Author name cluster

Eric Crawford

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

AAAI Conference 2020 Conference Paper

Exploiting Spatial Invariance for Scalable Unsupervised Object Tracking

Eric Crawford
Joelle Pineau

The ability to detect and track objects in the visual world is a crucial skill for any intelligent agent, as it is a necessary precursor to any object-level reasoning process. Moreover, it is important that agents learn to track objects without supervision (i. e. without access to annotated training videos) since this will allow agents to begin operating in new environments with minimal human assistance. The task of learning to discover and track objects in videos, which we call unsupervised object tracking, has grown in prominence in recent years; however, most architectures that address it still struggle to deal with large scenes containing many objects. In the current work, we propose an architecture that scales well to the large-scene, many-object setting by employing spatially invariant computations (convolutions and spatial attention) and representations (a spatially local object speciﬁcation scheme). In a series of experiments, we demonstrate a number of attractive features of our architecture; most notably, that it outperforms competing methods at tracking objects in cluttered scenes with many objects, and that it can generalize well to videos that are larger and/or contain more objects than videos encountered during training.

PDF Details

AAAI Conference 2019 Conference Paper

Spatially Invariant Unsupervised Object Detection with Convolutional Neural Networks

Eric Crawford
Joelle Pineau

There are many reasons to expect an ability to reason in terms of objects to be a crucial skill for any generally intelligent agent. Indeed, recent machine learning literature is replete with examples of the benefits of object-like representations: generalization, transfer to new tasks, and interpretability, among others. However, in order to reason in terms of objects, agents need a way of discovering and detecting objects in the visual world - a task which we call unsupervised object detection. This task has received significantly less attention in the literature than its supervised counterpart, especially in the case of large images containing many objects. In the current work, we develop a neural network architecture that effectively addresses this large-image, many-object setting. In particular, we combine ideas from Attend, Infer, Repeat (AIR), which performs unsupervised object detection but does not scale well, with recent developments in supervised object detection. We replace AIR’s core recurrent network with a convolutional (and thus spatially invariant) network, and make use of an object-specification scheme that describes the location of objects with respect to local grid cells rather than the image as a whole. Through a series of experiments, we demonstrate a number of features of our architecture: that, unlike AIR, it is able to discover and detect objects in large, many-object scenes; that it has a significant ability to generalize to images that are larger and contain more objects than images encountered during training; and that it is able to discover and detect objects with enough accuracy to facilitate non-trivial downstream processing.

PDF Details

RLDM Conference 2017 Conference Abstract

Differentiable Production Systems

Eric Crawford

Production systems have had a remarkable influence on the history of artificial intelligence, though have fallen out of favour in recent years. We propose to take this classical computational mechanism, which have recently been central to efforts to model the flexibility of human behaviour, and modernize it to take advantage of recent advances in deep learning research. In particular, we propose a framework for constructing differentiable computation graphs that combines the strengths of both of these paradigms, namely the flexibility of behaviour of the former and trainability of the latter. Furthermore, we identify an ensemble of tasks that provide significant perceptual, computational and flexibility challenges, and propose to use our framework to train a single model capable of solving any of them without modification.

PDF Details