IEEE Transactions on Pattern Analysis and Machine Intelligence · 2019 · 128 citations · 53 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionDeep LearningFeature DetectionObject DetectionObject RecognitionRepresentation LearningScene UnderstandingConvolutional Neural NetworksFine-grained Image ClassificationFine-grained Visual RecognitionFocal LossObject ClassificationObject Part DetectionPart LocalizationPart-based Object Recognition
This paper proposes an end-to-end fine-grained visual categorization system, termed Part-based Convolutional Neural Network (P-CNN), which consists of three modules. The first module is a Squeeze-and-Excitation (SE) block, which learns to recalibrate channel-wise feature responses by emphasizing informative channels and suppressing less useful ones. The second module is a Part Localization Network (PLN) used to locate distinctive object parts, through which a bank of convolutional filters are learned as discriminative part detectors. Thus, a group of informative parts can be discovered by convolving the feature maps with each part detector. The third module is a Part Classification Network (PCN) that has two streams. The first stream classifies each individual object part into image-level categories. The second stream concatenates part features and global feature into a joint feature for the final classification. In order to learn powerful part features and boost the joint feature capability, we propose a Duplex Focal Loss used for metric learning and part classification, which focuses on training hard examples. We further merge PLN and PCN into a unified network for an end-to-end training process via a simple training technique. Comprehensive experiments and comparisons with state-of-the-art methods on three benchmark datasets demonstrate the effectiveness of our proposed method.
53
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Ross Girshick, Jeff Donahue, Trevor Darrell et al. · 2014 · 31.8K citations
Squeeze-and-Excitation Networks
Learning Deep Features for Discriminative Localization
Bolei Zhou, Aditya Khosla, Àgata Lapedriza et al. · 2016 · 10.8K citations · Full text
Caltech-UCSD Birds-200-2011 Dataset
Catherine Wah · CaltechAUTHORS (California Institute of Technology) · 2024 · 3.9K citations · Full text
3D Object Representations for Fine-Grained Categorization
Jonathan Krause, Michael Stark, Jia Deng et al. · 2013 · 3.4K citations