Scribd Logo
Upload

Welcome to Scribd!

  • 68 views

    CS-671: Deep Learning and Its Applications Distance Metric Learning

    Uploaded by

    Shashi Kumar Fagna
    This document summarizes a lecture on distance metric learning and siamese networks. It discusses how siamese networks can be used to learn a similarity metric for matching pairs of images by using a shared CNN to encode each image, calculating the distance between encodings, and optimizing a contrastive loss on positive and negative image pairs. Specifically, it uses Euclidean distance for positive pairs and hinge loss for negative pairs to learn image embeddings that bring similar images together and separate different images by a margin. The siamese network architecture can be varied for different tasks based on empirical performance.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Flag for inappropriate content

    You might also like

    CS-671: Deep Learning and Its Applications Distance Metric Learning

    Uploaded by

    Shashi Kumar Fagna
    68 views15 pages
    This document summarizes a lecture on distance metric learning and siamese networks. It discusses how siamese networks can be used to learn a similarity metric for matching pairs of images by using a shared CNN to encode each image, calculating the distance between encodings, and optimizing a contrastive loss on positive and negative image pairs. Specifically, it uses Euclidean distance for positive pairs and hinge loss for negative pairs to learn image embeddings that bring similar images together and separate different images by a margin. The siamese network architecture can be varied for different tasks based on empirical performance.

    Original Description:

    Siamese Network Notes by Dr. Aditya Nigam

    Original Title

    Siamese_Network

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Report this Document
    This document summarizes a lecture on distance metric learning and siamese networks. It discusses how siamese networks can be used to learn a similarity metric for matching pairs of images by using a shared CNN to encode each image, calculating the distance between encodings, and optimizing a contrastive loss on positive and negative image pairs. Specifically, it uses Euclidean distance for positive pairs and hinge loss for negative pairs to learn image embeddings that bring similar images together and separate different images by a margin. The siamese network architecture can be varied for different tasks based on empirical performance.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as pdf or txt
    68 views15 pages

    CS-671: Deep Learning and Its Applications Distance Metric Learning

    Uploaded by

    Shashi Kumar Fagna
    This document summarizes a lecture on distance metric learning and siamese networks. It discusses how siamese networks can be used to learn a similarity metric for matching pairs of images by using a shared CNN to encode each image, calculating the distance between encodings, and optimizing a contrastive loss on positive and negative image pairs. Specifically, it uses Euclidean distance for positive pairs and hinge loss for negative pairs to learn image embeddings that bring similar images together and separate different images by a margin. The siamese network architecture can be varied for different tasks based on empirical performance.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as pdf or txt
    of 15

    CS-671: Deep Learning and its Applications

    Lecture: 16
    Distance metric learning

    Aditya Nigam, Assistant Professor


    School of Computing and Electrical Engineering (SCEE)
    Indian Institute of Technology, Mandi
    http://faculty.iitmandi.ac.in/ãditya/ aditya@iitmandi.ac.in

    Presentation for CS-671@IIT Mandi (16 April, 2019)


    (*Presented by : Daksh Thapar)

    February - May, 2019


    Need for Similarity Measures

    Several applications of Similarity Measures exist in today’s world.


    Handwriting recognition.

    Detection of faces in camera image.

    Aditya Nigam (SCEE, IIT-Mandi) aditya@iitmandi.ac.in Lecture, February - May, 2019


    Notion of a Metric

    A Metric is a function that quantifies a “distance00 between every


    pair of elements in a set, thus inducing a measure of similarity.

    A metric f (x, y ) must satisfy the following properties for all x, y , z


    belonging to the set:
    Non-negativity: f (x, y )0
    Identity of Discernible: f (x, y ) = 0 <=> x = y
    Symmetry: f (x, y ) = f (y , x)
    Triangle Inequality: f (x, z) <= f (x, y ) + f (y , z)

    Aditya Nigam (SCEE, IIT-Mandi) aditya@iitmandi.ac.in Lecture, February - May, 2019


    Traditional Approaches for Matching

    The traditional approach for matching images, relies on the following


    pipeline:
    1 Extract Features: For instance, color histograms of the input
    images.
    2 Learn Similarity: Use L1 − norm on the features.

    Challenges:
    The principal shortcoming of traditional metric learning based methods is
    that the feature representation of the data and the metric are not learned
    jointly.

    Aditya Nigam (SCEE, IIT-Mandi) aditya@iitmandi.ac.in Lecture, February - May, 2019


    Problem Statement

    Input: Given a pair of input images, we want to know how “similar”


    they are to each other.

    Output: The output can take a variety of forms:


    Either a binary label, i.e. 0 (same) or 1 (different).
    A Real number indicating how similar a pair of images are.

    Aditya Nigam (SCEE, IIT-Mandi) aditya@iitmandi.ac.in Lecture, February - May, 2019


    Siamese Networks

    Aditya Nigam (SCEE, IIT-Mandi) aditya@iitmandi.ac.in Lecture, February - May, 2019


    Siamese Networks as binary classification

    Aditya Nigam (SCEE, IIT-Mandi) aditya@iitmandi.ac.in Lecture, February - May, 2019


    Problem Statement

    Input: Given a pair of input images, we want to know how “similar”


    they are to each other.

    Output: The output can take a variety of forms:


    Either a binary label, i.e. 0 (same) or 1 (different).
    A Real number indicating how similar a pair of images are.
    d(img 1, img 2) = Degree of difference between images
    1 d(img 1, img 2) < t For images belonging to same class
    2 d(img 1, img 2) > t For images belonging to different class

    Aditya Nigam (SCEE, IIT-Mandi) aditya@iitmandi.ac.in Lecture, February - May, 2019


    Standard Siamese CNN

    Input: A pair of input images.


    Output: A label, 0 for similar, 1 else.

    Aditya Nigam (SCEE, IIT-Mandi) aditya@iitmandi.ac.in Lecture, February - May, 2019


    Siamese CNN - Loss Function

    Is there a problem with this formulation?

    Aditya Nigam (SCEE, IIT-Mandi) aditya@iitmandi.ac.in Lecture, February - May, 2019


    Siamese CNN - Loss Function

    Yes.
    The model could learn to embed every input to a same point i.e.
    predict a constant as output.
    In such a case, every pair of input would be categorized as positive pair.
    Aditya Nigam (SCEE, IIT-Mandi) aditya@iitmandi.ac.in Lecture, February - May, 2019
    Siamese CNN - Loss Function

    The final loss is defined as:

    L = Σloss of positive pairs + Σloss of negative pairs

    Aditya Nigam (SCEE, IIT-Mandi) aditya@iitmandi.ac.in Lecture, February - May, 2019


    Siamese CNN - Loss Function

    We can use different loss functions for the two types of inputs pairs.
    Typical positive pair (xp , xq ) loss: L(xp , xq ) = ||xp − xq ||2
    (Euclidean Loss)

    Aditya Nigam (SCEE, IIT-Mandi) aditya@iitmandi.ac.in Lecture, February - May, 2019


    Siamese CNN - Loss Function

    Typical negative pair (xn , xq ) loss:


    L(xn , xq ) = max(0, m2 − ||xn − xq ||2 ) (Hinge Loss)

    Aditya Nigam (SCEE, IIT-Mandi) aditya@iitmandi.ac.in Lecture, February - May, 2019


    Architecture Varieties

    Design largely governed by what performs well empirically on the task


    at hand.

    Aditya Nigam (SCEE, IIT-Mandi) aditya@iitmandi.ac.in Lecture, February - May, 2019

    You might also like