Trending Research
Real-Time-Voice-Cloning
NeurIPS 2018
• CorentinJ/Real-Time-Voice-Cloning
• 
Clone a voice in 5 seconds to generate arbitrary speech in real-time
SPEAKER VERIFICATION SPEECH SYNTHESIS TEXT-TO-SPEECH SYNTHESIS TRANSFER LEARNING
Deep Hough Voting for 3D Object Detection in Point Clouds
Current 3D object detection methods are heavily influenced by 2D detectors.
SOTA for 3D Object Detection on SUN-RGBD
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.
#2 best model for
Semantic Segmentation
on ShapeNet
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
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
Image Synthesis with a Single (Robust) Classifier
We show that the basic classification framework alone can be used to tackle some of the most challenging tasks in image synthesis.
#9 best model for
Image Generation
on CIFAR-10
Learning Perceptually-Aligned Representations via Adversarial 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.
On the Variance of the Adaptive Learning Rate and Beyond
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
RepPoints: Point Set Representation for Object Detection
They furthermore do not require the use of anchors to sample a space of bounding boxes.
#19 best model for
Object Detection
on COCO
LFFD: A Light and Fast Face Detector for Edge Devices
• YonghaoHe/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