Author name cluster

Trevor Standley

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.

4 papers

2 author rows

ICLR Conference 2023 Conference Paper

An Extensible Multi-modal Multi-task Object Dataset with Materials

Trevor Standley
Ruohan Gao
Dawn Chen
Jiajun Wu 0001
Silvio Savarese

We present EMMa, an Extensible, Multimodal dataset of Amazon product listings that contains rich Material annotations. It contains more than 2.8 million objects, each with image(s), listing text, mass, price, product ratings, and position in Amazon’s product-category taxonomy. We also design a comprehensive taxonomy of 182 physical materials (e.g., Plastic → Thermoplastic → Acrylic). Objects areannotated with one or more materials from this taxonomy. With the numerous attributes available for each object, we develop a Smart Labeling framework to quickly add new binary labels to all objects with very little manual labeling effort, making the dataset extensible. Each object attribute in our dataset can be included in either the model inputs or outputs, leading to combinatorial possibilities in task configurations. For example, we can train a model to predict the object category from the listing text, or the mass and price from the product listing image. EMMa offers a new benchmark for multi-task learning in computer vision and NLP, and allows practitioners to efficiently add new tasks and object attributes at scale.

Details

ICML Conference 2020 Conference Paper

Which Tasks Should Be Learned Together in Multi-task Learning?

Trevor Standley
Amir Zamir
Dawn Chen
Leonidas J. Guibas
Jitendra Malik
Silvio Savarese

Many computer vision applications require solving multiple tasks in real-time. A neural network can be trained to solve multiple tasks simultaneously using multi-task learning. This can save computation at inference time as only a single network needs to be evaluated. Unfortunately, this often leads to inferior overall performance as task objectives can compete, which consequently poses the question: which tasks should and should not be learned together in one network when employing multi-task learning? We study task cooperation and competition in several different learning settings and propose a framework for assigning tasks to a few neural networks such that cooperating tasks are computed by the same neural network, while competing tasks are computed by different networks. Our framework offers a time-accuracy trade-off and can produce better accuracy using less inference time than not only a single large multi-task neural network but also many single-task networks.

Details

IJCAI Conference 2011 Conference Paper

Complete Algorithms for Cooperative Pathfinding Problems

Trevor Standley
Richard Korf

Problems that require multiple agents to follow non-interfering paths from their current states to their respective goal states are called cooperative pathfinding problems. We present the first {complete algorithm for finding these paths that is sufficiently fast for real-time applications. Furthermore, our algorithm offers a trade-off between running time and solution quality. We then refine our algorithm into an anytime algorithm that first quickly finds a solution, and then uses any remaining time to incrementally improve that solution until it is optimal or the algorithm is terminated. We compare our algorithms to those in the literature and show that in addition to completeness, our algorithms offer improved solution quality as well as competitive running time.

PDF Details DOI

AAAI Conference 2010 Conference Paper

Finding Optimal Solutions to Cooperative Pathfinding Problems

Trevor Standley

In cooperative pathfinding problems, non-interfering paths that bring each agent from its current state to its goal state must be planned for multiple agents. We present the first practical, admissible, and complete algorithm for solving problems of this kind. First, we propose a technique called operator decomposition, which can be used to reduce the branching factors of many search algorithms, including algorithms for cooperative pathfinding. We then show how a type of independence common in instances of cooperative pathfinding problems can be exploited. Next, we take the idea of exploiting independent subproblems further by adding improvements that allow the algorithm to recognize many more cases of such independence. Finally, we show empirically that these techniques drastically improve the performance of the standard admissible algorithm for the cooperative pathfinding problem, and that their combination results in a complete algorithm capable of optimally solving relatively large problems in milliseconds.

PDF Details