Trending Research
CornerNet-Lite: Efficient Keypoint Based Object Detection
• princeton-vl/CornerNet-Lite
• 
Together these two variants address the two critical use cases in efficient object detection: improving efficiency without sacrificing accuracy, and improving accuracy at real-time efficiency.
#4 best model for
Real-Time Object Detection
on COCO
Objects as Points
We model an object as a single point --- the center point of its bounding box.
#5 best model for
Keypoint Detection
on COCO
(Test AP metric)
Precise Detection in Densely Packed Scenes
We propose a novel, deep-learning based method for precise object detection, designed for such challenging settings.
SOTA for Dense Object Detection on SKU-110K
Language Models are Unsupervised Multitask Learners
Preprint 2019
• minimaxir/gpt-2-simple
• 
Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets.
SOTA for Language Modelling on Penn Treebank (Word Level) (using extra training data)
COMMON SENSE REASONING DOCUMENT SUMMARIZATION LANGUAGE MODELLING MACHINE TRANSLATION QUESTION ANSWERING READING COMPREHENSION
CenterNet: Keypoint Triplets for Object Detection
In object detection, keypoint-based approaches often suffer a large number of incorrect object bounding boxes, arguably due to the lack of an additional look into the cropped regions.
#3 best model for
Object Detection
on COCO
PointConv: Deep Convolutional Networks on 3D Point Clouds
Besides, our experiments converting CIFAR-10 into a point cloud showed that networks built on PointConv can match the performance of convolutional networks in 2D images of a similar structure.
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
Similarly, the output feature maps of a convolution layer can also be seen as a mixture of information at different frequencies.
#5 best model for
Image Classification
on ImageNet
Adaptively Connected Neural Networks
This paper presents a novel adaptively connected neural network (ACNet) to improve the traditional convolutional neural networks (CNNs) {in} two aspects.
SOTA for Document Classification on Cora
DOCUMENT CLASSIFICATION IMAGE CLASSIFICATION PERSON RE-IDENTIFICATION
Res2Net: A New Multi-scale Backbone Architecture
We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e. g., CIFAR-100 and ImageNet.
#4 best model for
Image Classification
on CIFAR-100
Text Classification Algorithms: A Survey
In this paper, a brief overview of text classification algorithms is discussed.