Image Classification
Image classification is the task of classifying an image into a class category. It is the most well-known computer vision task. Famous benchmarks include the MNIST dataset, for handwritten digit classification, and ImageNet, a large-scale image dataset for object classification.
Models are typically evaluated with an Accuracy metric, for example Top 1 and Top 5 Accuracy for ImageNet.
( Image credit: GAL: A Global-Attributes Assisted Labeling System for Outdoor Scenes )
Leaderboards
| TREND | DATASET | BEST METHOD | PAPER TITLE | PAPER | CODE | COMPARE |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
Subtasks
Greatest papers with code
Searching for MobileNetV3
ICCV 2019
• tensorflow/models
• 
We achieve new state of the art results for mobile classification, detection and segmentation.
#112 best model for
Image Classification
on ImageNet
IMAGE CLASSIFICATION NEURAL ARCHITECTURE SEARCH OBJECT DETECTION SEMANTIC SEGMENTATION
Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
NeurIPS 2018
• tensorflow/models
•
Recent progress has demonstrated that such meta-learning methods may exceed scalable human-invented architectures on image classification tasks.
#2 best model for
Semantic Segmentation
on PASCAL VOC 2012 test
IMAGE CLASSIFICATION META-LEARNING SEMANTIC SEGMENTATION STREET SCENE PARSING
AutoAugment: Learning Augmentation Policies from Data
In our implementation, we have designed a search space where a policy consists of many sub-policies, one of which is randomly chosen for each image in each mini-batch.
SOTA for Image Classification on SVHN
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
ECCV 2018
• tensorflow/models
•
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.
IMAGE CLASSIFICATION LESION SEGMENTATION SEMANTIC SEGMENTATION
MobileNetV2: Inverted Residuals and Linear Bottlenecks
CVPR 2018
• tensorflow/models
•
In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes.
#117 best model for
Image Classification
on ImageNet
Progressive Neural Architecture Search
ECCV 2018
• tensorflow/models
•
We propose a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than recent state-of-the-art methods based on reinforcement learning and evolutionary algorithms.
#32 best model for
Image Classification
on ImageNet
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".
#33 best model for
Image Classification
on ImageNet
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.
#2 best model for
Image Classification
on iNaturalist
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
We present a class of efficient models called MobileNets for mobile and embedded vision applications.
#127 best model for
Image Classification
on ImageNet
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).
#69 best model for
Image Classification
on ImageNet