Trending Research

The Replica Dataset: A Digital Replica of Indoor Spaces

13 Jun 2019facebookresearch/Replica-Dataset

We introduce Replica, a dataset of 18 highly photo-realistic 3D indoor scene reconstructions at room and building scale.

3D SCENE RECONSTRUCTION

79
2.08 stars / hour

Character Region Awareness for Text Detection

CVPR 2019 clovaai/CRAFT-pytorch

Scene text detection methods based on neural networks have emerged recently and have shown promising results.

SCENE TEXT DETECTION

72
1.19 stars / hour

Hybrid Task Cascade for Instance Segmentation

CVPR 2019 amirassov/kaggle-imaterialist

In exploring a more effective approach, we find that the key to a successful instance segmentation cascade is to fully leverage the reciprocal relationship between detection and segmentation.

INSTANCE SEGMENTATION OBJECT DETECTION SEMANTIC SEGMENTATION

106
1.14 stars / hour

Making Convolutional Networks Shift-Invariant Again

25 Apr 2019adobe/antialiased-cnns

The well-known signal processing fix is anti-aliasing by low-pass filtering before downsampling.

CLASSIFICATION CONSISTENCY CONDITIONAL IMAGE GENERATION

186
0.94 stars / hour

Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation

4 Sep 2018asyml/texar-pytorch

We introduce Texar, an open-source toolkit aiming to support the broad set of text generation tasks that transforms any inputs into natural language, such as machine translation, summarization, dialog, content manipulation, and so forth.

MACHINE TRANSLATION TEXT GENERATION

112
0.81 stars / hour

Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers

9 Jun 2019Hadisalman/smoothing-adversarial

Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations.

ADVERSARIAL ATTACK ADVERSARIAL DEFENSE

59
0.65 stars / hour

Pose2Seg: Detection Free Human Instance Segmentation

CVPR 2019 liruilong940607/Pose2Seg

We demonstrate that our pose-based framework can achieve better accuracy than the state-of-art detection-based approach on the human instance segmentation problem, and can moreover better handle occlusion.

HUMAN INSTANCE SEGMENTATION OBJECT DETECTION SEMANTIC SEGMENTATION

139
0.61 stars / hour

YOLACT: Real-time Instance Segmentation

4 Apr 2019dbolya/yolact

Then we produce instance masks by linearly combining the prototypes with the mask coefficients.

REAL-TIME INSTANCE SEGMENTATION SEMANTIC SEGMENTATION

762
0.46 stars / hour

Sogou Machine Reading Comprehension Toolkit

28 Mar 2019sogou/SMRCToolkit

In this paper, we present a Sogou Machine Reading Comprehension (SMRC) toolkit that can be used to provide the fast and efficient development of modern machine comprehension models, including both published models and original prototypes.

MACHINE READING COMPREHENSION

809
0.38 stars / hour