中文
相关论文

相关论文: Studying Invariances of Trained Convolutional Neur…

200 篇论文

When seeing a new object, humans can immediately recognize it across different retinal locations: the internal object representation is invariant to translation. It is commonly believed that Convolutional Neural Networks (CNNs) are…

计算机视觉与模式识别 · 计算机科学 2021-10-13 Valerio Biscione , Jeffrey S. Bowers

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…

计算机视觉与模式识别 · 计算机科学 2018-11-01 Megha Srivastava , Kalanit Grill-Spector

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with…

计算机视觉与模式识别 · 计算机科学 2019-12-04 Xu Shen , Xinmei Tian , Anfeng He , Shaoyan Sun , Dacheng Tao

When seeing a new object, humans can immediately recognize it across different retinal locations: we say that the internal object representation is invariant to translation. It is commonly believed that Convolutional Neural Networks (CNNs)…

计算机视觉与模式识别 · 计算机科学 2020-11-25 Valerio Biscione , Jeffrey Bowers

An important goal in visual recognition is to devise image representations that are invariant to particular transformations. In this paper, we address this goal with a new type of convolutional neural network (CNN) whose invariance is…

计算机视觉与模式识别 · 计算机科学 2015-01-08 Julien Mairal , Piotr Koniusz , Zaid Harchaoui , Cordelia Schmid

Convolutional Neural Networks (CNNs) do not have a predictable recognition behavior with respect to the input resolution change. This prevents the feasibility of deployment on different input image resolutions for a specific model. To…

计算机视觉与模式识别 · 计算机科学 2020-07-14 Duo Li , Anbang Yao , Qifeng Chen

Convolutional Neural Networks (CNN) offer state of the art performance in various computer vision tasks. Many of those tasks require different subtypes of affine invariances (scale, rotational, translational) to image transformations.…

计算机视觉与模式识别 · 计算机科学 2023-10-13 Facundo Manuel Quiroga , Franco Ronchetti , Laura Lanzarini , Aurelio Fernandez-Bariviera

In this paper we propose integrating a priori knowledge into both design and training of convolutional neural networks (CNNs) to learn object representations that are invariant to affine transformations (i.e., translation, scale, rotation).…

计算机视觉与模式识别 · 计算机科学 2019-09-04 Xenju Xu , Guanghui Wang , Alan Sullivan , Ziming Zhang

Convolutional Neural Networks (ConvNets) have shown excellent results on many visual classification tasks. With the exception of ImageNet, these datasets are carefully crafted such that objects are well-aligned at similar scales. Naturally,…

计算机视觉与模式识别 · 计算机科学 2014-12-17 Angjoo Kanazawa , Abhishek Sharma , David Jacobs

We present a method for learning discriminative filters using a shallow Convolutional Neural Network (CNN). We encode rotation invariance directly in the model by tying the weights of groups of filters to several rotated versions of the…

计算机视觉与模式识别 · 计算机科学 2017-05-03 Diego Marcos , Michele Volpi , Devis Tuia

Convolutional Neural Networks (CNNs) dominate various computer vision tasks since Alex Krizhevsky showed that they can be trained effectively and reduced the top-5 error from 26.2 % to 15.3 % on the ImageNet large scale visual recognition…

计算机视觉与模式识别 · 计算机科学 2017-08-01 Martin Thoma

Convolution Neural Networks (CNNs) are widely used in medical image analysis, but their performance degrade when the magnification of testing images differ from the training images. The inability of CNNs to generalize across magnification…

图像与视频处理 · 电气工程与系统科学 2023-02-23 Pranav Jeevan , Nikhil Cherian Kurian , Amit Sethi

Convolutional Neural Networks (CNNs) are known to be brittle under various image transformations, including rotations, scalings, and changes of lighting conditions. We observe that the features of a transformed image are drastically…

计算机视觉与模式识别 · 计算机科学 2020-04-14 Shaohua Li , Xiuchao Sui , Jie Fu , Yong Liu , Rick Siow Mong Goh

Convolutional Neural Networks (CNNs) are state-of-the-art models for document image classification tasks. However, many of these approaches rely on parameters and architectures designed for classifying natural images, which differ from…

计算机视觉与模式识别 · 计算机科学 2017-08-11 Chris Tensmeyer , Tony Martinez

Training deep networks that generalize to a wide range of variations in test data is essential to building accurate and robust image classifiers. One standard strategy is to apply data augmentation to synthetically enlarge the training set.…

计算机视觉与模式识别 · 计算机科学 2020-06-29 Yunhan Zhao , Ye Tian , Charless Fowlkes , Wei Shen , Alan Yuille

Convolutional Neural Networks (CNNs) are commonly assumed to be invariant to small image transformations: either because of the convolutional architecture or because they were trained using data augmentation. Recently, several authors have…

计算机视觉与模式识别 · 计算机科学 2020-01-24 Aharon Azulay , Yair Weiss

Deep convolutional neural networks learn extremely powerful image representations, yet most of that power is hidden in the millions of deep-layer parameters. What exactly do these parameters represent? Recent work has started to analyse CNN…

计算机视觉与模式识别 · 计算机科学 2015-04-13 Xingchao Peng , Baochen Sun , Karim Ali , Kate Saenko

Convolutional neural networks (CNN's) are powerful and widely used tools. However, their interpretability is far from ideal. One such shortcoming is the difficulty of deducing a network's ability to generalize to unseen data. We use…

计算机视觉与模式识别 · 计算机科学 2019-10-21 Rickard Brüel Gabrielsson , Gunnar Carlsson

Deep convolutional neural networks are generally regarded as robust function approximators. So far, this intuition is based on perturbations to external stimuli such as the images to be classified. Here we explore the robustness of…

机器学习 · 计算机科学 2017-03-27 Nicholas Cheney , Martin Schrimpf , Gabriel Kreiman

Convolutional neural networks (CNNs) are the cutting edge model for supervised machine learning in computer vision. In recent years CNNs have outperformed traditional approaches in many computer vision tasks such as object detection, image…

神经与进化计算 · 计算机科学 2016-03-01 Nitzan Guberman
‹ 上一页 1 2 3 10 下一页 ›