MotionLM: Multi-Agent Motion Forecasting as Language Modeling

Reliable forecasting of the future behavior of road agents is a critical component to safe planning in autonomous vehicles. Here, we represent continuous trajectories as sequences of discrete motion tokens and cast multi-agent motion prediction as a language modeling task over this domain. Our model, MotionLM, provides several advantages: First, it does not require anchors or explicit latent variable optimization to learn multimodal distributions. Instead, we leverage a single standard language modeling objective, maximizing the average log probability over sequence tokens. Second, our approach bypasses post-hoc interaction heuristics where individual agent trajectory generation is conducted prior to interactive scoring. Instead, MotionLM produces joint distributions over interactive agent futures in a single autoregressive decoding process. In addition, the model's sequential factorization enables temporally causal conditional rollouts. The proposed approach establishes new state-of-the-art performance for multi-agent motion prediction on the Waymo Open Motion Dataset, ranking 1st on the interactive challenge leaderboard.

Vitruvion: A Generative Model of Parametric CAD Sketches

Parametric computer-aided design (CAD) tools are the predominant way that engineers specify physical structures, from bicycle pedals to airplanes to printed circuit boards. The key characteristic of parametric CAD is that design intent is encoded not only via geometric primitives, but also by parameterized constraints between the elements. This relational specification can be viewed as the construction of a constraint program, allowing edits to coherently propagate to other parts of the design. Machine learning offers the intriguing possibility of accelerating the design process via generative modeling of these structures, enabling new tools such as autocompletion, constraint inference, and conditional synthesis. In this work, we present such an approach to generative modeling of parametric CAD sketches, which constitute the basic computational building blocks of modern mechanical design. Our model, trained on real-world designs from the SketchGraphs dataset, autoregressively synthesizes sketches as sequences of primitives, with initial coordinates, and constraints that reference back to the sampled primitives. As samples from the model match the constraint graph representation used in standard CAD software, they may be directly imported, solved, and edited according to downstream design tasks. In addition, we condition the model on various contexts, including partial sketches (primers) and images of hand-drawn sketches. Evaluation of the proposed approach demonstrates its ability to synthesize realistic CAD sketches and its potential to aid the mechanical design workflow.

SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design

Parametric computer-aided design (CAD) is the dominant paradigm in mechanical engineering for physical design. Distinguished by relational geometry, parametric CAD models begin as two-dimensional sketches consisting of geometric primitives (e.g., line segments, arcs) and explicit constraints between them (e.g., coincidence, perpendicularity) that form the basis for three-dimensional construction operations. Training machine learning models to reason about and synthesize parametric CAD designs has the potential to reduce design time and enable new design workflows. Additionally, parametric CAD designs can be viewed as instances of constraint programming and they offer a well-scoped test bed for exploring ideas in program synthesis and induction. To facilitate this research, we introduce SketchGraphs, a collection of 15 million sketches extracted from real-world CAD models coupled with an open-source data processing pipeline. Each sketch is represented as a geometric constraint graph where edges denote designer-imposed geometric relationships between primitives, the nodes of the graph. We demonstrate and establish benchmarks for two use cases of the dataset: generative modeling of sketches and conditional generation of likely constraints given unconstrained geometry.

Discrete Object Generation with Reversible Inductive Construction

The success of generative modeling in continuous domains has led to a surge of interest in generating discrete data such as molecules, source code, and graphs. However, construction histories for these discrete objects are typically not unique and so generative models must reason about intractably large spaces in order to learn. Additionally, structured discrete domains are often characterized by strict constraints on what constitutes a valid object and generative models must respect these requirements in order to produce useful novel samples. Here, we present a generative model for discrete objects employing a Markov chain where transitions are restricted to a set of local operations that preserve validity. Building off of generative interpretations of denoising autoencoders, the Markov chain alternates between producing 1) a sequence of corrupted objects that are valid but not from the data distribution, and 2) a learned reconstruction distribution that attempts to fix the corruptions while also preserving validity. This approach constrains the generative model to only produce valid objects, requires the learner to only discover local modifications to the objects, and avoids marginalization over an unknown and potentially large space of construction histories. We evaluate the proposed approach on two highly structured discrete domains, molecules and Laman graphs, and find that it compares favorably to alternative methods at capturing distributional statistics for a host of semantically relevant metrics.

Continual Learning in Generative Adversarial Nets

Developments in deep generative models have allowed for tractable learning of high-dimensional data distributions. While the employed learning procedures typically assume that training data is drawn i.i.d. from the distribution of interest, it may be desirable to model distinct distributions which are observed sequentially, such as when different classes are encountered over time. Although conditional variations of deep generative models permit multiple distributions to be modeled by a single network in a disentangled fashion, they are susceptible to catastrophic forgetting when the distributions are encountered sequentially. In this paper, we adapt recent work in reducing catastrophic forgetting to the task of training generative adversarial networks on a sequence of distinct distributions, enabling continual generative modeling.

Learning from Maps: Visual Common Sense for Autonomous Driving

Today's autonomous vehicles rely extensively on high-definition 3D maps to navigate the environment. While this approach works well when these maps are completely up-to-date, safe autonomous vehicles must be able to corroborate the map's information via a real time sensor-based system. Our goal in this work is to develop a model for road layout inference given imagery from on-board cameras, without any reliance on high-definition maps. However, no sufficient dataset for training such a model exists. Here, we leverage the availability of standard navigation maps and corresponding street view images to construct an automatically labeled, large-scale dataset for this complex scene understanding problem. By matching road vectors and metadata from navigation maps with Google Street View images, we can assign ground truth road layout attributes (e.g., distance to an intersection, one-way vs. two-way street) to the images. We then train deep convolutional networks to predict these road layout attributes given a single monocular RGB image. Experimental evaluation demonstrates that our model learns to correctly infer the road attributes using only panoramas captured by car-mounted cameras as input. Additionally, our results indicate that this method may be suitable to the novel application of recommending safety improvements to infrastructure (e.g., suggesting an alternative speed limit for a street).

LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop

While there has been remarkable progress in the performance of visual recognition algorithms, the state-of-the-art models tend to be exceptionally data-hungry. Large labeled training datasets, expensive and tedious to produce, are required to optimize millions of parameters in deep network models. Lagging behind the growth in model capacity, the available datasets are quickly becoming outdated in terms of size and density. To circumvent this bottleneck, we propose to amplify human effort through a partially automated labeling scheme, leveraging deep learning with humans in the loop. Starting from a large set of candidate images for each category, we iteratively sample a subset, ask people to label them, classify the others with a trained model, split the set into positives, negatives, and unlabeled based on the classification confidence, and then iterate with the unlabeled set. To assess the effectiveness of this cascading procedure and enable further progress in visual recognition research, we construct a new image dataset, LSUN. It contains around one million labeled images for each of 10 scene categories and 20 object categories. We experiment with training popular convolutional networks and find that they achieve substantial performance gains when trained on this dataset.

DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving

Today, there are two major paradigms for vision-based autonomous driving systems: mediated perception approaches that parse an entire scene to make a driving decision, and behavior reflex approaches that directly map an input image to a driving action by a regressor. In this paper, we propose a third paradigm: a direct perception approach to estimate the affordance for driving. We propose to map an input image to a small number of key perception indicators that directly relate to the affordance of a road/traffic state for driving. Our representation provides a set of compact yet complete descriptions of the scene to enable a simple controller to drive autonomously. Falling in between the two extremes of mediated perception and behavior reflex, we argue that our direct perception representation provides the right level of abstraction. To demonstrate this, we train a deep Convolutional Neural Network using recording from 12 hours of human driving in a video game and show that our model can work well to drive a car in a very diverse set of virtual environments. We also train a model for car distance estimation on the KITTI dataset. Results show that our direct perception approach can generalize well to real driving images. Source code and data are available on our project website.

Improving Computer-aided Detection using Convolutional Neural Networks and Random View Aggregation

Automated computer-aided detection (CADe) in medical imaging has been an important tool in clinical practice and research. State-of-the-art methods often show high sensitivities but at the cost of high false-positives (FP) per patient rates. We design a two-tiered coarse-to-fine cascade framework that first operates a candidate generation system at sensitivities of $\sim$100% but at high FP levels. By leveraging existing CAD systems, coordinates of regions or volumes of interest (ROI or VOI) for lesion candidates are generated in this step and function as input for a second tier, which is our focus in this study. In this second stage, we generate $N$ 2D (two-dimensional) or 2.5D views via sampling through scale transformations, random translations and rotations with respect to each ROI's centroid coordinates. These random views are used to train deep convolutional neural network (ConvNet) classifiers. In testing, the trained ConvNets are employed to assign class (e.g., lesion, pathology) probabilities for a new set of $N$ random views that are then averaged at each ROI to compute a final per-candidate classification probability. This second tier behaves as a highly selective process to reject difficult false positives while preserving high sensitivities. The methods are evaluated on three different data sets with different numbers of patients: 59 patients for sclerotic metastases detection, 176 patients for lymph node detection, and 1,186 patients for colonic polyp detection. Experimental results show the ability of ConvNets to generalize well to different medical imaging CADe applications and scale elegantly to various data sets. Our proposed methods improve CADe performance markedly in all cases. CADe sensitivities improved from 57% to 70%, from 43% to 77% and from 58% to 75% at 3 FPs per patient for sclerotic metastases, lymph nodes and colonic polyps, respectively.

Interleaved Text/Image Deep Mining on a Large-Scale Radiology Database for Automated Image Interpretation

Despite tremendous progress in computer vision, there has not been an attempt for machine learning on very large-scale medical image databases. We present an interleaved text/image deep learning system to extract and mine the semantic interactions of radiology images and reports from a national research hospital's Picture Archiving and Communication System. With natural language processing, we mine a collection of representative ~216K two-dimensional key images selected by clinicians for diagnostic reference, and match the images with their descriptions in an automated manner. Our system interleaves between unsupervised learning and supervised learning on document- and sentence-level text collections, to generate semantic labels and to predict them given an image. Given an image of a patient scan, semantic topics in radiology levels are predicted, and associated key-words are generated. Also, a number of frequent disease types are detected as present or absent, to provide more specific interpretation of a patient scan. This shows the potential of large-scale learning and prediction in electronic patient records available in most modern clinical institutions.