Trending Research
Pen and Paper Exercises in Machine Learning
This is a collection of (mostly) pen-and-paper exercises in machine learning.
Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
kwea123/ngp_pl
•
•
Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate.
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
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)
Text2Human: Text-Driven Controllable Human Image Generation
In this work, we present a text-driven controllable framework, Text2Human, for a high-quality and diverse human generation.
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.
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
towhee-io/towhee
•
•
Furthermore, performance improvement has been largely achieved by scaling up the dataset with noisy image-text pairs collected from the web, which is a suboptimal source of supervision.
Ranked #1 on
Image Captioning
on nocaps-val-out-domain
TSM: Temporal Shift Module for Efficient Video Understanding
towhee-io/towhee
•
•
ICCV 2019
The explosive growth in video streaming gives rise to challenges on performing video understanding at high accuracy and low computation cost.
Ranked #13 on
Video Object Detection
on ImageNet VID
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.
EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications
mmaaz60/EdgeNeXt
•
•
Our EdgeNeXt model with 1. 3M parameters achieves 71. 2\% top-1 accuracy on ImageNet-1K, outperforming MobileViT with an absolute gain of 2. 2\% with 28\% reduction in FLOPs.
Ranked #37 on
Semantic Segmentation
on PASCAL VOC 2012 test
