Fine-Grained Image Analysis with Deep Learning: A Survey
arXiv:2111.06119
Abstract
Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications. The task of FGIA targets analyzing visual objects from subordinate categories, e.g., species of birds or models of cars. The small inter-class and large intra-class variation inherent to fine-grained image analysis makes it a challenging problem. Capitalizing on advances in deep learning, in recent years we have witnessed remarkable progress in deep learning powered FGIA. In this paper we present a systematic survey of these advances, where we attempt to re-define and broaden the field of FGIA by consolidating two fundamental fine-grained research areas -- fine-grained image recognition and fine-grained image retrieval. In addition, we also review other key issues of FGIA, such as publicly available benchmark datasets and related domain-specific applications. We conclude by highlighting several research directions and open problems which need further exploration from the community.
arXiv commentAccepted by IEEE TPAMI
References in corpus (24)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Neural Architecture Search: A Survey
- Fine-Grained Visual Classification of Aircraft
- Deep Face Recognition: A Survey
- The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification
- Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
- Object-Part Attention Model for Fine-grained Image Classification
- Human-in-the-loop Artificial Intelligence
- Weakly Supervised Fine-Grained Image Categorization
- A survey of advances in vision-based vehicle re-identification
- Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examples
- RPC: A Large-Scale Retail Product Checkout Dataset
- Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization
- Multi-Objective Matrix Normalization for Fine-grained Visual Recognition
- Fast Fine-grained Image Classification via Weakly Supervised Discriminative Localization
- A New Benchmark and Approach for Fine-grained Cross-media Retrieval
- Learning Deep Bilinear Transformation for Fine-grained Image Representation
- Deep Spatial Pyramid: The Devil is Once Again in the Details
- Visual Interpretability for Deep Learning: a Survey
- Products-10K: A Large-scale Product Recognition Dataset
- Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition
- Measuring Dataset Granularity
- Your "Flamingo" is My "Bird": Fine-Grained, or Not
- Enhancing camera surveillance using computer vision: a research note