Pen and Paper Exercises in Machine Learning

michaelgutmann/ml-pen-and-paper-exercises 27 Jun 2022

This is a collection of (mostly) pen-and-paper exercises in machine learning.

Variational Inference

831
4.03 stars / hour

LViT: Language meets Vision Transformer in Medical Image Segmentation

huanglizi/lvit 29 Jun 2022

In our model, medical text annotation is introduced to compensate for the quality deficiency in image data.

Medical Image Segmentation Semantic Segmentation

87
1.08 stars / hour

Multi-Graph Fusion Networks for Urban Region Embedding

wushangbin/mgfn 24 Jan 2022

Human mobility data contains rich but abundant information, which yields to the comprehensive region embeddings for cross domain tasks.

Crime Prediction

202
0.59 stars / hour

Denoised MDPs: Learning World Models Better Than the World Itself

facebookresearch/denoised_mdp 30 Jun 2022

The ability to separate signal from noise, and reason with clean abstractions, is critical to intelligence.

Representation Learning

56
0.56 stars / hour

BoT-SORT: Robust Associations Multi-Pedestrian Tracking

niraharon/bot-sort 29 Jun 2022

The goal of multi-object tracking (MOT) is detecting and tracking all the objects in a scene, while keeping a unique identifier for each object.

 Ranked #1 on Multi-Object Tracking on MOT20 (using extra training data)

Multi-Object Tracking

24
0.54 stars / hour

Ivy: Templated Deep Learning for Inter-Framework Portability

ivy-dl/ivy 4 Feb 2021

We introduce Ivy, a templated Deep Learning (DL) framework which abstracts existing DL frameworks.

3,016
0.53 stars / hour

Forecasting Future World Events with Neural Networks

andyzoujm/autocast 30 Jun 2022

We test language models on our forecasting task and find that performance is far below a human expert baseline.

Decision Making Language Modelling

29
0.51 stars / hour

ProGen2: Exploring the Boundaries of Protein Language Models

salesforce/progen 27 Jun 2022

Attention-based models trained on protein sequences have demonstrated incredible success at classification and generation tasks relevant for artificial intelligence-driven protein design.

70
0.42 stars / hour

BokehMe: When Neural Rendering Meets Classical Rendering

juewenpeng/bokehme CVPR 2022

Based on this formulation, we implement the classical renderer by a scattering-based method and propose a two-stage neural renderer to fix the erroneous areas from the classical renderer.

Neural Rendering

75
0.35 stars / hour

HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction

ZikangZhou/HiVT CVPR 2022

To tackle this challenge, we propose Hierarchical Vector Transformer (HiVT) for fast and accurate multi-agent motion prediction.

Motion Forecasting motion prediction +2

161
0.35 stars / hour