Browse > Computer Vision > Image Classification

Image Classification

279 papers with code · Computer Vision

Image classification is the task of classifying images into various categories.

State-of-the-art leaderboards

Greatest papers with code

Learning Transferable Architectures for Scalable Image Recognition

CVPR 2018 tensorflow/models

In our experiments, we search for the best convolutional layer (or "cell") on the CIFAR-10 dataset and then apply this cell to the ImageNet dataset by stacking together more copies of this cell, each with their own parameters to design a convolutional architecture, named "NASNet architecture". For instance, a small version of NASNet also achieves 74% top-1 accuracy, which is 3.1% better than equivalently-sized, state-of-the-art models for mobile platforms.


The iNaturalist Species Classification and Detection Dataset

CVPR 2018 tensorflow/models

Existing image classification datasets used in computer vision tend to have a uniform distribution of images across object categories. To encourage further progress in challenging real world conditions we present the iNaturalist species classification and detection dataset, consisting of 859,000 images from over 5,000 different species of plants and animals.


MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

17 Apr 2017tensorflow/models

We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to build light weight deep neural networks.


Xception: Deep Learning with Depthwise Separable Convolutions

CVPR 2017 tensorflow/models

We present an interpretation of Inception modules in convolutional neural networks as being an intermediate step in-between regular convolution and the depthwise separable convolution operation (a depthwise convolution followed by a pointwise convolution). In this light, a depthwise separable convolution can be understood as an Inception module with a maximally large number of towers.


Wide Residual Networks

23 May 2016tensorflow/models

Deep residual networks were shown to be able to scale up to thousands of layers and still have improving performance. However, each fraction of a percent of improved accuracy costs nearly doubling the number of layers, and so training very deep residual networks has a problem of diminishing feature reuse, which makes these networks very slow to train.


Identity Mappings in Deep Residual Networks

16 Mar 2016tensorflow/models

Deep residual networks have emerged as a family of extremely deep architectures showing compelling accuracy and nice convergence behaviors. In this paper, we analyze the propagation formulations behind the residual building blocks, which suggest that the forward and backward signals can be directly propagated from one block to any other block, when using identity mappings as the skip connections and after-addition activation.


Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

23 Feb 2016tensorflow/models

Recently, the introduction of residual connections in conjunction with a more traditional architecture has yielded state-of-the-art performance in the 2015 ILSVRC challenge; its performance was similar to the latest generation Inception-v3 network. Here we give clear empirical evidence that training with residual connections accelerates the training of Inception networks significantly.


Deep Residual Learning for Image Recognition

CVPR 2016 tensorflow/models

We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.


Rethinking the Inception Architecture for Computer Vision

CVPR 2016 tensorflow/models

Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains in various benchmarks.


Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

11 Feb 2015tensorflow/models

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities.