., source domain) to an unlabelled dataset…

In spite of remarkable success of the convolutional neural networks on semantic segmentation, they suffer from catastrophic forgetting: a significant performance drop for the already learned classes when new classes are added on the data,…

Audio-visual continual test-time adaptation involves continually adapting a source audio-visual model at test-time, to unlabeled non-stationary domains, where either or both modalities can be distributionally shifted, which hampers online…

We consider the problem of domain adaptation in LiDAR-based 3D object detection. Towards this, we propose a simple yet effective training strategy called Gradual Batch Alternation that can adapt from a large labeled source domain to an…

Object detection has seen tremendous progress in recent years. However, current algorithms don't generalize well when tested on diverse data distributions. We address the problem of incremental learning in object detection on the India…