English
Related papers

Related papers: Trainable Spectrally Initializable Matrix Transfor…

200 papers

Convolutional neural networks are based on a huge number of trained weights. Consequently, they are often data-greedy, sensitive to overtraining, and learn slowly. We follow the line of research in which filters of convolutional neural…

Neural and Evolutionary Computing · Computer Science 2020-04-08 Karol Chęciński , Paweł Wawrzyński

It is notoriously difficult to train Transformers on small datasets; typically, large pre-trained models are instead used as the starting point. We explore the weights of such pre-trained Transformers (particularly for vision) to attempt to…

Computer Vision and Pattern Recognition · Computer Science 2023-05-18 Asher Trockman , J. Zico Kolter

Transformer-based models are at the forefront in long time-series forecasting (LTSF). While in many cases, these models are able to achieve state of the art results, they suffer from a bias toward low-frequencies in the data and high…

Machine Learning · Computer Science 2026-05-13 Elisha Dayag , Nhat Thanh Van Tran , Jack Xin

Neural painting refers to the procedure of producing a series of strokes for a given image and non-photo-realistically recreating it using neural networks. While reinforcement learning (RL) based agents can generate a stroke sequence step…

Computer Vision and Pattern Recognition · Computer Science 2021-08-12 Songhua Liu , Tianwei Lin , Dongliang He , Fu Li , Ruifeng Deng , Xin Li , Errui Ding , Hao Wang

Parameter fine tuning is a transfer learning approach whereby learned parameters from pre-trained source network are transferred to the target network followed by fine-tuning. Prior research has shown that this approach is capable of…

Computer Vision and Pattern Recognition · Computer Science 2019-09-20 Tasfia Shermin , Shyh Wei Teng , Manzur Murshed , Guojun Lu , Ferdous Sohel , Manoranjan Paul

We develop a theory of transfer learning in infinitely wide neural networks under gradient flow that quantifies when pretraining on a source task improves generalization on a target task. We analyze both (i) fine-tuning, when the downstream…

Machine Learning · Computer Science 2026-02-25 Clarissa Lauditi , Blake Bordelon , Cengiz Pehlevan

As object recognition becomes an increasingly common ML task, and recent research demonstrating CNNs vulnerability to attacks and small image perturbations necessitate fully understanding the foundations of object recognition. We focus on…

Computer Vision and Pattern Recognition · Computer Science 2018-11-01 Megha Srivastava , Kalanit Grill-Spector

Owing to success in the data-rich domain of natural images, Transformers have recently become popular in medical image segmentation. However, the pairing of Transformers with convolutional blocks in varying architectural permutations leaves…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Saikat Roy , Gregor Koehler , Michael Baumgartner , Constantin Ulrich , Jens Petersen , Fabian Isensee , Klaus Maier-Hein

Within the graph learning community, conventional wisdom dictates that spectral convolutional networks may only be deployed on undirected graphs: Only there could the existence of a well-defined graph Fourier transform be guaranteed, so…

Machine Learning · Computer Science 2023-11-13 Christian Koke , Daniel Cremers

We introduce inverse transport networks as a learning architecture for inverse rendering problems where, given input image measurements, we seek to infer physical scene parameters such as shape, material, and illumination. During training,…

Computer Vision and Pattern Recognition · Computer Science 2018-10-01 Chengqian Che , Fujun Luan , Shuang Zhao , Kavita Bala , Ioannis Gkioulekas

Graph Neural Networks (GNNs) are the dominant architecture for molecular machine learning, particularly for molecular property prediction and machine learning interatomic potentials (MLIPs). GNNs perform message passing on predefined graphs…

Machine Learning · Computer Science 2025-10-03 Tobias Kreiman , Yutong Bai , Fadi Atieh , Elizabeth Weaver , Eric Qu , Aditi S. Krishnapriyan

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

We identify and overcome two key obstacles in extending the success of BERT-style pre-training, or the masked image modeling, to convolutional networks (convnets): (i) convolution operation cannot handle irregular, random-masked input…

Computer Vision and Pattern Recognition · Computer Science 2023-01-11 Keyu Tian , Yi Jiang , Qishuai Diao , Chen Lin , Liwei Wang , Zehuan Yuan

Convolutional Neural Networks (CNNs) have shown impressive performance in computer vision tasks such as image classification, detection, and segmentation. Moreover, recent work in Generative Adversarial Networks (GANs) has highlighted the…

Machine Learning · Computer Science 2021-01-06 Samarth Sinha , Animesh Garg , Hugo Larochelle

Deep neural networks are typically initialized with random weights, with variances chosen to facilitate signal propagation and stable gradients. It is also believed that diversity of features is an important property of these…

Machine Learning · Computer Science 2020-07-03 Yaniv Blumenfeld , Dar Gilboa , Daniel Soudry

Spectral bias, the tendency of neural networks to learn low-frequency features first, is a well-known issue with many training algorithms for physics-informed neural networks (PINNs). To overcome this issue, we propose IFeF-PINN, an…

Machine Learning · Computer Science 2025-10-23 Yulun Wu , Miguel Aguiar , Karl H. Johansson , Matthieu Barreau

This paper focuses on regularizing the training of the convolutional neural network (CNN). We propose a new regularization approach named ``PatchShuffle`` that can be adopted in any classification-oriented CNN models. It is easy to…

Computer Vision and Pattern Recognition · Computer Science 2017-07-25 Guoliang Kang , Xuanyi Dong , Liang Zheng , Yi Yang

Exploiting data invariances is crucial for efficient learning in both artificial and biological neural circuits. Understanding how neural networks can discover appropriate representations capable of harnessing the underlying symmetries of…

Disordered Systems and Neural Networks · Physics 2022-10-17 Alessandro Ingrosso , Sebastian Goldt

Feature transformation plays a critical role in enhancing machine learning model performance by optimizing data representations. Recent state-of-the-art approaches address this task as a continuous embedding optimization problem, converting…

Machine Learning · Computer Science 2025-08-29 Yang Gao , Dongjie Wang , Scott Piersall , Ye Zhang , Liqiang Wang

We show how bidirectional transformers trained for masked token prediction can be applied to neural image compression to achieve state-of-the-art results. Such models were previously used for image generation by progressivly sampling groups…

Image and Video Processing · Electrical Eng. & Systems 2023-04-18 Fabian Mentzer , Eirikur Agustsson , Michael Tschannen
‹ Prev 1 8 9 10 Next ›