Part Detector Discovery in Deep Convolutional Neural Networks

Abstract

Current fine-grained classification approaches often rely on a robust localization of object parts to extract localized feature representations suitable for discrimination. However, part localization is a challenging task due to the large variation of appearance and pose. In this paper, we show how pre-trained convolutional neural networks can be used for robust and efficient object part discovery and localization without the necessity to actually train the network on the current dataset. Our approach called "part detector discovery" (PDD) is based on analyzing the gradient maps of the network outputs and finding activation centers spatially related to annotated semantic parts or bounding boxes. This allows us not just to obtain excellent performance on the CUB200-2011 dataset, but in contrast to previous approaches also to perform detection and bird classification jointly without requiring a given bounding box annotation during testing and ground-truth parts during training. The code is available at http://www.inf-cv.uni-jena.de/part_discovery and https://github.com/cvjena/PartDetectorDisovery.

Accepted for publication on Asian Conference on Computer Vision (ACCV) 2014

References in corpus (5)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• DeepPose: Human Pose Estimation via Deep Neural Networks
• CNN Features off-the-shelf: an Astounding Baseline for Recognition
• Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
• Learning Human Pose Estimation Features with Convolutional Networks

Cited by in corpus (17)

• ImageNet pre-trained models with batch normalization
• Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks
• Interpreting CNN Knowledge via an Explanatory Graph
• Harnessing Intrinsic Noise in Memristor Hopfield Neural Networks for Combinatorial Optimization
• Interpretable Convolutional Neural Networks
• The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition
• Interactively Transferring CNN Patterns for Part Localization
• Learning Semantic Part-Based Models from Google Images
• Growing Interpretable Part Graphs on ConvNets via Multi-Shot Learning
• Examining CNN Representations with respect to Dataset Bias
• Mining Object Parts from CNNs via Active Question-Answering
• Low-rank Bilinear Pooling for Fine-Grained Classification
• Explanatory Graphs for CNNs
• Mining Interpretable AOG Representations from Convolutional Networks via Active Question Answering
• Objects as context for detecting their semantic parts
• Spot that Bird: A Location Based Bird Game
• Fine-Grained Categorization via CNN-Based Automatic Extraction and Integration of Object-Level and Part-Level Features