Browse SoTA > Computer Vision > Image Classification > Fine-Grained Image Classification

Fine-Grained Image Classification

45 papers with code · Computer Vision

The Fine-Grained Image Classification task focuses on differentiating between hard-to-distinguish object classes, such as species of birds, flowers, or animals; and identifying the makes or models of vehicles.

( Image credit: Looking for the Devil in the Details )

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Greatest papers with code

AutoAugment: Learning Augmentation Policies from Data

24 May 2018tensorflow/models

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.

FINE-GRAINED IMAGE CLASSIFICATION IMAGE AUGMENTATION

Deep Residual Learning for Image Recognition

CVPR 2016 tensorflow/models

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.

DOMAIN GENERALIZATION FINE-GRAINED IMAGE CLASSIFICATION IMAGE-TO-IMAGE TRANSLATION OBJECT DETECTION PERSON RE-IDENTIFICATION RETINAL OCT DISEASE CLASSIFICATION SEMANTIC SEGMENTATION

TResNet: High Performance GPU-Dedicated Architecture

30 Mar 2020rwightman/pytorch-image-models

In this work, we introduce a series of architecture modifications that aim to boost neural networks' accuracy, while retaining their GPU training and inference efficiency.

FINE-GRAINED IMAGE CLASSIFICATION MULTI-LABEL CLASSIFICATION OBJECT DETECTION

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

ICML 2019 rwightman/pytorch-image-models

Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available.

FINE-GRAINED IMAGE CLASSIFICATION NEURAL ARCHITECTURE SEARCH TRANSFER LEARNING

GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism

NeurIPS 2019 tensorflow/lingvo

Scaling up deep neural network capacity has been known as an effective approach to improving model quality for several different machine learning tasks.

Ranked #2 on Fine-Grained Image Classification on Birdsnap (using extra training data)

FINE-GRAINED IMAGE CLASSIFICATION MACHINE TRANSLATION

Learning to Navigate for Fine-grained Classification

ECCV 2018 osmr/imgclsmob

In consideration of intrinsic consistency between informativeness of the regions and their probability being ground-truth class, we design a novel training paradigm, which enables Navigator to detect most informative regions under the guidance from Teacher.

FINE-GRAINED IMAGE CLASSIFICATION

Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization

CVPR 2018 osmr/imgclsmob

Towards addressing this problem, we propose an iterative matrix square root normalization method for fast end-to-end training of global covariance pooling networks.

FINE-GRAINED IMAGE CLASSIFICATION FINE-GRAINED IMAGE RECOGNITION

Big Transfer (BiT): General Visual Representation Learning

ECCV 2020 google-research/big_transfer

We conduct detailed analysis of the main components that lead to high transfer performance.

 Ranked #1 on Image Classification on CIFAR-100 (using extra training data)

FEW-SHOT LEARNING FINE-GRAINED IMAGE CLASSIFICATION REPRESENTATION LEARNING

Gradient Centralization: A New Optimization Technique for Deep Neural Networks

ECCV 2020 lessw2020/Ranger-Deep-Learning-Optimizer

It has been shown that using the first and second order statistics (e. g., mean and variance) to perform Z-score standardization on network activations or weight vectors, such as batch normalization (BN) and weight standardization (WS), can improve the training performance.

FINE-GRAINED IMAGE CLASSIFICATION

Fixing the train-test resolution discrepancy

NeurIPS 2019 facebookresearch/FixRes

Conversely, when training a ResNeXt-101 32x48d pre-trained in weakly-supervised fashion on 940 million public images at resolution 224x224 and further optimizing for test resolution 320x320, we obtain a test top-1 accuracy of 86. 4% (top-5: 98. 0%) (single-crop).

 Ranked #1 on Image Classification on iNaturalist (using extra training data)

DATA AUGMENTATION FINE-GRAINED IMAGE CLASSIFICATION