Architecture Search of Dynamic Cells for Semantic Video Segmentation
V.Nekrasov, H. Chen, C.Shen, I.Reid
Winter conference on applications of Computer Vision (WACV), 2020
Applying neural architecture search to find dynamic operations for semantic video segmentation
Template-Based Automatic Search of Compact Semantic Segmentation Architectures
V.Nekrasov, C.Shen, I.Reid
Winter conference on applications of Computer Vision (WACV), 2020
models / paper
Automatically discovering compact segmentation networks with less than 0.5M parameters
Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells
V.Nekrasov, H. Chen (equal contribution), C.Shen, I.Reid
Conference on Computer Vision and Pattern Recognition (CVPR), 2019
code / paper
Fast reinforcement learning (RL)-based approach (in 8 GPU-days) of finding light-weight models for dense per-pixel tasks
Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations
V.Nekrasov, T.Dharmasiri, A.Spek, T.Drummond, C.Shen, I.Reid
International Conference on Robotics and Automation (ICRA), 2019
code / paper
A simple approach of performing joint segmentation, depth and surface normals estimation in real-time with SOTA results using a single model
Light-Weight RefineNet for Real-Time Semantic Segmentation
V.Nekrasov, C.Shen, I.Reid
British Machine Vision Conference (BMVC), 2018
code / paper
Re-thinking an encoder-decoder based segmentation network into the one able to attain high performance with the real-time inference
Diagnostics in Semantic Segmentation
V.Nekrasov, C.Shen, I.Reid
paper / supp
Evaluating SOTA segmentation networks in terms of their sensitivity to object properties and uncertainty measures
Global Deconvolutional Networks for Semantic Segmentation
V.Nekrasov, J.Ju, J.Choi
British Machine Vision Conference (BMVC), 2016
code / paper
Learnable matrix-based method for global interpolation inside segmentation networks

Re-implementations and extensions

Informative Drawings
PyTorch, CoreML
code / blogpost
Extending the authors’ repository with the CoreML model during inference for the neural sketching task
Segment Anything Model (SAM)
PyTorch, MPS
Extending the authors’ repository with the support for MPS (Mac Metal PyTorch backend) during inference
Re-implementation of DeepLab-v1 (LargeFOV) in TensorFlow
Re-implementation of DeepLab-v2 (ResNet-101) in TensorFlow
Conversion of DeepLab-v3+ pre-trained weights from TensorFlow into PyTorch
RefineNet based on ResNet-101 trained on PASCAL VOC in PyTorch


Football Stats Quiz Game
app / code / blogpost
Simple game on football stats made in Streamlit
Number of citations of CVPR awardees
code / blogpost
Looking at the number of citations the papers awarded at CVPR accrued over time
code / docs
PyTorch Wrapper for Smooth Workflow with Dense Per-Pixel Tasks (including multi-task learning)
Bio-Data Programming
code / shiny1 / shiny2
Shiny-based applications developed for the course on biomedical data programming - based on the NCI-60 cancel cell line panel dataset
EPL-16 Away Fixtures Map
code / shiny
Mapping of away fixtures in English Premier League Season ‘16-‘17 (first half) using leaflet and d3
GPU-server workload visualisation
Simple visualisation of workload on a GPU server in d3.js