Fine-Grained Image Classification
173 papers with code • 35 benchmarks • 36 datasets
Fine-Grained Image Classification is a task in computer vision where the goal is to classify images into subcategories within a larger category. For example, classifying different species of birds or different types of flowers. This task is considered to be fine-grained because it requires the model to distinguish between subtle differences in visual appearance and patterns, making it more challenging than regular image classification tasks.
( Image credit: Looking for the Devil in the Details )
Benchmarks
These leaderboards are used to track progress in Fine-Grained Image Classification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Fine-Grained Image Classification models and implementationsDatasets
MNIST
CUB-200-2011
Oxford 102 Flower
STL-10
Stanford Cars
Food-101
Caltech-101
iNaturalist
FGVC-Aircraft
EMNIST
Most implemented papers
See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification
Specifically, for each training image, we first generate attention maps to represent the object's discriminative parts by weakly supervised learning.
Presence-Only Geographical Priors for Fine-Grained Image Classification
gengchenmai/space2vec
•
•
ICCV 2019
Appearance information alone is often not sufficient to accurately differentiate between fine-grained visual categories.
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
In this paper, we leverage a noisy dataset of over one billion image alt-text pairs, obtained without expensive filtering or post-processing steps in the Conceptual Captions dataset.
ImageNet-21K Pretraining for the Masses
ImageNet-1K serves as the primary dataset for pretraining deep learning models for computer vision tasks.
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations
lightly-ai/lightly
•
•
ICCV 2021
On semi-supervised learning benchmarks we improve performance significantly when only 1% ImageNet labels are available, from 53. 8% to 56. 5%.
A Large-Scale Car Dataset for Fine-Grained Categorization and Verification
Updated on 24/09/2015: This update provides preliminary experiment results for fine-grained classification on the surveillance data of CompCars.
Learning Multi-Attention Convolutional Neural Network for Fine-Grained Image Recognition
Two losses are proposed to guide the multi-task learning of channel grouping and part classification, which encourages MA-CNN to generate more discriminative parts from feature channels and learn better fine-grained features from parts in a mutual reinforced way.
Fixing the train-test resolution discrepancy
facebookresearch/FixRes
•
•
NeurIPS 2019
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).
Are These Birds Similar: Learning Branched Networks for Fine-grained Representations
nicolalandro/ntsnet-cub200
•
•
In recent years, natural language descriptions are used to obtain information on discriminative parts of the object.
The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification
dongliangchang/Mutual-Channel-Loss
•
•
The proposed loss function, termed as mutual-channel loss (MC-Loss), consists of two channel-specific components: a discriminality component and a diversity component.
