Bird Species Categorization Using Pose Normalized Deep Convolutional Nets

Abstract

We propose an architecture for fine-grained visual categorization that approaches expert human performance in the classification of bird species. Our architecture first computes an estimate of the object's pose; this is used to compute local image features which are, in turn, used for classification. The features are computed by applying deep convolutional nets to image patches that are located and normalized by the pose. We perform an empirical study of a number of pose normalization schemes, including an investigation of higher order geometric warping functions. We propose a novel graph-based clustering algorithm for learning a compact pose normalization space. We perform a detailed investigation of state-of-the-art deep convolutional feature implementations and fine-tuning feature learning for fine-grained classification. We observe that a model that integrates lower-level feature layers with pose-normalized extraction routines and higher-level feature layers with unaligned image features works best. Our experiments advance state-of-the-art performance on bird species recognition, with a large improvement of correct classification rates over previous methods (75% vs. 55-65%).

References in corpus (1)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

Cited by in corpus (87)

• Pruning Convolutional Neural Networks for Resource Efficient Inference
• This Looks Like That: Deep Learning for Interpretable Image Recognition
• The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification
• Object-Part Attention Model for Fine-grained Image Classification
• Recent Advances in Convolutional Neural Networks
• Weakly Supervised Fine-Grained Image Categorization
• Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examples
• Fully Convolutional Attention Networks for Fine-Grained Recognition
• Mask-CNN: Localizing Parts and Selecting Descriptors for Fine-Grained Image Recognition
• Fast Fine-grained Image Classification via Weakly Supervised Discriminative Localization
• Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks
• Fine-grained Visual-textual Representation Learning
• Bilinear CNNs for Fine-grained Visual Recognition
• Spatial Transformer Networks
• A comparison of dense region detectors for image search and fine-grained classification
• Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularization
• Fine-grained pose prediction, normalization, and recognition
• Danish Fungi 2020 -- Not Just Another Image Recognition Dataset
• Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition
• Active and Continuous Exploration with Deep Neural Networks and Expected Model Output Changes
• Part Detector Discovery in Deep Convolutional Neural Networks
• Fine-grained Recognition Datasets for Biodiversity Analysis
• Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition
• Enhance the Motion Cues for Face Anti-Spoofing using CNN-LSTM Architecture
• HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks
• Fine-grained Categorization and Dataset Bootstrapping using Deep Metric Learning with Humans in the Loop
• The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition
• Structural Compression of Convolutional Neural Networks
• Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization
• Dynamic Computational Time for Visual Attention
• Cross-X Learning for Fine-Grained Visual Categorization
• Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition
• Crime Mapping from Satellite Imagery via Deep Learning
• Guided Zoom: Questioning Network Evidence for Fine-grained Classification
• Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization
• Look-into-Object: Self-supervised Structure Modeling for Object Recognition
• The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification
• Actions and Attributes from Wholes and Parts
• Knowledge-Embedded Representation Learning for Fine-Grained Image Recognition
• Joint Multi-Person Pose Estimation and Semantic Part Segmentation
• Fine-Grained Image Analysis with Deep Learning: A Survey
• DeepKSPD: Learning Kernel-matrix-based SPD Representation for Fine-grained Image Recognition
• One-to-many face recognition with bilinear CNNs
• Fine-grained Recognition in the Wild: A Multi-Task Domain Adaptation Approach
• Unsupervised Part Mining for Fine-grained Image Classification
• Deep Quantization: Encoding Convolutional Activations with Deep Generative Model
• Feature Boosting, Suppression, and Diversification for Fine-Grained Visual Classification
• An Out-of-the-box Full-network Embedding for Convolutional Neural Networks
• Learning Concept Embeddings with Combined Human-Machine Expertise
• Where to Focus: Deep Attention-based Spatially Recurrent Bilinear Networks for Fine-Grained Visual Recognition
• Geo-Aware Networks for Fine-Grained Recognition
• Part-Stacked CNN for Fine-Grained Visual Categorization
• Sparse, Collaborative, or Nonnegative Representation: Which Helps Pattern Classification?
• FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery
• Building Graph Representations of Deep Vector Embeddings
• Fine-grained visual recognition with salient feature detection
• Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition
• Pushing the Limits of Deep CNNs for Pedestrian Detection
• Your "Flamingo" is My "Bird": Fine-Grained, or Not
• Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding
• Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning
• Real Time Fine-Grained Categorization with Accuracy and Interpretability
• Data-driven Meta-set Based Fine-Grained Visual Classification
• Attribute-Aware Attention Model for Fine-grained Representation Learning
• RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition
• Convolutional Low-Resolution Fine-Grained Classification
• Sharpen Focus: Learning with Attention Separability and Consistency
• Learning a Discriminant Latent Space with Neural Discriminant Analysis
• Sequential Random Network for Fine-grained Image Classification
• Financial ticket intelligent recognition system based on deep learning
• One-Shot Fine-Grained Instance Retrieval
• DAF-NET: a saliency based weakly supervised method of dual attention fusion for fine-grained image classification
• Detecting Temporally Consistent Objects in Videos through Object Class Label Propagation
• Learning to Navigate for Fine-grained Classification
• Associating Multi-Scale Receptive Fields for Fine-grained Recognition
• Fine-Grained Visual Classification via Simultaneously Learning of Multi-regional Multi-grained Features
• Affine Non-negative Collaborative Representation Based Pattern Classification
• Salvage Reusable Samples from Noisy Data for Robust Learning
• Cascade one-vs-rest detection network for fine-grained recognition without part annotations
• Fine-grained Apparel Classification and Retrieval without rich annotations
• Generating Attention from Classifier Activations for Fine-grained Recognition
• Fine-Grained Classification of Pedestrians in Video: Benchmark and State of the Art
• REAPS: Towards Better Recognition of Fine-grained Images by Region Attending and Part Sequencing
• Subset Feature Learning for Fine-Grained Category Classification
• Scalable Annotation of Fine-Grained Categories Without Experts
• Vision Recognition using Discriminant Sparse Optimization Learning
• Weakly Supervised Keypoint Discovery