Related papers: Orthogonal Projection Subspace to Aggregate Online…

Open compound domain adaptation (OCDA) is a domain adaptation setting, where target domain is modeled as a compound of multiple unknown homogeneous domains, which brings the advantage of improved generalization to unseen domains. In this…

Recurrent neural networks trained with the backpropagation through time (BPTT) algorithm have led to astounding successes in various temporal tasks. However, BPTT introduces severe limitations, such as the requirement to propagate…

Test-time adaptation (TTA) aims to adapt a model, initially trained on training data, to test data with potential distribution shifts. Most existing TTA methods focus on classification problems. The pronounced success of classification…

Online test-time adaptation (OTTA) of vision-language models (VLMs) has recently garnered increased attention to take advantage of data observed along a stream to improve future predictions. Unfortunately, existing methods rely on…

Online Continual learning is a challenging learning scenario where the model must learn from a non-stationary stream of data where each sample is seen only once. The main challenge is to incrementally learn while avoiding catastrophic…

Continual Test-Time Adaptation (CTTA) aims to quickly fine-tune the model during the test phase so that it can adapt to multiple unknown downstream domain distributions without pre-acquiring downstream domain data. To this end, existing…

Test-time adaptation (TTA) addresses distribution shifts for streaming test data in unsupervised settings. Currently, most TTA methods can only deal with minor shifts and rely heavily on heuristic and empirical studies. To advance TTA under…

Class-incremental learning (CIL) aims to learn new classes while retaining previous knowledge. Although pre-trained model (PTM) based approaches show strong performance, directly fine-tuning PTMs on incremental task streams often causes…

Continual adaptation is essential for general autonomous agents. For example, a household robot pretrained with a repertoire of skills must still adapt to unseen tasks specific to each household. Motivated by this, building upon…

Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. Two recent continual-learning scenarios have opened new avenues of research. In meta-continual learning, the…

Online continual learning (OCL) aims to enable model learning from a non-stationary data stream to continuously acquire new knowledge as well as retain the learnt one, under the constraints of having limited system size and computational…

Test-time adaptation (TTA) refers to adjusting the model during the testing phase to cope with changes in sample distribution and enhance the model's adaptability to new environments. In real-world scenarios, models often encounter samples…

Current test-time adaptation (TTA) approaches aim to adapt a machine learning model to environments that change continuously. Yet, it is unclear whether TTA methods can maintain their adaptability over prolonged periods. To answer this…

Test-time adaptation (TTA) aims to fine-tune a trained model online using unlabeled testing data to adapt to new environments or out-of-distribution data, demonstrating broad application potential in real-world scenarios. However, in this…

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…

Catastrophic forgetting makes neural network models unstable when learning visual domains consecutively. The neural network model drifts to catastrophic forgetting-induced low performance of previously learnt domains when training with new…

Continual Test Time Adaptation (CTTA) has emerged as a critical approach for bridging the domain gap between the controlled training environments and the real-world scenarios, enhancing model adaptability and robustness. Existing CTTA…

Continual learning aims to rapidly and continually learn the current task from a sequence of tasks. Compared to other kinds of methods, the methods based on experience replay have shown great advantages to overcome catastrophic forgetting.…

Domain adaptation solves image classification problems in the target domain by taking advantage of the labelled source data and unlabelled target data. Usually, the source and target domains share the same set of classes. As a special case,…

Test-time adaptation (TTA) is a technique aimed at enhancing the generalization performance of models by leveraging unlabeled samples solely during prediction. Given the need for robustness in neural network systems when faced with…