English
Related papers

Related papers: UniDrop: A Simple yet Effective Technique to Impro…

200 papers

Deep learning models learn to fit training data while they are highly expected to generalize well to testing data. Most works aim at finding such models by creatively designing architectures and fine-tuning parameters. To adapt to…

Computer Vision and Pattern Recognition · Computer Science 2018-09-10 Tianyang Wang , Jun Huan , Bo Li

Recently, nested dropout was proposed as a method for ordering representation units in autoencoders by their information content, without diminishing reconstruction cost. However, it has only been applied to training fully-connected…

Computer Vision and Pattern Recognition · Computer Science 2015-04-13 Chelsea Finn , Lisa Anne Hendricks , Trevor Darrell

Deep neural networks are learning models with a very high capacity and therefore prone to over-fitting. Many regularization techniques such as Dropout, DropConnect, and weight decay all attempt to solve the problem of over-fitting by…

Machine Learning · Computer Science 2016-12-06 Armen Aghajanyan

Transformer models, which leverage architectural improvements like self-attention, perform remarkably well on Natural Language Processing (NLP) tasks. The self-attention mechanism is position agnostic. In order to capture positional…

Computation and Language · Computer Science 2021-09-28 Zhiheng Huang , Davis Liang , Peng Xu , Bing Xiang

This paper presents a new version of Dropout called Split Dropout (sDropout) and rotational convolution techniques to improve CNNs' performance on image classification. The widely used standard Dropout has advantage of preventing deep…

Computer Vision and Pattern Recognition · Computer Science 2015-08-03 Fa Wu , Peijun Hu , Dexing Kong

Very deep convolutional neural networks offer excellent recognition results, yet their computational expense limits their impact for many real-world applications. We introduce BlockDrop, an approach that learns to dynamically choose which…

Computer Vision and Pattern Recognition · Computer Science 2019-01-29 Zuxuan Wu , Tushar Nagarajan , Abhishek Kumar , Steven Rennie , Larry S. Davis , Kristen Grauman , Rogerio Feris

This paper presents UniBERT, a compact multilingual language model that uses an innovative training framework that integrates three components: masked language modeling, adversarial training, and knowledge distillation. Pre-trained on a…

Computation and Language · Computer Science 2025-09-03 Andrei-Marius Avram , Marian Lupaşcu , Dumitru-Clementin Cercel , Ionuţ Mironică , Ştefan Trăuşan-Matu

Reading comprehension has recently seen rapid progress, with systems matching humans on the most popular datasets for the task. However, a large body of work has highlighted the brittleness of these systems, showing that there is much work…

Computation and Language · Computer Science 2019-04-18 Dheeru Dua , Yizhong Wang , Pradeep Dasigi , Gabriel Stanovsky , Sameer Singh , Matt Gardner

To enhance the generalization ability of the model and improve the effectiveness of the transformer for named entity recognition tasks, the XLNet-Transformer-R model is proposed in this paper. The XLNet pre-trained model and the Transformer…

Computation and Language · Computer Science 2023-06-16 Weidong Ji , Yousheng Zhang , Guohui Zhou , Xu Wang

Text embeddings, i.e. vector representations of entire texts, play an important role in many NLP applications, such as retrieval-augmented generation, clustering, or visualizing collections of texts for data exploration. Currently,…

Computation and Language · Computer Science 2026-03-17 Rita González-Márquez , Philipp Berens , Dmitry Kobak

Model-based reinforcement learning is a widely accepted solution for solving excessive sample demands. However, the predictions of the dynamics models are often not accurate enough, and the resulting bias may incur catastrophic decisions…

Machine Learning · Computer Science 2024-05-03 Wanpeng Zhang , Xi Xiao , Yao Yao , Mingzhe Chen , Dijun Luo

With the growing attention on learning-to-learn new tasks using only a few examples, meta-learning has been widely used in numerous problems such as few-shot classification, reinforcement learning, and domain generalization. However,…

Computer Vision and Pattern Recognition · Computer Science 2020-04-14 Hung-Yu Tseng , Yi-Wen Chen , Yi-Hsuan Tsai , Sifei Liu , Yen-Yu Lin , Ming-Hsuan Yang

We introduce Data Diversification: a simple but effective strategy to boost neural machine translation (NMT) performance. It diversifies the training data by using the predictions of multiple forward and backward models and then merging…

Computation and Language · Computer Science 2020-10-06 Xuan-Phi Nguyen , Shafiq Joty , Wu Kui , Ai Ti Aw

Dropout is often used in deep neural networks to prevent over-fitting. Conventionally, dropout training invokes \textit{random drop} of nodes from the hidden layers of a Neural Network. It is our hypothesis that a guided selection of nodes…

Machine Learning · Computer Science 2018-12-11 Rohit Keshari , Richa Singh , Mayank Vatsa

Transformer architectures dominate modern NLP but often demand heavy computational resources and intricate hyperparameter tuning. To mitigate these challenges, we propose a novel framework, BoostTransformer, that augments transformers with…

Machine Learning · Computer Science 2025-11-04 Biyi Fang , Truong Vo , Jean Utke , Diego Klabjan

Machine Translation models are trained to translate a variety of documents from one language into another. However, models specifically trained for a particular characteristics of the documents tend to perform better. Fine-tuning is a…

Computation and Language · Computer Science 2019-10-09 Alberto Poncelas , Gideon Maillette de Buy Wenniger , Andy Way

Real-world data contains a vast amount of multimodal information, among which vision and language are the two most representative modalities. Moreover, increasingly heavier models, \textit{e}.\textit{g}., Transformers, have attracted the…

Computer Vision and Pattern Recognition · Computer Science 2023-07-03 Dachuan Shi , Chaofan Tao , Ying Jin , Zhendong Yang , Chun Yuan , Jiaqi Wang

Adapter-Tuning (AT) method involves freezing a pre-trained model and introducing trainable adapter modules to acquire downstream knowledge, thereby calibrating the model for better adaptation to downstream tasks. This paper proposes a…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Jiacheng Ruan , Jingsheng Gao , Mingye Xie , Daize Dong , Suncheng Xiang , Ting Liu , Yuzhuo Fu

We study Transformers through the perspective of optimal control theory, using tools from continuous-time formulations to derive actionable insights into training and architecture design. This framework improves the performance of existing…

Machine Learning · Computer Science 2025-10-27 Kelvin Kan , Xingjian Li , Benjamin J. Zhang , Tuhin Sahai , Stanley Osher , Markos A. Katsoulakis

Dropout is typically interpreted as bagging a large number of models sharing parameters. We show that using dropout in a network can also be interpreted as a kind of data augmentation in the input space without domain knowledge. We present…

Machine Learning · Statistics 2016-01-11 Xavier Bouthillier , Kishore Konda , Pascal Vincent , Roland Memisevic