Trending Research

CornerNet-Lite: Efficient Keypoint Based Object Detection

18 Apr 2019princeton-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.

REAL-TIME OBJECT DETECTION

539
3.18 stars / hour

Objects as Points

16 Apr 2019xingyizhou/CenterNet

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)

KEYPOINT DETECTION OBJECT DETECTION

731
1.20 stars / hour

Precise Detection in Densely Packed Scenes

1 Apr 2019eg4000/SKU110K_CVPR19

We propose a novel, deep-learning based method for precise object detection, designed for such challenging settings.

DENSE OBJECT DETECTION

120
1.16 stars / hour

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

157
1.08 stars / hour

CenterNet: Keypoint Triplets for Object Detection

17 Apr 2019Duankaiwen/CenterNet

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.

OBJECT DETECTION

478
0.87 stars / hour

PointConv: Deep Convolutional Networks on 3D Point Clouds

17 Nov 2018DylanWusee/pointconv

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.

3D PART SEGMENTATION DENSITY ESTIMATION

76
0.71 stars / hour

Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution

10 Apr 2019lxtGH/OctaveConv_pytorch

Similarly, the output feature maps of a convolution layer can also be seen as a mixture of information at different frequencies.

IMAGE CLASSIFICATION VIDEO RECOGNITION

243
0.62 stars / hour

Adaptively Connected Neural Networks

7 Apr 2019lxtGH/OctaveConv_pytorch

This paper presents a novel adaptively connected neural network (ACNet) to improve the traditional convolutional neural networks (CNNs) {in} two aspects.

DOCUMENT CLASSIFICATION IMAGE CLASSIFICATION PERSON RE-IDENTIFICATION

243
0.62 stars / hour

Res2Net: A New Multi-scale Backbone Architecture

2 Apr 2019lxtGH/OctaveConv_pytorch

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.

IMAGE CLASSIFICATION SALIENT OBJECT DETECTION

243
0.62 stars / hour

Text Classification Algorithms: A Survey

17 Apr 2019kk7nc/Text_Classification

In this paper, a brief overview of text classification algorithms is discussed.

DIMENSIONALITY REDUCTION TEXT CLASSIFICATION

190
0.59 stars / hour