$30 off During Our Annual Pro Sale. View Details »

Good Old Pretraining for Landmark Recognition

Good Old Pretraining for Landmark Recognition

Cookpad Bristol

June 16, 2019
Tweet

More Decks by Cookpad Bristol

Other Decks in Research

Transcript

  1. CVPR'19 Landmark Recognition Workshop
    5th Place: Good Old Pretraining (with New Tricks)
    Daniel Fernandez, Andrey Ponikar and Mikhail Fain (Cookpad Ltd.)
    1. Landmark-Not-Landmark classifier
    2. Pretraining SE-ResNeXt-101
    3. Training and inference for 140K common classes
    Manually tag 100
    images as landmarks of
    X different types, or not
    landmarks, using active
    learning techniques
    Retrain top layer of
    ResNet-50 with
    cross-entropy loss
    Landmark-Not-Landmark
    Classifier
    Repeat 10 times
    4MM training
    images,
    200K classes
    Filter out rare
    classes, with
    <25 images
    Filter non-landmarks
    and cluster the
    images using
    ImageNet-based
    features. For each
    class, keep only
    images belonging to
    largest cluster
    600K training
    images, 10K
    classes
    Train
    SE-ResNeXt-101
    with softmax
    cross-entropy
    Feature extractor
    (the layer before
    last)
    Image
    Feature extractors
    (fixed)
    (size 4000x1)
    FC
    (4000x1)
    FC (375x64)
    MatMul
    (375x375)
    FC (64x375)
    Reshape
    (140Kx1)
    FC
    (4000x1)
    Factorized version of FC (140Kx1), to
    regularize and allow larger batch sizes
    Landmark classifier
    (fixed)
    Softmax
    Splitting stage 2 and 3 allowed rapid
    experimentation since features are precomputed
    A bit of manual effort for landmark labeling goes a
    long way, helping with data cleanup and calibrating
    the probabilities for GAP metric
    With appropriate regularization, softmax
    cross-entropy on top of precomputed features is
    still competitive on this task
    The final model is a blend of models with the same
    pipeline as described but minor tweaks (different
    feature extractors, clustering etc.)
    Top-1
    Multiply
    probabilities
    Class and
    probability
    Main Takeaways
    Training: for Stage 3
    model we used
    logarithmic sampling
    scheme with softmax
    cross-entropy as a
    loss function

    View Slide