Image Compression with Neural Networks

Nowadays many apps and social networking sites are dealing with large number of images which lead to huge storage cost and problem in surfacing those images on client machine in case of bad/low network speed. In this talk we will present how can we achieve low bpp using RNNs.

 
 

Outline/Structure of the Talk

  • Introduction [2 min]
  • Architecture of network [3 min]
  • Reconstruction framework [5 min]
  • Entropy encoding [7 min]
  • Support in client libraries [3 min]

Learning Outcome

Participants will learn about image data pre-processing, how encoder decoder network works and transfer learning.

Target Audience

Anyone who is interested in practical application of deep learning techniques.

Prerequisites for Attendees

Knowledge of basic machine learning techniques.

schedule Submitted 1 year ago

Public Feedback

comment Suggest improvements to the Speaker
  • Venkatraman J
    By Venkatraman J  ~  1 year ago
    reply Reply

    Hi Rohit,

    Thanks for the proposal. In your topic you have mentioned "RNNs". Does that mean Recurrent Neural nets?. The paper doesn't talk about RNN rather is uses CNN's to solve the problem. Can you please update the topic?.

  • Sarah Masud
    By Sarah Masud  ~  1 year ago
    reply Reply

    Hey Rohit,

    Can you please provide a deatiled structure of the session. Giving details for the following.

    1. The topics that will be covered(in order)

    2. The time estimated to covering each topic

    3. Who will be speaking for what topic.

    The reason I am asking for this is, because you have 2 speakers for a 20 mins session, and continuous swtiching of speakers breaks the flow for the audience.

    • Rohit Gupta
      By Rohit Gupta  ~  1 year ago
      reply Reply

      Hey Sarah, 

      I have removed co presenter and added time estimate in structure of the session.

       

      • Sarah Masud
        By Sarah Masud  ~  1 year ago
        reply Reply

        Thanks, Rohit. This definitely helps :)

  • Naresh Jain
    By Naresh Jain  ~  1 year ago
    reply Reply

    Thanks, Rohit. This topic is very interesting. Is there a blog or an article from you on this topic where I can learn more? Maybe a place where I can see a before and after compression demo?

    • Rohit Gupta
      By Rohit Gupta  ~  1 year ago
      reply Reply

      Sorry there is no such blog by me, but you can find literature in below links

      https://arxiv.org/pdf/1708.00838v1.pdf

      https://cs.stanford.edu/people/eroberts/courses/soco/projects/neural-networks/Applications/imagecompression.html

       

  • Vishal Gokhale
    By Vishal Gokhale  ~  1 year ago
    reply Reply

    Hi Rohit, 
    Thanks for the proposal. 
    Can you please reply to the previous comments


  • Liked Gunjan Juyal
    keyboard_arrow_down

    Gunjan Juyal - Building a Case for a Standardized Data Pipeline for All Your Organizational Data

    Gunjan Juyal
    Gunjan Juyal
    Sr. Consultant
    XNSIO
    schedule 1 year ago
    Sold Out!
    20 Mins
    Experience Report
    Beginner

    Organizations of all size and domains today face a data explosion problem, driven by a proliferation of data management tools and techniques. A very common scenario is creation of silos of data and data-products which increases the system’s complexity spread across the whole data lifecycle - right from data modeling to storage and processing infrastructure.

    High complexity = high system maintenance overheads = sluggish decision making. Another side-effect of this is divergence of the implemented system’s behaviour from high-level business objectives.

    In this talk we look at Zeta's experience as a case-study for reducing this complexity by defining and tackling various concerns at well-defined stages so as to prevent a build of complexity.

  • Liked Manish Kumar Shukla
    keyboard_arrow_down

    Manish Kumar Shukla - Machine learning With Quantum Systems

    Manish Kumar Shukla
    Manish Kumar Shukla
    Software Engineer
    Zeta
    schedule 1 year ago
    Sold Out!
    20 Mins
    Talk
    Intermediate
    The domain of Machine learning and Quantum computation are the next big leap in the general experience of computing. Using machine learning we want to take smart decisions and enlarge our solution space. In this era, we can see active research in Medical image processing, self driving cars, Content summarisation, sentiment analysis etc. All these can be obtained by using classical computers. Another domain of active research is Quantum information processing, here we try to use the principles of quantum mechanics to gain a leap in efficiency of information processing task. One such example is Shor's factoring algorithm which can solve the prime factorisation problem in O((log N)2(log log N)(log log log N) which is NP hard if we use classical computers. The primary reason which enables this the phenomena of superposition.
    The confluence of Classical machine learning with Quantum information theory which gives rise to field of Quantum Machine Learning, which is still in its nascent stages, but never the less very interesting to study. It is interesting to ask two types of questions
    a. How good would be a quantum computer in learning the the classical information. To give an example will a quantum computer be able to classify Apples and Oranges better than a classical computer.
    b. Another interesting question is to ask will some of the problems which are hard in quantum world be learned using classical computers. One such example is to classify entangled vs separable states.
    In this conference I will talk about how two domains are similar and different and what are some proposed solutions for the above stated problems.