Jacob Gildenblat

Deriving confidence intervals for variants of Recall, Precision and F1

Jun 14, 2023 · 4 min read Statistics

Deriving confidence intervals for binary and macro Recall, Precision and F1 using the multivariate delta method on the confusion matrix.
Exploring Explainability for Vision Transformers

Dec 31, 2020 · 11 min read Deep learning

A visual exploration of the Q, K and V attention patterns inside a Vision Transformer, and how to turn them...
Overview of Active Learning for Deep Learning

Feb 21, 2020 · 16 min read Deep learning

Overview of different Active Learning algorithms for Deep Learning.
Hallucinating faces with Deep Learning

Mar 31, 2018 · 5 min read Deep learning

Here is the github repository with all the code for this post. Scroll to the end if you just want...
Accelerating Deep Neural Networks with Tensor Decompositions

Jan 23, 2018 · 11 min read Deep learning

My PyTorch implementation for tensor decomposition methods on convolutional layers. Notebook contributed to TensorLy.
Pruning deep neural networks to make them fast and small

Jun 23, 2017 · 10 min read Deep learning

My PyTorch implementation of [1611.06440 Pruning Convolutional Neural Networks for Resource Efficient Inference].
Visualizations for regressing wheel steering angles in self driving cars

Oct 26, 2016 · 5 min read Deep learning

Pixels that contribute to steering right, using the grad-cam method described below Video using the hypercolumns and occlusion map methods...
Class activation maps in Keras for visualizing where deep learning networks pay attention

Aug 19, 2016 · 5 min read Deep learning

Github project for class activation maps Github repo for gradient based class activation maps
A few notes on using the Tensorflow C++ API

Jun 10, 2016 · 1 min read Deep learning

If you are unfamiliar with bazel, then there are some quirks in getting TensorFlow to work with OpenCV, optimizations turned...
Visualizing CNN filters with keras

Mar 23, 2016 · 3 min read Deep learning

Here is a utility I made for visualizing filters with Keras, using a few regularizations for more natural outputs.
Smoothing images with the Mumford Shah functional

Apr 26, 2015 · 2 min read Computer vision

My python implementation for minimizing the Mumford Shah functional.
Simple Image saliency detection from histogram backprojection

Apr 24, 2015 · 3 min read Computer vision

Github repository Image saliency detection is about identifying the interesting parts of an image, the parts of the image human...
Image Fisher Vectors In Python

Dec 5, 2014 · 2 min read Machine learning

Although the state of the art in image classification (while writing this post) is deep learning, Bag of words approaches...
Bag of visual words for image classification

May 5, 2014 · 1 min read Machine learning

Github repository I wanted to play around with Bag Of Words for visual classification, so I coded a Matlab implementation...
Refining the Hough Transform with CAMSHIFT

May 5, 2014 · 3 min read Machine learning

The Circular Hough Transform result is often not very accurate due to noise\details\occlusions. Typical ways of dealing with this are:...