Skip to main content

Pokemon Classification by Siamese Network and One Shot Learning

Some of my recent clients are interested in image classification using limited learning data. A major use case is in detecting defective products on the manufacturing line. Defective products are normally caught by human operators watching the production line. It requires constant concentration and effort so if this can be automated it will bring a lot of productivity boost to manufacturers.

One method to overcome this issue is by creating a network to compare input images with the training dataset. For defective products, the images will look different from the passing products.

Experiments

For this experiment, I used a Siamese Network to generate embeddings for images of Pokemon. The Pokemon has 4 classes, Pikachu, Squirtle, Bulbasaur and Charmander. The images are scraped from the internet using the Bing API.


The images in the training dataset is trained to find the set of weights that will clearly separate the 4 classes. If a new image which is not included in the 4 classes is used, the resulting distance (difference) will be large enough to separate it with the 4 available classes.

The Siamese network trains triplets of Anchor, Positive and Negative images, and I generated some hard batches to improve the training accuracy. For details look into the original article in Credits section.

Results

The best result I got was AUC 84%.


And the image tests with this set of weights are as follows




Discussions

As we can see in the second row, the input image of Bulbasaur is wrongly classified as Squirtle. This error can happen when the input image of Bulbasaur has the same color tone as Squirtle. Therefore, we can conclude that although One-Shot learning can be useful for classification with minimal data because it only measures the distance between images, it can also produce errors when the images are similar to each other. For all use cases, it will depend on the data available, and if the images have enough distance (sufficiently different). 

Credit

This experiment was created by modifying the original pipeline found here:
https://medium.com/@crimy/one-shot-learning-siamese-networks-and-triplet-loss-with-keras-2885ed022352










Comments

Post a Comment

Popular posts from this blog

Installing a custom ROM on Android (on the GT-N8013)

It's been a while since my last entry and since it is a new start in 2019, I thought I'd write something about "gone with the old and in with the new". I've had my Samsung Galaxy Note 10.1 (pnotewifi) since 2014, and it's one of the early Galaxy Note tablet series. It has served me well all this years but now it just sits there collecting dust. My old Samsung GT-N8013 I've known a long time about custom Android ROMs like CyanogenMod but has never had the motivation to try them out, until now ! Overview of the process For beginners like me, I didn't have an understanding of the installation process and so it looked complicated and it was one of the reasons I was put off in trying the custom ROM. I just want to say, it's not complicated at all!   Basically you will need to Prepare an SD card and install Android SDK (you need adb ). Install a custom boot loader ( TWRP is the de facto tool at the moment). Use adb to copy custom...
15 comments
Read more

Pitfalls during Training and Object Detection with TensorFlow for Absolute Beginners

This article is based on the great tutorial here on how to train and detect custom objects with Tensorflow. I also referred to the official documentations here and  here  for running Tensorflow model building locally. It was my first custom detection project and I faced some hiccups along the way and this article is to log and share my finding so it can help other beginners like me. In the end, I managed to train a tensorflow model to detect Batsumaru , a character from Sanrio. This is how the detection will look like. The tools Windows 10 Pro 64 Tensorflow originally 1.7.1 and upgraded to 1.12.0. I will share the reason later. Python 3.5.4 LabelImg for image labeling PyCharm IDE Steps and Pitfalls Some of the mistakes I made and other discoveries when following the guide. I will not repeat the steps mentioned in the original guide, but only the parts where I had to deviate from the walkthrough and found out things by myself. The training and...
1 comment
Read more

Unity Best Practices for Beginners

Unity is a fabulous tool for not only games but also interactive entertainment, simulations, etc. And there are many good tutorials on tips and tricks to optimize performance and code readability. I compiled this list as a memo to myself when starting out on Unity, so I can always refer back to the basics and hoping that this can help someone else too. Object pooling. Object pooling is a pretty cool trick and it improves performance because you can reduce the number of Initiate() and Destroy() calls. To illustrate why Destroy can be bad, I attached a screenshot of a project I was building with Unity. I'm not going to go into the details of Object Pooling because there are already many good tutorials out there. One of them being this one.  One thing to always keep in mind is that it is easy to get MissingReferenceException if you accidentally Destroy() the pooled objects. It happened to me once where I attached one script to multiple prefabs which behave the same except that so...
Post a Comment
Read more