Related papers: Playing Lottery Tickets in Style Transfer Models

Pruning is a well-established technique for removing unnecessary structure from neural networks after training to improve the performance of inference. Several recent results have explored the possibility of pruning at initialization time…

Classical statistical learning theory predicts that overparameterized models should exhibit severe overfitting, yet modern deep neural networks with far more parameters than training samples consistently generalize well. This contradiction…

It has been demonstrated that deep neural networks outperform traditional machine learning. However, deep networks lack generalisability, that is, they will not perform as good as in a new (testing) set drawn from a different distribution…

Text style transfer aims to paraphrase a sentence in one style into another style while preserving content. Due to lack of parallel training data, state-of-art methods are unsupervised and rely on large datasets that share content.…

While different neural models often exhibit latent spaces that are alike when exposed to semantically related data, this intrinsic similarity is not always immediately discernible. Towards a better understanding of this phenomenon, our work…

We investigate whether post-trained capabilities can be transferred across models without retraining, with a focus on transfer across different model scales. We propose the Master Key Hypothesis, which states that model capabilities…

In recent years, Recurrent Neural Networks (RNNs) based models have been applied to the Slot Filling problem of Spoken Language Understanding and achieved the state-of-the-art performances. In this paper, we investigate the effect of…

Test-time training (TTT) methods explicitly update the weights of a model to adapt to the specific test instance, and they have found success in a variety of settings, including most recently language modeling and reasoning. To demystify…

Knitting patterns are a crucial component in the creation and design of knitted materials. Traditionally, these patterns were taught informally, but thanks to advancements in technology, anyone interested in knitting can use the patterns as…

Pruning refers to the elimination of trivial weights from neural networks. The sub-networks within an overparameterized model produced after pruning are often called Lottery tickets. This research aims to generate winning lottery tickets…

Accurate forecasting of recovery rates (RR) is central to credit risk management and regulatory capital determination. In many loan portfolios, however, RR modeling is constrained by data scarcity arising from infrequent default events.…

End-to-end neural TTS training has shown improved performance in speech style transfer. However, the improvement is still limited by the training data in both target styles and speakers. Inadequate style transfer performance occurs when the…

Machine learning (ML) research strongly relies on benchmarks in order to determine the relative effectiveness of newly proposed models. Recently, a number of prominent research effort argued that a number of models that improve the…

Transfer learning can significantly improve the sample efficiency of neural networks, by exploiting the relatedness between a data-scarce target task and a data-abundant source task. Despite years of successful applications, transfer…

This paper presents a novel design of neural network system for fine-grained style modeling, transfer and prediction in expressive text-to-speech (TTS) synthesis. Fine-grained modeling is realized by extracting style embeddings from the…

Vision transformers have revolutionized computer vision, but their computational demands present challenges for training and deployment. This paper introduces LOTUS (LOttery Transformers with Ultra Sparsity), a novel method that leverages…

Long-sequence modeling faces a fundamental trade-off between the efficiency of compressive fixed-size memory in RNN-like models and the fidelity of lossless growing memory in attention-based Transformers. Inspired by the Multi-Store Model…

Style transfer is a useful image synthesis technique that can re-render given image into another artistic style while preserving its content information. Generative Adversarial Network (GAN) is a widely adopted framework toward this task…

We explore the method of style transfer presented in the article "A Neural Algorithm of Artistic Style" by Leon A. Gatys, Alexander S. Ecker and Matthias Bethge (arXiv:1508.06576). We first demonstrate the power of the suggested style space…

We present a novel approach to the problem of text style transfer. Unlike previous approaches requiring style-labeled training data, our method makes use of readily-available unlabeled text by relying on the implicit connection in style…