lionroarroar/awesome-fine-grained-visual-classification

Awesome Fine-grained Visual Classification

Awesome Fine-grained Visual Classification

Awesome Fine-grained Visual Classification

• Survey
• Papers
• Paper Summary
• Recognition leaderboard
• Workshops
• Challenges or Competitions
• Datasets

---

Survey

• Fine-Grained Image Analysis with DeepLearning: A Survey (2021)
• Awesome Fine-Grained Image Analysis – Papers, Codes and Datasets
• Deep Learning for Fine-Grained Image Analysis: A Survey

---

Papers

2023

• [GIST] Generating Image-Specific Text for Fine-grained Object Classification (Arxiv, 2023) [paper]
• Leveraging Vision-Language Foundation Models for Fine-Grained Downstream Tasks (Arxiv, 2023) [paper]
• [M2Former] M2Former: Multi-Scale Patch Selection for Fine-Grained Visual Recognition (Arxiv, 2023) [paper]
• [SM-ViT] Salient Mask-Guided Vision Transformer for Fine-Grained Classification (VISAPP, 2023) [paper]

2022

• [DCAL] Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification (CVPR, 2022) [paper]
• [SR-GNN] SR-GNN: Spatial Relation-Aware Graph Neural Network for Fine-Grained Image Categorization (CVPR, 2022) [paper]
• [ViT-FOD] ViT-FOD: A Vision Transformer based Fine-grained Object Discriminator (arxiv, 2022) [paper]

2021

• [FFVT] Feature Fusion Vision Transformer. (arxiv, 2021) [paper]
• [TPSKG] Transformer with Peak Suppression and Knowledge Guidance. (arxiv, 2021) [paper]
• [RAMS-Trans] RAMS-Trans: Recurrent Attention Multi-scale Transformer for Fine-grained Image Recognition. (arxiv, 2021) [paper]
• Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification. (ICCV, 2021) [paper] [code]
• [TransFG] TransFG: A Transformer Architecture for Fine-grained Recognition. (arxiv, 2021)[paper][code]
• Graph-Based High-Order Relation Discovery for Fine-Grained Recognition. (CVPR, 2021)[paper][code]
• Your "Flamingo" is My "Bird": Fine-Grained, or Not (CVPR, 2021)[paper]
• Discrimination-Aware Mechanism for Fine-Grained Representation Learning (CVPR, 2021)[paper]
• Neural Prototype Trees for Interpretable Fine-Grained Image Recognition (CVPR, 2021) [paper]
• Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification (AAAI, 2021) [paper]
• Intra-class Part Swapping for Fine-Grained Image Classification (WACV, 2021) [paper]
• A free lunch from ViT:Adaptive Attention Multi-scale Fusion Transformer for Fine-grained Visual Recognition (arxiv, 2021) [paper]

2020

• Interpretable and Accurate Fine-grained Recognition via Region Grouping (CVPR, 2020) [paper]
• [LIO] Look-into-Object: Self-supervised Structure Modeling for Object Recognition (CVPR, 2020) [paper][code]
• Weakly Supervised Fine-Grained Image Classification via Guassian Mixture Model Oriented Discriminative Learning [paper] [video]
• Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization (CVPR, 2020) [paper][code]
• [CIN] Channel Interaction Networks for Fine-Grained Image Categorization (AAAI, 2020) [paper]
• Graph-propagation based Correlation Learning for Weakly Supervised Fine-grained Image Classification (AAAI, 2020)
• [FDL] Filtration and Distillation: Enhancing Region Attention for Fine-Grained Visual Categorization (AAAI, 2020) [paper]
• [API-Net] Learning Attentive Pairwise Interaction for Fine-Grained Classification (AAAI, 2020) [paper]
• [PMG] Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches (ECCV, 2020)[paper]
• [MC-loss] The Devil is in the Channels Mutual-Channel Loss for Fine-Grained Image Classification (TIP, 2020) [paper] [code]

2019

• [TASN] Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition (CVPR, 2019) [paper]
• Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up (CVPR, 2019)[paper]
• [Cross-X] Cross-X Learning for Fine-Grained Visual Categorization (ICCV, 2019) [paper]
• [DCL] Destruction and Construction Learning for Fine-grained Image Recognition (CVPR, 2019) [paper]
• [S3N] Selective Sparse Sampling for Fine-grained Image Recognition (ICCV, 2019) [paper] [code]
• [MGE-CNN] Learning a Mixture of Granularity-Specific Experts for Fine-GrainedCategorization (ICCV, 2019)[paper]
• [DBTNet-50] Learning Deep Bilinear Transformation for Fine-grained Image Representation (NeuIPS, 2019)[paper]

2018

• [MAMC] Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition (ECCV, 2018)[paper]
• [PC] Pairwise Confusion for Fine-Grained Visual Classification (ECCV, 2018) [paper]
• [WSBAN] Weakly Supervised Bilinear Attention Network for Fine-Grained Visual Classification (unknown, 2018) [paper]
• [NTS-Net] Learning to Navigate for Fine-grained Classification (ECCV, 2018) [paper] [code]
• [OPAM] Object-Part Attention Model for Fine-grained Image Classification (IEEE TIP, 2018) [paper]

2017

• [RA-CNN] Look Closer to See Better: Recurrent Attention Convolutional Neural Networkfor Fine-grained Image Recognition (CVPR, 2017) [paper]
• [MA-CNN] Learning Multi-Attention Convolutional Neural Network for Fine-GrainedImage Recognition (ICCV, 2017) [paper]
• [Cai $et~al.$] Higher-order Integration of Hierarchical Convolutional Activations for Fine-grained Visual Categorization (ICCV, 2017) [paper]
• [KP] Kernel Pooling for Convolutional Neural Networks (CVPR, 2017) [paper]

2016

• [C-BCNN] Compact Bilinear Pooling (CVPR,2016) [paper] [code]
• [SPDA-CNN] SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-grained Recognition (CVPR,2016) [paper]
• [PS-CNN] Part-Stacked CNN for Fine-Grained Visual Categorization (CVPR,2016) [paper]

2015

• [BCNN] Bilinear CNN Models for Fine-grained Visual Recognition (ICCV,2015) [paper] [code]
• [Krause $et~al.$] Fine-Grained Recognition without Part Annotations (CVPR,2015) [paper]
• [Deep LAC] Deep LAC: Deep Localization, Alignment and Classificationfor Fine-grained Recognition (CVPR,2015) [paper]
• [CL] The Treasure beneath Convolutional Layers：Cross-convolutional-layer Pooling for Image Classification (CVPR,2015) [paper]

2014

• [PB RCNN] Part-Based R-CNNs for Fine-Grained Category Detection (ECCV,2014) [paper]

---

Paper Summary

By localize and rescale techniques

• [PB R-CNN] Part-Based R-CNNs for Fine-Grained Category Detection (ECCV,2014) [paper]
• [Krause $et~al.$] Fine-Grained Recognition without Part Annotations (CVPR,2015) [paper]
• [Deep LAC] Deep LAC: Deep Localization, Alignment and Classificationfor Fine-grained Recognition (CVPR,2015) [paper]
• [PS-CNN] Part-Stacked CNN for Fine-Grained Visual Categorization (CVPR,2016) [paper]
• [SPDA-CNN] SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-grained Recognition (CVPR,2016) [paper]
• [RA-CNN] Look Closer to See Better: Recurrent Attention Convolutional Neural Networkfor Fine-grained Image Recognition (CVPR, 2017) [paper]
• [MA-CNN] Learning Multi-Attention Convolutional Neural Network for Fine-GrainedImage Recognition (ICCV, 2017) [paper]
• [NTS-Net] Learning to Navigate for Fine-grained Classification (ECCV, 2018) [paper] [code]
• [MGE-CNN] Learning a Mixture of Granularity-Specific Experts for Fine-GrainedCategorization (ICCV, 2019)[paper]
• [FDL] Filtration and Distillation: Enhancing Region Attention for Fine-Grained Visual Categorization (AAAI, 2020) [paper]

By metric learning

• [BCNN] Bilinear CNN Models for Fine-grained Visual Recognition (ICCV,2015) [paper] [code]
• [CL] The Treasure beneath Convolutional Layers：Cross-convolutional-layer Pooling for Image Classification (CVPR,2015) [paper]
• [C-BCNN] Compact Bilinear Pooling (CVPR,2016) [paper] [code]
• [Cai $et~al.$] Higher-order Integration of Hierarchical Convolutional Activations for Fine-grained Visual Categorization (ICCV, 2017) [paper]
• [KP] Kernel Pooling for Convolutional Neural Networks (CVPR, 2017) [paper]
• [MAMC] Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition (ECCV, 2018)[paper]
• [PC] Pairwise Confusion for Fine-Grained Visual Classification (ECCV, 2018) [paper]
• [DBTNet-50] Learning Deep Bilinear Transformation for Fine-grained Image Representation (NeuIPS, 2019)[paper]
• [CIN] Channel Interaction Networks for Fine-Grained Image Categorization (AAAI, 2020) [paper]
• [API-Net] Learning Attentive Pairwise Interaction for Fine-Grained Classification (AAAI, 2020) [paper]

By Attention-based methods

• [RA-CNN] Look Closer to See Better: Recurrent Attention Convolutional Neural Networkfor Fine-grained Image Recognition (CVPR, 2017) [paper]
• [MA-CNN] Learning Multi-Attention Convolutional Neural Network for Fine-GrainedImage Recognition (ICCV, 2017) [paper]
• [WSBAN] Weakly Supervised Bilinear Attention Network for Fine-Grained Visual Classification (unknown, 2018) [paper]
• [OPAM] Object-Part Attention Model for Fine-grained Image Classification (IEEE TIP, 2018) [paper]
• [Cross-X] Cross-X Learning for Fine-Grained Visual Categorization (ICCV, 2019) [paper]
• [TASN] Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition (CVPR, 2019) [paper]
• Interpretable and Accurate Fine-grained Recognition via Region Grouping (CVPR, 2020) [paper]
• Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization (CVPR, 2020) [paper][code]
• [SR-GNN] SR-GNN: Spatial Relation-Aware Graph Neural Network for Fine-Grained Image Categorization (CVPR, 2022) [paper]
• Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification. (ICCV, 2021) [paper] [code]

Transformer-based methods

• [TransFG] TransFG: A Transformer Architecture for Fine-grained Recognition. (arxiv, 2021)[paper][code]
• [FFVT] Feature Fusion Vision Transformer. (arxiv, 2021) [paper]
• [TPSKG] Transformer with Peak Suppression and Knowledge Guidance. (arxiv, 2021) [paper]
• [RAMS-Trans] RAMS-Trans: Recurrent Attention Multi-scale Transformer for Fine-grained Image Recognition. (arxiv, 2021) [paper]
• [ViT-FOD] ViT-FOD: A Vision Transformer based Fine-grained Object Discriminator (arxiv, 2022) [paper]

General Useful Mechanism

• Multi-Level. (e.g., PMG / Cross-X / MGE-CNN)
• Multi-Scale. (e.g., RA-CNN / MGE-CNN / NTS-Net/ TransFG (overlap-split) )

---

Recognition leaderboard

Method	Backbone	CUB(%)	CAR(%)	AIR(%)	DOG(%)
Krause $et~al.$	CaffeNet	75.7	-	-	-
PS-CNN	CaffeNet	76.6	-	-	-
CL	Alex-Net	73.5	-	-	-
PB R-CNN	Alex-Net	76.4	-	-	-
Deep LAC	Alex-Net	80.3	-	-	-
BCNN	VGG16+VGG-M	84.1	91.3	84.1	-
C-BCNN	VGG16	84.3	91.2	84.1	-
SPDA-CNN	VGG16	85.1	-	-	-
Cai $et~al.$	VGG16	85.3	91.7	88.3	-
OPAM	VGG16	85.8	92.2	-	-
KP	VGG16	86.2	92.4	86.9	-
DPTNet-50	VGG16	87.5	94.1	91.2	-
RA-CNN	VGG19	85.3	92.5	88.4	87.3
MA-CNN	VGG19	86.5	92.8	89.9	-
MAMC	ResNet101	86.5	93.0	-	85.2
PC	DenseNet161	86.9	92.9	89.2	83.8
FDL	DenseNet161	89.1	94.0	-	84.9
NTS-Net	ResNet50	87.5	93.9	91.4	-
Cross-X	ResNet50	87.7	94.6	-	88.9
S3N	ResNet50	88.5	94.7	92.8	-
DCL	ResNet50	87.8	94.5	93.0	-
TASN	ResNet50	87.9	93.8	-	-
PMG	ResNet50	89.6	95.1	93.4	-
CIN	ResNet50	88.1	94.5	92.8	-
API-Net	DenseNet161	90.0	95.3	93.9	89.4
LIO	ResNet50	88.0	94.5	92.7	-
TransFG	ViT-B/16	91.7	94.8	-	92.3
ViT_FOD	ViT-B/16	91.9	-	-	93.0

---

Workshops

• The Eight Workshop on Fine-Grained Visual Categorization

Challenges or Competitions

• ACCV 2020 Webly-Supervised Fine-Grained Recognition Challenge

Datasets

• CUB-200-2011
• Stanford Dogs
• Stanford Cars
• FGVC Aircrafts
• RP2K
• Products-10k

Feel free to contact me if you find any interesting paper is missing.

awesome-fine-grained-visual-classification's Issues

Some Question

作者你好，我最近在测试Hf-net的时候遇到一些问题，我在Sarlin的网页中看到了您的评估结果，可以添加一下我的联系方式吗，我的qq是1329237887，期待您的回复

Could add my implement for FGVC?

@LionRoarRoar

I'm implemented Latest Pytorch Version FGVC Model.
It'can be helpful research for FGVC.

Check below LINK

• Mixture-of-Granularity-Specific-Experts-for-Fine-Grained-Categorization
• Latest_Progressive-Multi-Granularity-Training-of-Jigsaw-Patches

add thank you for making additional useful materials.!