Related papers: TripleE: Easy Domain Generalization via Episodic R…
Domain generalization (DG) tends to alleviate the poor generalization capability of deep neural networks by learning model with multiple source domains. A classical solution to DG is domain augmentation, the common belief of which is that…
State-of-the-art models often make use of superficial patterns in the data that do not generalize well to out-of-domain or adversarial settings. For example, textual entailment models often learn that particular key words imply entailment,…
Transferring knowledge across different datasets is an important approach to successfully train deep models with a small-scale target dataset or when few labeled instances are available. In this paper, we aim at developing a model that can…
Open-set single-source domain generalization aims to use a single-source domain to learn a robust model that can be generalized to unknown target domains with both domain shifts and label shifts. The scarcity of the source domain and the…
Human adaptability relies crucially on the ability to learn and merge knowledge both from supervised and unsupervised learning: the parents point out few important concepts, but then the children fill in the gaps on their own. This is…
Improving generalization is one key challenge in embodied AI, where obtaining large-scale datasets across diverse scenarios is costly. Traditional weak augmentations, such as cropping and flipping, are insufficient for improving a model's…
Domain generalization (DG) aims to learn a generic model from multiple observed source domains that generalizes well to arbitrary unseen target domains without further training. The major challenge in DG is that the model inevitably faces a…
Despite much progress being made in the field of object recognition with the advances of deep learning, there are still several factors negatively affecting the performance of deep learning models. Domain shift is one of these factors and…
A popular assumption for out-of-distribution generalization is that the training data comprises sub-datasets, each drawn from a distinct distribution; the goal is then to "interpolate" these distributions and "extrapolate" beyond them --…
Few-shot learning aims to generalize unseen classes that appear during testing but are unavailable during training. Prototypical networks incorporate few-shot metric learning, by constructing a class prototype in the form of a mean vector…
Ensemble methods are known for enhancing the accuracy and robustness of machine learning models by combining multiple base learners. However, standard approaches like greedy or random ensembling often fall short, as they assume a constant…
Experience replay is widely used to improve learning efficiency in reinforcement learning by leveraging past experiences. However, existing experience replay methods, whether based on uniform or prioritized sampling, often suffer from low…
Deep reinforcement learning (RL) agents may successfully generalize to new settings if trained on an appropriately diverse set of environment and task configurations. Unsupervised Environment Design (UED) is a promising self-supervised RL…
Deep metric learning is often used to learn an embedding function that captures the semantic differences within a dataset. A key factor in many problem domains is how this embedding generalizes to new classes of data. In observing many…
Empirical interpolation method (EIM) is a well-known technique to efficiently approximate parameterized functions. This paper proposes to use EIM algorithm to efficiently reduce the dimension of the training data within supervised machine…
Class-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Despite the strong performance of Pre-Trained Models (PTMs) in CIL, a critical issue persists: learning new classes often…
Domain generalization (DG) is the challenging and topical problem of learning models that generalize to novel testing domains with different statistics than a set of known training domains. The simple approach of aggregating data from all…
Mixup is a popular data augmentation technique for training deep neural networks where additional samples are generated by linearly interpolating pairs of inputs and their labels. This technique is known to improve the generalization…
Continual learning seeks to enable machine learning systems to solve an increasing corpus of tasks sequentially. A critical challenge for continual learning is forgetting, where the performance on previously learned tasks decreases as new…
Generalizing learned representations across significantly different visual domains is a fundamental yet crucial ability of the human visual system. While recent self-supervised learning methods have achieved good performances with…