LATERAL: Learning Automatic, Transfer-Enhanced, and Relation-Aware Labels

Abstract

Our team obtained excellent results in all of the official evaluations of the Darpa Learning with Less Labels (LwLL) program. We participated in the image classification, object detection, and machine translation tasks. For many of the checkpoints, we achieved the very best results across all performers, significantly outperforming the baseline provided by the JPL team. A key lesson learned to achieve these strong results was to focus on finding a good feature embedding, so that new tasks can be learned with just a few examples. In this vein, we proposed novel approaches for representation learning (across domains and modalities, using real and synthetic data), explored new model architectures, as well as transfer learning techniques. These research works have been published in top-tier AI conferences and several of them integrated into our high-performing systems delivered to Darpa for the official program evaluations.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 24, 2023
Accession Number
AD1206340

Entities

People

  • Aadarsh Sahoo
  • Assaf Arbelle
  • Graeme Blackwood
  • Joseph Schtok
  • Leonid Karlinsky
  • Rogerio Feris

Organizations

  • International Business Machines Corporation (Armonk, NY)

Tags

Communities of Interest

  • Materials and Manufacturing Processes
  • Space

DTIC Thesaurus Topics

  • Air Force
  • Artificial Intelligence
  • Artificial Intelligence Software
  • Computational Science
  • Computer Languages
  • Cross Domain
  • Data Sets
  • Detection
  • Image Classification
  • Information Systems
  • Language
  • Machine Learning
  • Machine Translation
  • Recognition
  • Standards
  • Supervised Machine Learning
  • Translations

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Research Science/Academic Research

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks