Related papers: DocTTT: Test-Time Training for Handwritten Documen…

Unsupervised meta-learning aims to learn feature representations from unsupervised datasets that can transfer to downstream tasks with limited labeled data. In this paper, we propose a novel approach to unsupervised meta-learning that…

Task specific fine-tuning of a pre-trained neural language model using a custom softmax output layer is the de facto approach of late when dealing with document classification problems. This technique is not adequate when labeled examples…

Handwritten text recognition for historical documents is an important task but it remains difficult due to a lack of sufficient training data in combination with a large variability of writing styles and degradation of historical documents.…

Handwritten Text Recognition has achieved an impressive performance in public benchmarks. However, due to the high inter- and intra-class variability between handwriting styles, such recognizers need to be trained using huge volumes of…

Prior to the deployment of robotic systems, pre-training the deep-recognition models on all potential visual cases is infeasible in practice. Hence, test-time adaptation (TTA) allows the model to adapt itself to novel environments and…

Tactile perception is indispensable for robots to implement various manipulations dexterously, especially in contact-rich scenarios. However, alongside the development of deep learning techniques, it meanwhile suffers from training data…

Contemporary medical contrastive learning faces challenges from inconsistent semantics and sample pair morphology, leading to dispersed and converging semantic shifts. The variability in text reports, due to multiple authors, complicates…

Decision Transformers (DT) have demonstrated strong performances in offline reinforcement learning settings, but quickly adapting to unseen novel tasks remains challenging. To address this challenge, we propose a new framework, called…

Deploying models on target domain data subject to distribution shift requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available,…

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…

In the arena of language model fine-tuning, the traditional approaches, such as Domain-Adaptive Pretraining (DAPT) and Task-Adaptive Pretraining (TAPT), although effective, but computational intensive. This research introduces a novel…

Pre-trained Large Language Models (LLMs) often struggle on out-of-domain datasets like healthcare focused text. We explore specialized pre-training to adapt smaller LLMs to different healthcare datasets. Three methods are assessed:…

Until recently, the number of public real-world text images was insufficient for training scene text recognizers. Therefore, most modern training methods rely on synthetic data and operate in a fully supervised manner. Nevertheless, the…

Continual Test-Time Adaptation (CTTA) is proposed to migrate a source pre-trained model to continually changing target distributions, addressing real-world dynamism. Existing CTTA methods mainly rely on entropy minimization or…

The ability to learn new concepts with small amounts of data is a critical aspect of intelligence that has proven challenging for deep learning methods. Meta-learning has emerged as a promising technique for leveraging data from previous…

Deep learning-based symbol detector gains increasing attention due to the simple algorithm design than the traditional model-based algorithms such as Viterbi and BCJR. The supervised learning framework is often employed to predict the input…

Recent advances in deep learning, in particular enabled by hardware advances and big data, have provided impressive results across a wide range of computational problems such as computer vision, natural language, or reinforcement learning.…

Considerable research attention has been paid to table detection by developing not only rule-based approaches reliant on hand-crafted heuristics but also deep learning approaches. Although recent studies successfully perform table detection…

Unsupervised multivariate time series (MTS) representation learning aims to extract compact and informative representations from raw sequences without relying on labels, enabling efficient transfer to diverse downstream tasks. In this…

Optical character recognition remains critical infrastructure for document digitization, yet state-of-the-art performance is often restricted to well-resourced institutions by prohibitive computational barriers. End-to-end transformer…