Image Classification

3712 papers with code • 165 benchmarks • 239 datasets

Image Classification is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike object detection, which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as image retrieval, which also involves finding similar images in a large database.

Source: Metamorphic Testing for Object Detection Systems

Libraries

Use these libraries to find Image Classification models and implementations

Most implemented papers

A Simple Framework for Contrastive Learning of Visual Representations

google-research/simclr ICML 2020

This paper presents SimCLR: a simple framework for contrastive learning of visual representations.

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

tensorflow/models 23 Feb 2016

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.

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

cbfinn/maml ICML 2017

We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning.

Squeeze-and-Excitation Networks

hujie-frank/SENet CVPR 2018

Squeeze-and-Excitation Networks formed the foundation of our ILSVRC 2017 classification submission which won first place and reduced the top-5 error to 2. 251%, surpassing the winning entry of 2016 by a relative improvement of ~25%.

Going Deeper with Convolutions

worksheets/0xbcd424d2 CVPR 2015

We propose a deep convolutional neural network architecture codenamed "Inception", which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC 2014).

Dynamic Routing Between Capsules

Sarasra/models NeurIPS 2017

We use the length of the activity vector to represent the probability that the entity exists and its orientation to represent the instantiation parameters.

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

tensorflow/models ECCV 2018

The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view, while the latter networks can capture sharper object boundaries by gradually recovering the spatial information.

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

tensorflow/models 11 Feb 2015

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.

Wide Residual Networks

szagoruyko/wide-residual-networks 23 May 2016

Deep residual networks were shown to be able to scale up to thousands of layers and still have improving performance.

mixup: Beyond Empirical Risk Minimization

facebookresearch/mixup-cifar10 ICLR 2018

We also find that mixup reduces the memorization of corrupt labels, increases the robustness to adversarial examples, and stabilizes the training of generative adversarial networks.