English
Related papers

Related papers: Learnable Polyphase Sampling for Shift Invariant a…

200 papers

Machine learning interatomic potentials (MLIPs) are an emerging modeling technique that promises to provide electronic structure theory accuracy for a fraction of its cost, however, the transferability of MLIPs is a largely unknown factor.…

Chemical Physics · Physics 2024-02-27 Tristan Maxson , Tibor Szilvasi

Pre-trained deep image representations are useful for post-training tasks such as classification through transfer learning, image retrieval, and object detection. Data augmentations are a crucial aspect of pre-training robust…

Computer Vision and Pattern Recognition · Computer Science 2023-02-23 Sangnie Bhardwaj , Willie McClinton , Tongzhou Wang , Guillaume Lajoie , Chen Sun , Phillip Isola , Dilip Krishnan

Tremendous progress has been made in visual representation learning, notably with the recent success of self-supervised contrastive learning methods. Supervised contrastive learning has also been shown to outperform its cross-entropy…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Ashraful Islam , Chun-Fu Chen , Rameswar Panda , Leonid Karlinsky , Richard Radke , Rogerio Feris

Deep neural networks have attained remarkable success across diverse classification tasks. Recent empirical studies have shown that deep networks learn features that are linearly separable across classes. However, these findings often lack…

Machine Learning · Computer Science 2026-03-20 Alec S. Xu , Can Yaras , Peng Wang , Qing Qu

Pooling is an important component in convolutional neural networks (CNNs) for aggregating features and reducing computational burden. Compared with other components such as convolutional layers and fully connected layers which are…

Computer Vision and Pattern Recognition · Computer Science 2017-06-19 Shuai Li , Wanqing Li , Chris Cook , Ce Zhu , Yanbo Gao

The translational equivariant nature of Convolutional Neural Networks (CNNs) is a reason for its great success in computer vision. However, networks do not enjoy more general equivariance properties such as rotation or scaling, ultimately…

Computer Vision and Pattern Recognition · Computer Science 2023-03-02 Zikai Sun , Thierry Blu

A novel learnable dictionary encoding layer is proposed in this paper for end-to-end language identification. It is inline with the conventional GMM i-vector approach both theoretically and practically. We imitate the mechanism of…

Audio and Speech Processing · Electrical Eng. & Systems 2018-04-03 Weicheng Cai , Zexin Cai , Xiang Zhang , Xiaoqi Wang , Ming Li

The success of existing deep-learning based multi-view stereo (MVS) approaches greatly depends on the availability of large-scale supervision in the form of dense depth maps. Such supervision, while not always possible, tends to hinder the…

Computer Vision and Pattern Recognition · Computer Science 2019-09-02 Yuchao Dai , Zhidong Zhu , Zhibo Rao , Bo Li

Disentanglement learning is central to understanding and reusing learned representations in variational autoencoders (VAEs). Although equivariance has been explored in this context, effectively exploiting it for disentanglement remains…

Machine Learning · Computer Science 2026-02-06 Hee-Jun Jung , Jaehyoung Jeong , Kangil Kim

Deep embeddings answer one simple question: How similar are two images? Learning these embeddings is the bedrock of verification, zero-shot learning, and visual search. The most prominent approaches optimize a deep convolutional network…

Computer Vision and Pattern Recognition · Computer Science 2018-01-17 Chao-Yuan Wu , R. Manmatha , Alexander J. Smola , Philipp Krähenbühl

Adapting pre-trained models with broad capabilities has become standard practice for learning a wide range of downstream tasks. The typical approach of fine-tuning different models for each task is performant, but incurs a substantial…

We propose a novel learning-based approach for robust 3D shape matching. Our method builds upon deep functional maps and can be trained in a fully unsupervised manner. Previous deep functional map methods mainly focus on predicting…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Dongliang Cao , Paul Roetzer , Florian Bernard

In recent years, deep neural networks have emerged as a solution for inverse imaging problems. These networks are generally trained using pairs of images: one degraded and the other of high quality, the latter being called 'ground truth'.…

Information Retrieval · Computer Science 2025-10-01 Victor Sechaud , Patrice Abry , Laurent Jacques , Julián Tachella

Abstract notions of convexity over the vertices of a graph, and corresponding notions of halfspaces, have recently gained attention from the machine learning community. In this work we study monophonic halfspaces, a notion of graph…

Machine Learning · Computer Science 2025-07-01 Marco Bressan , Victor Chepoi , Emmanuel Esposito , Maximilian Thiessen

In this paper we explore tying together the ideas from Scattering Transforms and Convolutional Neural Networks (CNN) for Image Analysis by proposing a learnable ScatterNet. Previous attempts at tying them together in hybrid networks have…

Computer Vision and Pattern Recognition · Computer Science 2019-03-11 Fergal Cotter , Nick Kingsbury

Local Hebbian learning is believed to be inferior in performance to end-to-end training using a backpropagation algorithm. We question this popular belief by designing a local algorithm that can learn convolutional filters at scale on large…

Computer Vision and Pattern Recognition · Computer Science 2019-08-27 Leopold Grinberg , John Hopfield , Dmitry Krotov

Over the last years, deep convolutional neural networks (ConvNets) have transformed the field of computer vision thanks to their unparalleled capacity to learn high level semantic image features. However, in order to successfully learn…

Computer Vision and Pattern Recognition · Computer Science 2018-03-22 Spyros Gidaris , Praveer Singh , Nikos Komodakis

Recognition of speech, and in particular the ability to generalize and learn from small sets of labelled examples like humans do, depends on an appropriate representation of the acoustic input. We formulate the problem of finding robust…

We introduce the Convolutional Conditional Neural Process (ConvCNP), a new member of the Neural Process family that models translation equivariance in the data. Translation equivariance is an important inductive bias for many learning…

Convolutional dictionary learning (CDL) estimates shift invariant basis adapted to multidimensional data. CDL has proven useful for image denoising or inpainting, as well as for pattern discovery on multivariate signals. As estimated…

Machine Learning · Computer Science 2019-01-29 Thomas Moreau , Alexandre Gramfort