English
Related papers

Related papers: Orthogonal and Idempotent Transformations for Lear…

200 papers

Convolutional neural networks have become the main tools for processing two-dimensional data. They work well for images, yet convolutions have a limited receptive field that prevents its applications to more complex 2D tasks. We propose a…

Machine Learning · Computer Science 2020-10-06 Emīls Ozoliņš , Kārlis Freivalds , Agris Šostaks

The increasing size of neural networks has led to a growing demand for methods of efficient fine-tuning. Recently, an orthogonal fine-tuning paradigm was introduced that uses orthogonal matrices for adapting the weights of a pretrained…

Machine Learning · Computer Science 2024-06-17 Mikhail Gorbunov , Nikolay Yudin , Vera Soboleva , Aibek Alanov , Alexey Naumov , Maxim Rakhuba

Training recurrent neural networks (RNNs) is a hard problem due to degeneracies in the optimization landscape, a problem also known as vanishing/exploding gradients. Short of designing new RNN architectures, previous methods for dealing…

Neural and Evolutionary Computing · Computer Science 2020-02-11 A. Emin Orhan , Xaq Pitkow

Generative models, as a powerful technique for generation, also gradually become a critical tool for recognition tasks. However, in skeleton-based action recognition, the features obtained from existing pre-trained generative methods…

Computer Vision and Pattern Recognition · Computer Science 2024-10-29 Lilang Lin , Lehong Wu , Jiahang Zhang , Jiaying Liu

State-of-the-art deep learning systems often require large amounts of data and computation. For this reason, leveraging known or unknown structure of the data is paramount. Convolutional neural networks (CNNs) are successful examples of…

Computer Vision and Pattern Recognition · Computer Science 2020-12-07 Carlos Esteves

Transformer networks have become the preferred architecture for many tasks due to their state-of-the-art performance. However, the optimal way to implement residual connections in Transformer, which are essential for effective training, is…

Computation and Language · Computer Science 2023-05-01 Shufang Xie , Huishuai Zhang , Junliang Guo , Xu Tan , Jiang Bian , Hany Hassan Awadalla , Arul Menezes , Tao Qin , Rui Yan

Convolutional Neural Networks define an exceptionally powerful class of models, but are still limited by the lack of ability to be spatially invariant to the input data in a computationally and parameter efficient manner. In this work we…

Computer Vision and Pattern Recognition · Computer Science 2016-02-05 Max Jaderberg , Karen Simonyan , Andrew Zisserman , Koray Kavukcuoglu

The extraction of text in high quality is essential for text-based document analysis tasks like Document Classification or Named Entity Recognition. Unfortunately, this is not always ensured, as poor scan quality and the resulting artifacts…

Computer Vision and Pattern Recognition · Computer Science 2023-06-06 David Kreuzer , Michael Munz

Convolutional Neural Networks (CNNs) has revolutionized computer vision, but training very deep networks has been challenging due to the vanishing gradient problem. This paper explores Residual Networks (ResNet), introduced by He et al.…

Computer Vision and Pattern Recognition · Computer Science 2025-10-29 Xingyu Liu , Kun Ming Goh

Deep convolutional neural networks are hindered by training instability and feature redundancy towards further performance improvement. A promising solution is to impose orthogonality on convolutional filters. We develop an efficient…

Computer Vision and Pattern Recognition · Computer Science 2020-04-09 Jiayun Wang , Yubei Chen , Rudrasis Chakraborty , Stella X. Yu

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Machine Learning · Statistics 2026-03-18 Nuri Mert Vural , Alberto Bietti , Mahdi Soltanolkotabi , Denny Wu

Residual connections are one of the most important components in neural network architectures for mitigating the vanishing gradient problem and facilitating the training of much deeper networks. One possible explanation for how residual…

Machine Learning · Computer Science 2024-11-15 Sejik Park

Learning transformation invariant representations of visual data is an important problem in computer vision. Deep convolutional networks have demonstrated remarkable results for image and video classification tasks. However, they have…

Computer Vision and Pattern Recognition · Computer Science 2018-08-23 Renata Khasanova , Pascal Frossard

Learning rich and diverse representations is critical for the performance of deep convolutional neural networks (CNNs). In this paper, we consider how to use privileged information to promote inherent diversity of a single CNN model such…

Computer Vision and Pattern Recognition · Computer Science 2017-08-21 Yunpeng Chen , Xiaojie Jin , Jiashi Feng , Shuicheng Yan

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Patrick Esser , Robin Rombach , Björn Ommer

Transformer layers, which use an alternating pattern of multi-head attention and multi-layer perceptron (MLP) layers, provide an effective tool for a variety of machine learning problems. As the transformer layers use residual connections…

Machine Learning · Computer Science 2022-12-13 Yaofeng Desmond Zhong , Tongtao Zhang , Amit Chakraborty , Biswadip Dey

Enforcing orthonormal or isometric property for the weight matrices has been shown to enhance the training of deep neural networks by mitigating gradient exploding/vanishing and increasing the robustness of the learned networks. However,…

Machine Learning · Computer Science 2024-03-01 Zhen Qin , Xuwei Tan , Zhihui Zhu

Learning transformation invariant representations of visual data is an important problem in computer vision. Deep convolutional networks have demonstrated remarkable results for image and video classification tasks. However, they have…

Computer Vision and Pattern Recognition · Computer Science 2017-03-02 Renata Khasanova , Pascal Frossard

In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…

Machine Learning · Computer Science 2022-01-11 Calvin Murdock , George Cazenavette , Simon Lucey

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…

Machine Learning · Computer Science 2023-03-28 Quentin Fournier , Gaétan Marceau Caron , Daniel Aloise