Corpus ID: 17041200

Weakly-supervised Discriminative Patch Learning via CNN for Fine-grained Recognition

  title={Weakly-supervised Discriminative Patch Learning via CNN for Fine-grained Recognition},
  author={Y. Wang and V. Morariu and L. Davis},
  • Y. Wang, V. Morariu, L. Davis
  • Published 2016
  • Computer Science
  • ArXiv
  • Research on fine-grained recognition has recently shifted from multistage frameworks to convolutional neural networks (CNN) that are trained end-to-end. [...] Key Method We achieve this by designing a novel asymmetric two-stream network architecture with supervision on convolutional filters and a nonrandom way of layer initialization. Experimental results show that our approach is able to find high-quality discriminative patches and achieves state-of-the-art on two publicly available fine-grained recognition…Expand Abstract
    9 Citations
    Selective Sparse Sampling for Fine-Grained Image Recognition
    • 12
    • PDF
    Fast Fine-Grained Image Classification via Weakly Supervised Discriminative Localization
    • 21
    • PDF
    Which and How Many Regions to Gaze: Focus Discriminative Regions for Fine-Grained Visual Categorization
    • 19
    Object-Part Attention Model for Fine-Grained Image Classification
    • 116
    • PDF
    FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery
    • 34
    • PDF


    Hyper-class augmented and regularized deep learning for fine-grained image classification
    • 123
    • PDF
    Fully Convolutional Attention Localization Networks: Efficient Attention Localization for Fine-Grained Recognition
    • 60
    • PDF
    Part-Based R-CNNs for Fine-Grained Category Detection
    • 714
    • PDF
    The application of two-level attention models in deep convolutional neural network for fine-grained image classification
    • 465
    • PDF
    Embedding Label Structures for Fine-Grained Feature Representation
    • 132
    • PDF
    Learning Deep Features for Discriminative Localization
    • 2,703
    • Highly Influential
    • PDF
    Part-Stacked CNN for Fine-Grained Visual Categorization
    • 208
    • Highly Influential
    • PDF
    Fine-grained recognition without part annotations
    • 325
    • PDF
    Fine-Grained Categorization and Dataset Bootstrapping Using Deep Metric Learning with Humans in the Loop
    • 147
    • PDF