Trending Research
pytorch-transformers
• huggingface/pytorch-transformers
• 
👾 A library of state-of-the-art pretrained models for Natural Language Processing (NLP)
DOCUMENT RANKING LANGUAGE MODELLING NATURAL LANGUAGE INFERENCE QUESTION ANSWERING READING COMPREHENSION SEMANTIC TEXTUAL SIMILARITY SENTIMENT ANALYSIS TEXT CLASSIFICATION
Generative Modeling by Estimating Gradients of the Data Distribution
• ermongroup/ncsn
•
We introduce a new generative model where samples are produced via Langevin dynamics using gradients of the data distribution estimated with score matching.
SOTA for Image Generation on CIFAR-10
Sliced Score Matching: A Scalable Approach to Density and Score Estimation
• ermongroup/ncsn
•
However, it has been so far limited to simple, shallow models or low-dimensional data, due to the difficulty of computing the Hessian of log-density functions.
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming
• bethgelab/robust-detection-benchmark
The ability to detect objects regardless of image distortions or weather conditions is crucial for real-world applications of deep learning like autonomous driving.
SOTA for Robust Object Detection on COCO
AUTONOMOUS DRIVING DATA AUGMENTATION INSTANCE SEGMENTATION ROBUST OBJECT DETECTION
Med3D: Transfer Learning for 3D Medical Image Analysis
The performance on deep learning is significantly affected by volume of training data.
Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches
• MaurizioFD/RecSys2019_DeepLearning_Evaluation
Deep learning techniques have become the method of choice for researchers working on algorithmic aspects of recommender systems.
Realistic-Neural-Talking-Head-Models
• vincent-thevenin/Realistic-Neural-Talking-Head-Models
•
My implementation of Few-Shot Adversarial Learning of Realistic Neural Talking Head Models (Egor Zakharov et al.).
Natural Adversarial Examples
• hendrycks/natural-adv-examples
We curate 7, 500 natural adversarial examples and release them in an ImageNet classifier test set that we call ImageNet-A.
On the ''steerability" of generative adversarial networks
We hypothesize that the degree of distributional shift is related to the breadth of the training data distribution, and conduct experiments that demonstrate this.
A Baseline for 3D Multi-Object Tracking
Although our baseline system is a straightforward combination of standard methods, we obtain the state-of-the-art results.
SOTA for 3D Multi-Object Tracking on KITTI