English
Related papers

Related papers: Set Norm and Equivariant Skip Connections: Putting…

200 papers

Skip connection, is a widely-used technique to improve the performance and the convergence of deep neural networks, which is believed to relieve the difficulty in optimization due to non-linearity by propagating a linear component through…

Machine Learning · Computer Science 2021-05-18 Fenglin Liu , Xuancheng Ren , Zhiyuan Zhang , Xu Sun , Yuexian Zou

This work attempts to interpret modern deep (convolutional) networks from the principles of rate reduction and (shift) invariant classification. We show that the basic iterative gradient ascent scheme for optimizing the rate reduction of…

Machine Learning · Computer Science 2020-10-30 Kwan Ho Ryan Chan , Yaodong Yu , Chong You , Haozhi Qi , John Wright , Yi Ma

Recent advances in deep learning and Transformers have driven major breakthroughs in robotics by employing techniques such as imitation learning, reinforcement learning, and LLM-based multimodal perception and decision-making. However,…

In this work we propose a new neural network architecture that efficiently implements and learns general purpose set-equivariant functions. Such a function f maps a set of entities x = {x1, . . . , xn} from one domain to a set of same…

Machine Learning · Computer Science 2019-09-23 Roland Vollgraf

With the development of the financial industry, credit default prediction, as an important task in financial risk management, has received increasing attention. Traditional credit default prediction methods mostly rely on machine learning…

Risk Management · Quantitative Finance 2024-12-25 Yuhan Wang , Zhen Xu , Yue Yao , Jinsong Liu , Jiating Lin

In recent years, deep learning techniques have shown great success in various tasks related to inverse problems, where a target quantity of interest can only be observed through indirect measurements by a forward operator. Common approaches…

Numerical Analysis · Mathematics 2024-03-18 Matthias Beckmann , Nick Heilenkötter

Many successful deep learning architectures are equivariant to certain transformations in order to conserve parameters and improve generalization: most famously, convolution layers are equivariant to shifts of the input. This approach only…

Machine Learning · Computer Science 2021-03-31 Allan Zhou , Tom Knowles , Chelsea Finn

In this work we investigate how to achieve equivariance to input transformations in deep networks, purely from data, without being given a model of those transformations. Convolutional Neural Networks (CNNs), for example, are equivariant to…

Computer Vision and Pattern Recognition · Computer Science 2021-11-29 Jianbo Jiao , João F. Henriques

Many real-world problems, e.g. object detection, have outputs that are naturally expressed as sets of entities. This creates a challenge for traditional deep neural networks which naturally deal with structured outputs such as vectors,…

Computer Vision and Pattern Recognition · Computer Science 2018-10-03 S. Hamid Rezatofighi , Roman Kaskman , Farbod T. Motlagh , Qinfeng Shi , Daniel Cremers , Laura Leal-Taixé , Ian Reid

Dense depth and surface normal predictors should possess the equivariant property to cropping-and-resizing -- cropping the input image should result in cropping the same output image. However, we find that state-of-the-art depth and normal…

Computer Vision and Pattern Recognition · Computer Science 2023-10-18 Yuanyi Zhong , Anand Bhattad , Yu-Xiong Wang , David Forsyth

In recent years the use of convolutional layers to encode an inductive bias (translational equivariance) in neural networks has proven to be a very fruitful idea. The successes of this approach have motivated a line of research into…

Latent representations are used extensively for downstream tasks, such as visualization, interpolation or feature extraction of deep learning models. Invariant and equivariant neural networks are powerful and well-established models for…

Machine Learning · Computer Science 2025-01-16 Andreas Abildtrup Hansen , Anna Calissano , Aasa Feragen

Transformers have become the dominant architecture for sequence modeling tasks such as natural language processing or audio processing, and they are now even considered for tasks that are not naturally sequential such as image…

Machine Learning · Computer Science 2024-03-05 Jorg Bornschein , Yazhe Li , Amal Rannen-Triki

It is often said that a deep learning model is "invariant" to some specific type of transformation. However, what is meant by this statement strongly depends on the context in which it is made. In this paper we explore the nature of…

Machine Learning · Computer Science 2022-10-11 Henry Kvinge , Tegan H. Emerson , Grayson Jorgenson , Scott Vasquez , Timothy Doster , Jesse D. Lew

Learning from set-structured data, such as point clouds, has gained significant attention from the machine learning community. Geometric deep learning provides a blueprint for designing effective set neural networks that preserve the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Abihith Kothapalli , Ashkan Shahbazi , Xinran Liu , Robert Sheng , Soheil Kolouri

In the past few years, convolutional neural nets (CNN) have shown incredible promise for learning visual representations. In this paper, we use CNNs for the task of predicting surface normals from a single image. But what is the right…

Computer Vision and Pattern Recognition · Computer Science 2014-11-19 Xiaolong Wang , David F. Fouhey , Abhinav Gupta

Most set prediction models in deep learning use set-equivariant operations, but they actually operate on multisets. We show that set-equivariant functions cannot represent certain functions on multisets, so we introduce the more appropriate…

Machine Learning · Computer Science 2022-02-07 Yan Zhang , David W. Zhang , Simon Lacoste-Julien , Gertjan J. Burghouts , Cees G. M. Snoek

We present a generative model that is defined on finite sets of exchangeable, potentially high dimensional, data. As the architecture is an extension of RealNVPs, it inherits all its favorable properties, such as being invertible and…

Machine Learning · Computer Science 2019-09-09 Kashif Rasul , Ingmar Schuster , Roland Vollgraf , Urs Bergmann

Based on its great successes in inference and denosing tasks, Dictionary Learning (DL) and its related sparse optimization formulations have garnered a lot of research interest. While most solutions have focused on single layer…

Machine Learning · Computer Science 2021-04-22 Wen Tang , Emilie Chouzenoux , Jean-Christophe Pesquet , Hamid Krim

In many information processing systems, it may be desirable to ensure that any change of the input, whether by shifting or scaling, results in a corresponding change in the system response. While deep neural networks are gradually replacing…

Computer Vision and Pattern Recognition · Computer Science 2024-02-22 Sébastien Herbreteau , Emmanuel Moebel , Charles Kervrann