Predicting future behaviors of road agents is a key task in autonomous driving. While existing models have demonstrated great success in predicting marginal agent future behaviors, it remains a challenge to efficiently predict consistent joint behaviors of multiple agents. Recently, the occupancy flow fields representation was proposed to represent joint future states of road agents through a combination of occupancy grid and flow, which supports efficient and consistent joint predictions. In this work, we propose a novel occupancy flow fields predictor to produce accurate occupancy and flow predictions, by combining the power of an image encoder that learns features from a rasterized traffic image and a vector encoder that captures information of continuous agent trajectories and map states. The two encoded features are fused by multiple attention modules before generating final predictions. Our simple but effective model ranks 3rd place on the Waymo Open Dataset Occupancy and Flow Prediction Challenge, and achieves the best performance in the occluded occupancy and flow prediction task.

Previous lists have included both general purpose and specialized machine learning and deep learning libraries, along with auxiliary support, data cleaning, and automation tools. This time around we showcase 5 more machine learning-related projects which you may not yet heard of, including those from across a number of different ecosystems and programming languages. You may find that, even if you have no requirement for any of these particular tools, inspecting their broad implementation details or their specific code may help in generating some ideas of your own. Like the previous iteration, there is no formal criteria for inclusion beyond projects that have caught my eye over time spent online, and the projects have Github repositories. Yes, it's subjective, but there is no qualitative approach to this task that would make any sense.

Previous lists have included both general purpose and specialized machine learning and deep learning libraries, along with auxiliary support, data cleaning, and automation tools. Vectorflow looks to be an interesting machine learning project for those in the D ecosystem. The link above is to a blog post introducing Optimus, a library for accomplishing just that. Facets is a machine learning dataset visualization library.

With the deluge of deep learning libraries and software innovation in the field over the last few years, it is an exciting time to be working on machine learning problems. Most of the libraries available evolved from fairly specialized computational code for large dense problems such as image classification into general frameworks for neural-network-based models offering marginal support for sparse models. At Netflix, our machine learning scientists deal with a wide variety of problems across a broad spectrum of areas: from tailoring TV and movie recommendations to your taste to optimizing encoding algorithms. A subset of our problems involve dealing with extremely sparse data; the total dimensionality of the problem at hand can easily reach tens of millions of features, even though every observation may only have a handful of non-zero entries. For these cases, we felt the need for a minimalist library that is specifically optimized for training shallow feedforward neural nets on sparse data in a single-machine, multi-core environment.