Weakly Supervised Fine-Grained Image Categorization

Abstract

In this paper, we categorize fine-grained images without using any object / part annotation neither in the training nor in the testing stage, a step towards making it suitable for deployments. Fine-grained image categorization aims to classify objects with subtle distinctions. Most existing works heavily rely on object / part detectors to build the correspondence between object parts by using object or object part annotations inside training images. The need for expensive object annotations prevents the wide usage of these methods. Instead, we propose to select useful parts from multi-scale part proposals in objects, and use them to compute a global image representation for categorization. This is specially designed for the annotation-free fine-grained categorization task, because useful parts have shown to play an important role in existing annotation-dependent works but accurate part detectors can be hardly acquired. With the proposed image representation, we can further detect and visualize the key (most discriminative) parts in objects of different classes. In the experiment, the proposed annotation-free method achieves better accuracy than that of state-of-the-art annotation-free and most existing annotation-dependent methods on two challenging datasets, which shows that it is not always necessary to use accurate object / part annotations in fine-grained image categorization.

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
• DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection
• A comparison of dense region detectors for image search and fine-grained classification
• Fine-grained Recognition Datasets for Biodiversity Analysis
• Fisher Kernel for Deep Neural Activations

Cited by in corpus (29)

• Object-Part Attention Model for Fine-grained Image Classification
• Recent Advances in Convolutional Neural Networks
• Delving Deep into Label Smoothing
• Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification
• Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examples
• Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs
• Fully Convolutional Attention Networks for Fine-Grained Recognition
• SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization
• Fast Fine-grained Image Classification via Weakly Supervised Discriminative Localization
• Fine-grained Visual-textual Representation Learning
• Fine-Grained 3D Shape Classification with Hierarchical Part-View Attentions
• Unsupervised Semantic-based Aggregation of Deep Convolutional Features
• Fine-grained Discriminative Localization via Saliency-guided Faster R-CNN
• Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval
• Object Discovery From a Single Unlabeled Image by Mining Frequent Itemset With Multi-scale Features
• Part-Aware Fine-grained Object Categorization using Weakly Supervised Part Detection Network
• Embedding Deep Networks into Visual Explanations
• The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition
• Fine-Grained Image Analysis with Deep Learning: A Survey
• Unsupervised Part Mining for Fine-grained Image Classification
• Visual Concept Recognition and Localization via Iterative Introspection
• Parsing Objects at a Finer Granularity: A Survey
• Your "Flamingo" is My "Bird": Fine-Grained, or Not
• Data-driven Meta-set Based Fine-Grained Visual Classification
• Group Based Deep Shared Feature Learning for Fine-grained Image Classification
• The State of Lifelong Learning in Service Robots: Current Bottlenecks in Object Perception and Manipulation
• Fine-Grained Few Shot Learning with Foreground Object Transformation
• Interactive Open-Ended Learning for 3D Object Recognition
• Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data