Projects

Here is a selection of projects I have worked on in my spare time. For an up-to-date list, please visit my GitHub.

dino_from_scratch

Implementing from scratch "Emerging Properties in Self-Supervised Vision Transformers" ICCV 2021.

dqn_from_scratch

Implementing from scratch DQN (Deep Q-Network) from the paper "Playing atari with deep reinforcement learning" DeepMind 2013.

detr_from_scratch

Implementing from scratch the paper "End-to-End Object Detection with Transformers" ECCV 2020.

flownet_from_scratch

Implementing from scratch the paper "FlowNet: Learning Optical Flow with Convolutional Networks" ECCV 2015.

prnet_from_scratch

Implementing from scratch the paper "Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network" ECCV 2018.

ByteTrack_from_scratch

Implementing from scratch the paper "ByteTrack: Multi-Object Tracking by Associating Every Detection Box" ECCV 2022.

moco_from_scratch

Implementing from scratch the paper "Momentum Contrast for Unsupervised Visual Representation Learning" CVPR 2020.

clip_from_scratch

Implementing from scratch the paper "Learning Transferable Visual Models From Natural Language Supervision" ICML 2021 (OpenAI CLIP).

gpt_from_scratch

Implementing from scratch the paper "Improving Language Understanding by Generative Pre-Training" OpenAI GPT-1.

dpt_from_scratch

Implementing from scratch the paper "Vision Transformers for Dense Prediction" ICCV 2021.

nerf_from_scratch

Implementing from scratch the paper "NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis" ECCV 2020.

mae_from_scratch

Implementing from scratch the paper "Masked Autoencoders Are Scalable Vision Learners" CVPR 2022.

ViT_from_scratch

Implementing from scratch the paper "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale" ICLR 2021.

pointnet_from_scratch

Implementing from scratch the paper "PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation" CVPR 2017.