Related papers: Stroke-Based Autoencoders: Self-Supervised Learner…
Face swapping has gained significant attention for its varied applications. Most previous face swapping approaches have relied on the seesaw game training scheme, also known as the target-oriented approach. However, this often leads to…
Due to the huge category number, the sophisticated combinations of various strokes and radicals, and the free writing or printing styles, generating Chinese characters with diverse styles is always considered as a difficult task. In this…
Sparse autoencoders (SAEs) have emerged as a powerful tool for uncovering interpretable features in large language models (LLMs) through the sparse directions they learn. However, the sheer number of extracted directions makes comprehensive…
Does a Variational AutoEncoder (VAE) consistently encode typical samples generated from its decoder? This paper shows that the perhaps surprising answer to this question is `No'; a (nominally trained) VAE does not necessarily amortize…
Directed graphs are a natural model for many phenomena, in particular scientific knowledge graphs such as molecular interaction or chemical reaction networks that define cellular signaling relationships. In these situations, source nodes…
Zero-shot cross-lingual information extraction(IE) aims at constructing an IE model for some low-resource target languages, given annotations exclusively in some rich-resource languages. Recent studies based on language-universal features…
Non-parallel text style transfer has attracted increasing research interests in recent years. Despite successes in transferring the style based on the encoder-decoder framework, current approaches still lack the ability to preserve the…
Unsupervised learning methods have become increasingly important in deep learning due to their demonstrated large utilization of datasets and higher accuracy in computer vision and natural language processing tasks. There is a growing trend…
In this paper, we propose a novel model, named Stroke Sequence-dependent Deep Convolutional Neural Network (SSDCNN), using the stroke sequence information and eight-directional features for Online Handwritten Chinese Character Recognition…
Self-supervised learning (SSL) enables learning useful inductive biases through utilizing pretext tasks that require no labels. The unlabeled nature of SSL makes it especially important for whole slide histopathological images (WSIs), where…
Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based autoencoders have shown great potential in detecting anomalies in medical images. However, especially…
Ancient Chinese character recognition is a core capability for cultural heritage digitization, yet real-world workflows are inherently non-stationary: newly excavated materials are continuously onboarded, bringing new classes in different…
Autoencoding is a popular method in representation learning. Conventional autoencoders employ symmetric encoding-decoding procedures and a simple Euclidean latent space to detect hidden low-dimensional structures in an unsupervised way.…
Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of…
Enterprise relational databases increasingly contain vast amounts of non-semantic data - IP addresses, product identifiers, encoded keys, and timestamps - that challenge traditional semantic analysis. This paper introduces a novel…
In deep learning for drug discovery, chemical data are often represented as simplified molecular-input line-entry system (SMILES) sequences which allow for straightforward implementation of natural language processing methodologies, one…
Chinese Spelling Check (CSC) is a task to detect and correct spelling errors in Chinese natural language. Existing methods have made attempts to incorporate the similarity knowledge between Chinese characters. However, they take the…
Recently, significant progress has been made in masked image modeling to catch up to masked language modeling. However, unlike words in NLP, the lack of semantic decomposition of images still makes masked autoencoding (MAE) different…
Tokenization is fundamental to pretrained language models (PLMs). Existing tokenization methods for Chinese PLMs typically treat each character as an indivisible token. However, they ignore the unique feature of the Chinese writing system…
Sparse Autoencoders (SAEs) are widely employed for mechanistic interpretability and model steering. Within this context, steering is by design performed by means of decoding altered SAE intermediate representations. This procedure…