Related papers: Enhancing Handwritten Text Recognition with N-gram…

We develop new algorithms for simultaneous learning of multiple tasks (e.g., image classification, depth estimation), and for adapting to unseen task/domain distributions within those high-level tasks (e.g., different environments). First,…

Decoding visual information from time-resolved brain recordings, such as EEG and MEG, plays a pivotal role in real-time brain-computer interfaces. However, existing approaches primarily focus on direct brain-image feature alignment and are…

Unconstrained handwritten text recognition is a major step in most document analysis tasks. This is generally processed by deep recurrent neural networks and more specifically with the use of Long Short-Term Memory cells. The main drawbacks…

Unsupervised graph representation learning(GRL) aims to distill diverse graph information into task-agnostic embeddings without label supervision. Due to a lack of support from labels, recent representation learning methods usually adopt…

Despite significant progress toward super resolving more realistic images by deeper convolutional neural networks (CNNs), reconstructing fine and natural textures still remains a challenging problem. Recent works on single image super…

Despite considerable advancements with deep neural language models, the enigma of neural text degeneration persists when these models are tested as text generators. The counter-intuitive empirical observation is that even though the use of…

Neural network models have shown their promising opportunities for multi-task learning, which focus on learning the shared layers to extract the common and task-invariant features. However, in most existing approaches, the extracted shared…

In both Computer Vision and the wider Deep Learning field, the Transformer architecture is well-established as state-of-the-art for many applications. For Multitask Learning, however, where there may be many more queries necessary compared…

Despite recent progress, learning new tasks through language instructions remains an extremely challenging problem. On the ALFRED benchmark for task learning, the published state-of-the-art system only achieves a task success rate of less…

Despite the growing discriminative capabilities of modern deep learning methods for recognition tasks, the inner workings of the state-of-art models still remain mostly black-boxes. In this paper, we propose a systematic interpretation of…

Typical text recognition methods rely on an encoder-decoder structure, in which the encoder extracts features from an image, and the decoder produces recognized text from these features. In this study, we propose a simpler and more…

Interpretable Multi-Task Learning can be expressed as learning a sparse graph of the task relationship based on the prediction performance of the learned models. Since many natural phenomenon exhibit sparse structures, enforcing sparsity on…

Machine learning on graph structured data has attracted much research interest due to its ubiquity in real world data. However, how to efficiently represent graph data in a general way is still an open problem. Traditional methods use…

Leveraging Graph Neural Networks (GNNs) as graph encoders and aligning the resulting representations with Large Language Models (LLMs) through alignment instruction tuning has become a mainstream paradigm for constructing Graph Language…

Multi-task learning leverages potential correlations among related tasks to extract common features and yield performance gains. However, most previous works only consider simple or weak interactions, thereby failing to model complex…

Graph Neural Networks (GNNs) are a framework for graph representation learning, where a model learns to generate low dimensional node embeddings that encapsulate structural and feature-related information. GNNs are usually trained in an…

Pre-training has proven to be effective in unsupervised machine translation due to its ability to model deep context information in cross-lingual scenarios. However, the cross-lingual information obtained from shared BPE spaces is…

The emergence of multi-modal deep learning models has made significant impacts on clinical applications in the last decade. However, the majority of models are limited to single-tasking, without considering disease diagnosis is indeed a…

End-to-end training of deep learning-based models allows for implicit learning of intermediate representations based on the final task loss. However, the end-to-end approach ignores the useful domain knowledge encoded in explicit…

Attention-based sequence-to-sequence modeling provides a powerful and elegant solution for applications that need to map one sequence to a different sequence. Its success heavily relies on the availability of large amounts of training data.…