Interview for HydraNets course
Last month the creator of the HydraNets course on multi-task learning Jeremy Cohen reached out to me and asked if I would be interested in speaking with him ...
Posts by Tag
- research 5
- real-time 3
- semantic-segmentation 3
- pytorch 3
- multi-task-learning 2
- javascript 2
- demo 2
- cvpr 2
- review 2
- pascal-voc 1
- medium 1
- depth-estimation 1
- surface-normals 1
- code 1
- tutorial 1
- updates 1
- nas 1
- are-we-there-yet 1
- education 1
- internship 1
- skydio 1
- exploratory 1
- coreml 1
- macos 1
- stats 1
- streamlit 1
- football 1
research
Real-Time Joint Segmentation, Depth and Surface Normals Estimation
Our paper, titled “Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations” has recently been accepted at International Confe...
On the perils of being slow in semantic segmentation
Segmenting a turtle - one of the slowest animals on Earth: left - original photo, right - segmentation result (highligh...
Light-Weight RefineNet
After nearly two years from my first publication (at the same venue as now), which included a year of academic break, I have finally submitted my first paper...
real-time
Real-Time Joint Segmentation, Depth and Surface Normals Estimation
Our paper, titled “Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations” has recently been accepted at International Confe...
On the perils of being slow in semantic segmentation
Segmenting a turtle - one of the slowest animals on Earth: left - original photo, right - segmentation result (highligh...
Light-Weight RefineNet
After nearly two years from my first publication (at the same venue as now), which included a year of academic break, I have finally submitted my first paper...
semantic-segmentation
Real-Time Joint Segmentation, Depth and Surface Normals Estimation
Our paper, titled “Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations” has recently been accepted at International Confe...
On the perils of being slow in semantic segmentation
Segmenting a turtle - one of the slowest animals on Earth: left - original photo, right - segmentation result (highligh...
Light-Weight RefineNet
After nearly two years from my first publication (at the same venue as now), which included a year of academic break, I have finally submitted my first paper...
pytorch
Example of speeding up inference of PyTorch models on M1 via Core ML tools
I recently read the CVPR 2022 paper titled “Learning to generate line drawings that convey geometry and semantics”, and I found the results quite interesting...
Tutorial - Converting a PyTorch model to TensorFlow.js
In this tutorial, I will cover one possible way of converting a PyTorch model into TensorFlow.js. This conversion will allow us to embed our model into a web...
Release of DenseTorch
I have just released a PyTorch wrapper that aims to facilitate a typical training workflow of dense per-pixel tasks. The project code is available here. Curr...
multi-task-learning
Interview for HydraNets course
Last month the creator of the HydraNets course on multi-task learning Jeremy Cohen reached out to me and asked if I would be interested in speaking with him ...
Real-Time Joint Segmentation, Depth and Surface Normals Estimation
Our paper, titled “Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations” has recently been accepted at International Confe...
javascript
Tutorial - Converting a PyTorch model to TensorFlow.js
In this tutorial, I will cover one possible way of converting a PyTorch model into TensorFlow.js. This conversion will allow us to embed our model into a web...
Multi-Task RefineNet Demo in Your Browser
I have just added a demo of Multi-Task RefineNet running in your browser with the help of TensorFlow.js. Check it out in demos! For now, only browsers with W...
demo
Tutorial - Converting a PyTorch model to TensorFlow.js
In this tutorial, I will cover one possible way of converting a PyTorch model into TensorFlow.js. This conversion will allow us to embed our model into a web...
Multi-Task RefineNet Demo in Your Browser
I have just added a demo of Multi-Task RefineNet running in your browser with the help of TensorFlow.js. Check it out in demos! For now, only browsers with W...
cvpr
Number of Citations of Papers Awarded at CVPR conferences
CVPR has long been regarded as the cream of the crop in the area of computer vision, attracting high-quality and influential publications. Traditionally, sev...
review
Are we there yet? Part I. Education
As of 2019, if you were to build a text generator (akin to this one), chances are that after the word Artificial it would mostly likely be predicting the wor...
pascal-voc
Light-Weight RefineNet
After nearly two years from my first publication (at the same venue as now), which included a year of academic break, I have finally submitted my first paper...
medium
On the perils of being slow in semantic segmentation
Segmenting a turtle - one of the slowest animals on Earth: left - original photo, right - segmentation result (highligh...
depth-estimation
Real-Time Joint Segmentation, Depth and Surface Normals Estimation
Our paper, titled “Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations” has recently been accepted at International Confe...
surface-normals
Real-Time Joint Segmentation, Depth and Surface Normals Estimation
Our paper, titled “Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations” has recently been accepted at International Confe...
code
Release of DenseTorch
I have just released a PyTorch wrapper that aims to facilitate a typical training workflow of dense per-pixel tasks. The project code is available here. Curr...
tutorial
Tutorial - Converting a PyTorch model to TensorFlow.js
In this tutorial, I will cover one possible way of converting a PyTorch model into TensorFlow.js. This conversion will allow us to embed our model into a web...
updates
A Couple of Updates
I am currently in Long Beach attending CVPR 2019, where we are going to present our paper on fast neural architecture search for semantic segmentation – t...
nas
Back to Top ↑are-we-there-yet
Are we there yet? Part I. Education
As of 2019, if you were to build a text generator (akin to this one), chances are that after the word Artificial it would mostly likely be predicting the wor...
education
Are we there yet? Part I. Education
As of 2019, if you were to build a text generator (akin to this one), chances are that after the word Artificial it would mostly likely be predicting the wor...
internship
My internship at Skydio
Recently I returned to Australia from the US where I had spent five months as an intern at Skydio, a Redwood City-based startup that is building autonomous f...
skydio
My internship at Skydio
Recently I returned to Australia from the US where I had spent five months as an intern at Skydio, a Redwood City-based startup that is building autonomous f...
exploratory
Number of Citations of Papers Awarded at CVPR conferences
CVPR has long been regarded as the cream of the crop in the area of computer vision, attracting high-quality and influential publications. Traditionally, sev...
coreml
Example of speeding up inference of PyTorch models on M1 via Core ML tools
I recently read the CVPR 2022 paper titled “Learning to generate line drawings that convey geometry and semantics”, and I found the results quite interesting...
macos
Example of speeding up inference of PyTorch models on M1 via Core ML tools
I recently read the CVPR 2022 paper titled “Learning to generate line drawings that convey geometry and semantics”, and I found the results quite interesting...
stats
Football Stats Quiz
About a month ago I watched a very awesome and inspirational talk by Patrick Lucey from StatsPerform on an overview of AI in sport. In one of their slides th...
streamlit
Football Stats Quiz
About a month ago I watched a very awesome and inspirational talk by Patrick Lucey from StatsPerform on an overview of AI in sport. In one of their slides th...
football
Football Stats Quiz
About a month ago I watched a very awesome and inspirational talk by Patrick Lucey from StatsPerform on an overview of AI in sport. In one of their slides th...