Related papers: Continuous Learning for Large-scale Personalized D…

We describe a method for selecting relevant new training data for the LSTM-based domain selection component of our personal assistant system. Adding more annotated training data for any ML system typically improves accuracy, but only if it…

While Large language models (LLMs) have demonstrated considerable capabilities across various natural language tasks, they often fall short of the performance achieved by domain-specific state-of-the-art models. One potential approach to…

Language models (LMs) have been instrumental for the rapid advance of natural language processing. This paper studies continual pre-training of LMs, in particular, continual domain-adaptive pre-training (or continual DAP-training). Existing…

Classifying and resolving coreferences of objects (e.g., product names) and attributes (e.g., product aspects) in opinionated reviews is crucial for improving the opinion mining performance. However, the task is challenging as one often…

Visual localization is a fundamental machine learning problem. Absolute Pose Regression (APR) trains a scene-dependent model to efficiently map an input image to the camera pose in a pre-defined scene. However, many applications have…

In this paper, we propose a novel implicit semantic data augmentation (ISDA) approach to complement traditional augmentation techniques like flipping, translation or rotation. Our work is motivated by the intriguing property that deep…

In large-scale domain classification, an utterance can be handled by multiple domains with overlapped capabilities. However, only a limited number of ground-truth domains are provided for each training utterance in practice while knowing as…

Machine learning models often struggle to generalize across domains with varying data distributions, such as differing noise levels, leading to degraded performance. Traditional strategies like personalized training, which trains separate…

State-of-the-art speaker recognition systems comprise an x-vector (or i-vector) speaker embedding front-end followed by a probabilistic linear discriminant analysis (PLDA) backend. The effectiveness of these components relies on the…

The effectiveness of unsupervised domain adaptation degrades when there is a large discrepancy between the source and target domains. Gradual domain adaptation (GDA) is one promising way to mitigate such an issue, by leveraging additional…

Unsupervised domain adaptation (UDA) is important for applications where large scale annotation of representative data is challenging. For semantic segmentation in particular, it helps deploy on real "target domain" data models that are…

We focus on bridging domain discrepancy in lane detection among different scenarios to greatly reduce extra annotation and re-training costs for autonomous driving. Critical factors hinder the performance improvement of cross-domain lane…

Unsupervised domain adaptation (UDA) enables knowledge transfer from the labelled source domain to the unlabeled target domain by reducing the cross-domain discrepancy. However, most of the studies were based on direct adaptation from the…

LiDAR semantic segmentation provides 3D semantic information about the environment, an essential cue for intelligent systems during their decision making processes. Deep neural networks are achieving state-of-the-art results on large public…

Imitating skills from low-quality datasets, such as sub-optimal demonstrations and observations with distractors, is common in real-world applications. In this work, we focus on the problem of Learning from Noisy Demonstrations (LND), where…

Novel Class Discovery (NCD) is the problem of trying to discover novel classes in an unlabeled set, given a labeled set of different but related classes. The majority of NCD methods proposed so far only deal with image data, despite tabular…

Despite great progress in supervised semantic segmentation,a large performance drop is usually observed when deploying the model in the wild. Domain adaptation methods tackle the issue by aligning the source domain and the target domain.…

Data augmentation is widely known as a simple yet surprisingly effective technique for regularizing deep networks. Conventional data augmentation schemes, e.g., flipping, translation or rotation, are low-level, data-independent and…

Unsupervised domain adaptation(UDA) has been applied to image semantic segmentation to solve the problem of domain offset. However, in some difficult categories with poor recognition accuracy, the segmentation effects are still not ideal.…

Multimodal large language models (MLLMs) have shown remarkable capabilities in multimodal perception and understanding tasks. However, their effectiveness in specialized domains, such as remote sensing and medical imaging, remains limited.…