Discover more from Deep Learning Weekly
Deep Learning Weekly Issue #137
Apple acquires XNOR.AI, PyTorch 1.4.0, Efficient Transformers, AutoML from Amazon, and more...
You may also enjoy “A sober look at Bayesian Neural Networks”, a guide to training object detectors with no real data using domain randomization, a sequence model visualization tool from Facebook, an autonomous reinforcement learning library for PyTorch, and a new high-resolution segmentation model architecture.
As always, happy reading and hacking. If you have something you think should be in next week's issue, find us on Twitter: @dl_weekly.
Until next week!
A week after news of Snap’s acquisition of AI Factory, it’s reported that Apple has acquired XNOR to bolster their lower power AI projects.
Amazon open sources an AutoML library with support for hyperparameter tuning, model selection, and more.
Mobile build customization, Distributed model parallel training, Java bindings, and more.
2 million synthetically generated images of 80 humanoid models including 3D pose annotations, body part segmentation, and more.
Creating an image recognition system that automatically train dogs to help get them ready for adoption.
A transformer model from Google specializing in extremely large context windows of up to 1 million words.
Asking the question “Do Bayesian Neural Networks make sense?”
Implemented Deep RL techniques in TF2.
Solving sim2real transfer for specialized object detectors with no budget
Libraries & Code
High-resolution representation learning (HRNets) for Semantic Segmentation
Facebook releases an open source tool for visualizing text generation models.
An implementation of ULMFiT for genomics classification using Pytorch and Fastai.
The Autonomous Learning Library: A PyTorch Library for Building Reinforcement Learning Agents
A neural network library for JAX designed for flexibility
Papers & Publications
Abstract: ....Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle, PyTorch, Caffe2, MxNet, Keras, TensorFlow and it can benchmark the robustness of machine learning models. Compared to previous work, our platform supports black box attacks on Machine-Learning-as-a-service, as well as more attack scenarios, such as Face Recognition Attack, Stealth T-shirt, and Deepfake Face Detect….
Abstract: We introduce HybridPose, a novel 6D object pose estimation approach. HybridPose utilizes a hybrid intermediate representation to express different geometric information in the input image, including keypoints, edge vectors, and symmetry correspondences. Compared to a unitary representation, our hybrid representation allows pose regression to exploit more and diverse features when one type of predicted representation is inaccurate (e.g., because of occlusion). HybridPose leverages a robust regression module to filter out outliers in predicted intermediate representation…. Compared to state-of-the-art pose estimation approaches, HybridPose is comparable in running time and is significantly more accurate. For example, on Occlusion Linemod dataset, our method achieves a prediction speed of 30 fps with a mean ADD(-S) accuracy of 79.2%, representing a 67.4% improvement from the current state-of-the-art approach.