Ameya Joshi

Ameya Joshi

I am a Research Scientist at InstaDeep AI, Boston, interested in multi-modal and sequence models. My current research focuses on building models for genomics and proteomics.

Posts by Tags

Artificial Intelligence

The Traveling Salesman Problem - Using Ant Algorithms

12 minute read

Published:

As I had promised, this post will be about using the Ant algorithms I had discussed in the previous post to solve a complex computational problem. But, before we go on, let us have a look again at Ant Colony optimization. Read more

Bag of Features

VLAD- An extension of Bag of Words

4 minute read

Published:

Recently, I was a participant at TagMe- an image categorization competition conducted by Microsoft and Indian Institute of Science, Bangalore. The problem statement was to classify a set of given images into five classes: faces, shoes, flowers, buildings and vehicles. As it goes, it is not a trivial problem to solve. So, I decided to attempt my existing bag-of-words algorithm on that. It worked to an extent, I got an accuracy of 86% approximately with SIFT features and an RBF SVM for classification. In order to improve my score though, I decided to look at better methods of feature quantization. I had been looking at VLAD (Vector of Locally Aggregated Descriptors): A first order extension to BoW for my Leaf Recognition project. Read more

Computer Vision

An Interesting History of Computer Vision Permalink

less than 1 minute read

Published:

Dr. Fei Fei Li from Stanford discusses the advent and growth of computer vision in recent years. Particularly intersting is her recent research on multimodal interactions and large scale visual recognition. This has been primarily made possible due to the growth in GPU technology. I hope to try out Theano and Caffe for deep learning in this scenario soon. Read more

VLAD- An extension of Bag of Words

4 minute read

Published:

Recently, I was a participant at TagMe- an image categorization competition conducted by Microsoft and Indian Institute of Science, Bangalore. The problem statement was to classify a set of given images into five classes: faces, shoes, flowers, buildings and vehicles. As it goes, it is not a trivial problem to solve. So, I decided to attempt my existing bag-of-words algorithm on that. It worked to an extent, I got an accuracy of 86% approximately with SIFT features and an RBF SVM for classification. In order to improve my score though, I decided to look at better methods of feature quantization. I had been looking at VLAD (Vector of Locally Aggregated Descriptors): A first order extension to BoW for my Leaf Recognition project. Read more

DCMI

Deep Learning

Education

Embedded Systems

Fei Fei Li

An Interesting History of Computer Vision Permalink

less than 1 minute read

Published:

Dr. Fei Fei Li from Stanford discusses the advent and growth of computer vision in recent years. Particularly intersting is her recent research on multimodal interactions and large scale visual recognition. This has been primarily made possible due to the growth in GPU technology. I hope to try out Theano and Caffe for deep learning in this scenario soon. Read more

GPU

An Interesting History of Computer Vision Permalink

less than 1 minute read

Published:

Dr. Fei Fei Li from Stanford discusses the advent and growth of computer vision in recent years. Particularly intersting is her recent research on multimodal interactions and large scale visual recognition. This has been primarily made possible due to the growth in GPU technology. I hope to try out Theano and Caffe for deep learning in this scenario soon. Read more

Image Classification

VLAD- An extension of Bag of Words

4 minute read

Published:

Recently, I was a participant at TagMe- an image categorization competition conducted by Microsoft and Indian Institute of Science, Bangalore. The problem statement was to classify a set of given images into five classes: faces, shoes, flowers, buildings and vehicles. As it goes, it is not a trivial problem to solve. So, I decided to attempt my existing bag-of-words algorithm on that. It worked to an extent, I got an accuracy of 86% approximately with SIFT features and an RBF SVM for classification. In order to improve my score though, I decided to look at better methods of feature quantization. I had been looking at VLAD (Vector of Locally Aggregated Descriptors): A first order extension to BoW for my Leaf Recognition project. Read more

Image Processing & Computer Vision

Machine Learning

VLAD- An extension of Bag of Words

4 minute read

Published:

Recently, I was a participant at TagMe- an image categorization competition conducted by Microsoft and Indian Institute of Science, Bangalore. The problem statement was to classify a set of given images into five classes: faces, shoes, flowers, buildings and vehicles. As it goes, it is not a trivial problem to solve. So, I decided to attempt my existing bag-of-words algorithm on that. It worked to an extent, I got an accuracy of 86% approximately with SIFT features and an RBF SVM for classification. In order to improve my score though, I decided to look at better methods of feature quantization. I had been looking at VLAD (Vector of Locally Aggregated Descriptors): A first order extension to BoW for my Leaf Recognition project. Read more

Object Recognition

VLAD- An extension of Bag of Words

4 minute read

Published:

Recently, I was a participant at TagMe- an image categorization competition conducted by Microsoft and Indian Institute of Science, Bangalore. The problem statement was to classify a set of given images into five classes: faces, shoes, flowers, buildings and vehicles. As it goes, it is not a trivial problem to solve. So, I decided to attempt my existing bag-of-words algorithm on that. It worked to an extent, I got an accuracy of 86% approximately with SIFT features and an RBF SVM for classification. In order to improve my score though, I decided to look at better methods of feature quantization. I had been looking at VLAD (Vector of Locally Aggregated Descriptors): A first order extension to BoW for my Leaf Recognition project. Read more

Optimization

The Traveling Salesman Problem - Using Ant Algorithms

12 minute read

Published:

As I had promised, this post will be about using the Ant algorithms I had discussed in the previous post to solve a complex computational problem. But, before we go on, let us have a look again at Ant Colony optimization. Read more

Projects

Research

SIFT

SLIC

SLIC Superpixels

STM32F4

Stanford

An Interesting History of Computer Vision Permalink

less than 1 minute read

Published:

Dr. Fei Fei Li from Stanford discusses the advent and growth of computer vision in recent years. Particularly intersting is her recent research on multimodal interactions and large scale visual recognition. This has been primarily made possible due to the growth in GPU technology. I hope to try out Theano and Caffe for deep learning in this scenario soon. Read more

Travelling salesman problem

The Traveling Salesman Problem - Using Ant Algorithms

12 minute read

Published:

As I had promised, this post will be about using the Ant algorithms I had discussed in the previous post to solve a complex computational problem. But, before we go on, let us have a look again at Ant Colony optimization. Read more

VLAD

VLAD- An extension of Bag of Words

4 minute read

Published:

Recently, I was a participant at TagMe- an image categorization competition conducted by Microsoft and Indian Institute of Science, Bangalore. The problem statement was to classify a set of given images into five classes: faces, shoes, flowers, buildings and vehicles. As it goes, it is not a trivial problem to solve. So, I decided to attempt my existing bag-of-words algorithm on that. It worked to an extent, I got an accuracy of 86% approximately with SIFT features and an RBF SVM for classification. In order to improve my score though, I decided to look at better methods of feature quantization. I had been looking at VLAD (Vector of Locally Aggregated Descriptors): A first order extension to BoW for my Leaf Recognition project. Read more

ant algorithms

The Traveling Salesman Problem - Using Ant Algorithms

12 minute read

Published:

As I had promised, this post will be about using the Ant algorithms I had discussed in the previous post to solve a complex computational problem. But, before we go on, let us have a look again at Ant Colony optimization. Read more

bag of words

VLAD- An extension of Bag of Words

4 minute read

Published:

Recently, I was a participant at TagMe- an image categorization competition conducted by Microsoft and Indian Institute of Science, Bangalore. The problem statement was to classify a set of given images into five classes: faces, shoes, flowers, buildings and vehicles. As it goes, it is not a trivial problem to solve. So, I decided to attempt my existing bag-of-words algorithm on that. It worked to an extent, I got an accuracy of 86% approximately with SIFT features and an RBF SVM for classification. In order to improve my score though, I decided to look at better methods of feature quantization. I had been looking at VLAD (Vector of Locally Aggregated Descriptors): A first order extension to BoW for my Leaf Recognition project. Read more

category1

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false. Read more

category2

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false. Read more

cool posts

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false. Read more

human computer interaction

Color Predicates

2 minute read

Published:

It’s been a long time since I posted something here. But here it is. Read more

m tim jones

The Traveling Salesman Problem - Using Ant Algorithms

12 minute read

Published:

As I had promised, this post will be about using the Ant algorithms I had discussed in the previous post to solve a complex computational problem. But, before we go on, let us have a look again at Ant Colony optimization. Read more

marco dorigo

The Traveling Salesman Problem - Using Ant Algorithms

12 minute read

Published:

As I had promised, this post will be about using the Ant algorithms I had discussed in the previous post to solve a complex computational problem. But, before we go on, let us have a look again at Ant Colony optimization. Read more

object classification

object segmentation

programming

The Traveling Salesman Problem - Using Ant Algorithms

12 minute read

Published:

As I had promised, this post will be about using the Ant algorithms I had discussed in the previous post to solve a complex computational problem. But, before we go on, let us have a look again at Ant Colony optimization. Read more

Color Predicates

2 minute read

Published:

It’s been a long time since I posted something here. But here it is. Read more

scene classification

VLAD- An extension of Bag of Words

4 minute read

Published:

Recently, I was a participant at TagMe- an image categorization competition conducted by Microsoft and Indian Institute of Science, Bangalore. The problem statement was to classify a set of given images into five classes: faces, shoes, flowers, buildings and vehicles. As it goes, it is not a trivial problem to solve. So, I decided to attempt my existing bag-of-words algorithm on that. It worked to an extent, I got an accuracy of 86% approximately with SIFT features and an RBF SVM for classification. In order to improve my score though, I decided to look at better methods of feature quantization. I had been looking at VLAD (Vector of Locally Aggregated Descriptors): A first order extension to BoW for my Leaf Recognition project. Read more

science

segmentation

technology