相关论文: CINIC-10 is not ImageNet or CIFAR-10

Image classification is a fundamental task in computer vision with diverse applications, ranging from autonomous systems to medical imaging. The CIFAR-10 dataset is a widely used benchmark to evaluate the performance of classification…

The original ImageNet dataset is a popular large-scale benchmark for training Deep Neural Networks. Since the cost of performing experiments (e.g, algorithm design, architecture search, and hyperparameter tuning) on the original dataset…

Image classification requires the generation of features capable of detecting image patterns informative of group identity. The objective of this study was to classify images from the public CIFAR-10 image dataset by leveraging combinations…

This project performed image completion on CIFAR-10, a dataset of 60,000 32x32 RGB images, using three different neural network architectures: fully convolutional networks, convolutional networks with fully connected layers, and…

ResNets (or Residual Networks) are one of the most commonly used models for image classification tasks. In this project, we design and train a modified ResNet model for CIFAR-10 image classification. In particular, we aimed at maximizing…

The CIFAR-10 and CIFAR-100 datasets are two of the most heavily benchmarked datasets in computer vision and are often used to evaluate novel methods and model architectures in the field of deep learning. However, we find that 3.3% and 10%…

Analyzing model performance in various unseen environments is a critical research problem in the machine learning community. To study this problem, it is important to construct a testbed with out-of-distribution test sets that have broad…

This paper presents our proposed approach that won the first prize at the ICLR competition on Hardware Aware Efficient Training. The challenge is to achieve the highest possible accuracy in an image classification task in less than 10…

This article demonstrates a new conceptor network based classifier in classifying images. Mathematical descriptions and analysis are presented. Various tests are experimented using three benchmark datasets: MNIST, CIFAR-10 and CIFAR-100.…

In this paper, we study the performance of different classifiers on the CIFAR-10 dataset, and build an ensemble of classifiers to reach a better performance. We show that, on CIFAR-10, K-Nearest Neighbors (KNN) and Convolutional Neural…

Convolutional neural networks for visual recognition require large amounts of training samples and usually benefit from data augmentation. This paper proposes PatchMix, a data augmentation method that creates new samples by composing…

Datasets (semi-)automatically collected from the web can easily scale to millions of entries, but a dataset's usefulness is directly related to how clean and high-quality its examples are. In this paper, we describe and publicly release an…

Large datasets have been crucial to the success of deep learning models in the recent years, which keep performing better as they are trained with more labelled data. While there have been sustained efforts to make these models more…

In recent years, deep learning methods have been successfully applied to image classification tasks. Many such deep neural networks exist today that can easily differentiate cats from dogs. One such model is the ResNeXt model that uses a…

Residual Neural Networks [1] won first place in all five main tracks of the ImageNet and COCO 2015 competitions. This kind of network involves the creation of pluggable modules such that the output contains a residual from the input. The…

ImageNet is a large scale and publicly available image database. It currently offers more than 14 millions of images, organised according to the WordNet hierarchy. One of the main objective of the creators is to provide to the research…

PixelCNNs are a recently proposed class of powerful generative models with tractable likelihood. Here we discuss our implementation of PixelCNNs which we make available at https://github.com/openai/pixel-cnn. Our implementation contains a…

Recent technological advances in synthetic data have enabled the generation of images with such high quality that human beings cannot tell the difference between real-life photographs and Artificial Intelligence (AI) generated images. Given…

Current infrared and visible image fusion (IVIF) methods go to great lengths to excavate complementary features and design complex fusion strategies, which is extremely challenging. To this end, we rethink the IVIF outside the box,…

A wide range of scientific imaging datasets benefit from human inspection for purposes ranging from prosaic-such as fault identification and quality inspection-to profound, enabling the discovery of new phenomena. As such, these datasets…