Fine-grained pose prediction, normalization, and recognition

Abstract

Pose variation and subtle differences in appearance are key challenges to fine-grained classification. While deep networks have markedly improved general recognition, many approaches to fine-grained recognition rely on anchoring networks to parts for better accuracy. Identifying parts to find correspondence discounts pose variation so that features can be tuned to appearance. To this end previous methods have examined how to find parts and extract pose-normalized features. These methods have generally separated fine-grained recognition into stages which first localize parts using hand-engineered and coarsely-localized proposal features, and then separately learn deep descriptors centered on inferred part positions. We unify these steps in an end-to-end trainable network supervised by keypoint locations and class labels that localizes parts by a fully convolutional network to focus the learning of feature representations for the fine-grained classification task. Experiments on the popular CUB200 dataset show that our method is state-of-the-art and suggest a continuing role for strong supervision.

References in corpus (4)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Multiple Object Recognition with Visual Attention
• Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
• Compact Bilinear Pooling

Cited by in corpus (16)

• Human pose estimation via Convolutional Part Heatmap Regression
• Trunk-Branch Ensemble Convolutional Neural Networks for Video-based Face Recognition
• Hierarchical binary CNNs for landmark localization with limited resources
• Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition
• From Plants to Landmarks: Time-invariant Plant Localization that uses Deep Pose Regression in Agricultural Fields
• Body Joint guided 3D Deep Convolutional Descriptors for Action Recognition
• Lightweight Real-time Makeup Try-on in Mobile Browsers with Tiny CNN Models for Facial Tracking
• Visual Concept Recognition and Localization via Iterative Introspection
• Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition
• Low-rank Bilinear Pooling for Fine-Grained Classification
• Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition
• Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning
• Real Time Fine-Grained Categorization with Accuracy and Interpretability
• Group Based Deep Shared Feature Learning for Fine-grained Image Classification
• Learning a Discriminant Latent Space with Neural Discriminant Analysis
• A CNN Cascade for Landmark Guided Semantic Part Segmentation