Trending Research
Pen and Paper Exercises in Machine Learning
This is a collection of (mostly) pen-and-paper exercises in machine learning.
LViT: Language meets Vision Transformer in Medical Image Segmentation
huanglizi/lvit
•
•
In our model, medical text annotation is introduced to compensate for the quality deficiency in image data.
Ranked #1 on
Medical Image Segmentation
on MoNuSeg
Multi-Graph Fusion Networks for Urban Region Embedding
wushangbin/mgfn
•
•
Human mobility data contains rich but abundant information, which yields to the comprehensive region embeddings for cross domain tasks.
Denoised MDPs: Learning World Models Better Than the World Itself
facebookresearch/denoised_mdp
•
•
The ability to separate signal from noise, and reason with clean abstractions, is critical to intelligence.
Ivy: Templated Deep Learning for Inter-Framework Portability
ivy-dl/ivy
•
•
We introduce Ivy, a templated Deep Learning (DL) framework which abstracts existing DL frameworks.
Forecasting Future World Events with Neural Networks
We test language models on our forecasting task and find that performance is far below a human expert baseline.
ProGen2: Exploring the Boundaries of Protein Language Models
Attention-based models trained on protein sequences have demonstrated incredible success at classification and generation tasks relevant for artificial intelligence-driven protein design.
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.
BoT-SORT: Robust Associations Multi-Pedestrian Tracking
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)
PolarFormer: Multi-camera 3D Object Detection with Polar Transformer
3D object detection in autonomous driving aims to reason "what" and "where" the objects of interest present in a 3D world.
