Trending Research

Deep Hough Voting for 3D Object Detection in Point Clouds

21 Apr 2019facebookresearch/votenet

Current 3D object detection methods are heavily influenced by 2D detectors.

3D OBJECT DETECTION

92
1.89 stars / hour

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

NeurIPS 2017 facebookresearch/votenet

By exploiting metric space distances, our network is able to learn local features with increasing contextual scales.

3D PART SEGMENTATION

92
1.89 stars / hour

ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks

6 Aug 2019jiasenlu/vilbert_beta

We present ViLBERT (short for Vision-and-Language BERT), a model for learning task-agnostic joint representations of image content and natural language.

IMAGE RETRIEVAL QUESTION ANSWERING VISUAL COMMONSENSE REASONING VISUAL QUESTION ANSWERING

66
1.44 stars / hour

Image Synthesis with a Single (Robust) Classifier

6 Jun 2019MadryLab/robustness

We show that the basic classification framework alone can be used to tackle some of the most challenging tasks in image synthesis.

IMAGE GENERATION

79
1.18 stars / hour

Learning Perceptually-Aligned Representations via Adversarial Robustness

3 Jun 2019MadryLab/robustness

Many applications of machine learning require models that are human-aligned, i. e., that make decisions based on human-meaningful information about the input.

79
1.18 stars / hour

On the Variance of the Adaptive Learning Rate and Beyond

8 Aug 2019LiyuanLucasLiu/RAdam

The learning rate warmup heuristic achieves remarkable success in stabilizing training, accelerating convergence and improving generalization for adaptive stochastic optimization algorithms like RMSprop and Adam.

IMAGE CLASSIFICATION LANGUAGE MODELLING MACHINE TRANSLATION STOCHASTIC OPTIMIZATION

1,090
1.18 stars / hour

RepPoints: Point Set Representation for Object Detection

25 Apr 2019microsoft/RepPoints

They furthermore do not require the use of anchors to sample a space of bounding boxes.

#19 best model for Object Detection on COCO

OBJECT DETECTION

126
1.15 stars / hour

LFFD: A Light and Fast Face Detector for Edge Devices

24 Apr 2019YonghaoHe/A-Light-and-Fast-Face-Detector-for-Edge-Devices

Under the new schema, the proposed method can achieve superior accuracy (WIDER FACE Val/Test -- Easy: 0. 910/0. 896, Medium: 0. 881/0. 865, Hard: 0. 780/0. 770; FDDB -- discontinuous: 0. 973, continuous: 0. 724).

#6 best model for Face Detection on FDDB

FACE DETECTION

305
0.98 stars / hour

kaldi

Interspeech 2018 2018 kaldi-asr/kaldi

This is the official location of the Kaldi project.

END-TO-END SPEECH RECOGNITION SPEECH RECOGNITION

6,878
0.78 stars / hour