Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery

Katie Z. Luo*, Zhenzhen Liu, Xiangyu Chen, Yurong You, Sagie Benaim, Cheng Perng Phoo, Mark Campbell, Wen Sun, Bharath Hariharan, Kilian Q. Weinberger

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

Abstract

Recent advances in machine learning have shown that Reinforcement Learning from Human Feedback (RLHF) can improve machine learning models and align them with human preferences. Although very successful for Large Language Models (LLMs), these advancements have not had a comparable impact in research for autonomous vehicles-where alignment with human expectations can be imperative. In this paper, we propose to adapt similar RL-based methods to unsupervised object discovery, i.e. learning to detect objects from LiDAR points without any training labels. Instead of labels, we use simple heuristics to mimic human feedback. More explicitly, we combine multiple heuristics into a simple reward function that positively correlates its score with bounding box accuracy, i.e., boxes containing objects are scored higher than those without. We start from the detector's own predictions to explore the space and reinforce boxes with high rewards through gradient updates. Empirically, we demonstrate that our approach is not only more accurate, but also orders of magnitudes faster to train compared to prior works on object discovery. Code is available at https://github.com/katieluo88/DRIFT.

Original languageEnglish
JournalAdvances in Neural Information Processing Systems
Volume36
StatePublished - 2023
Event37th Conference on Neural Information Processing Systems, NeurIPS 2023 - New Orleans, United States
Duration: 10 Dec 202316 Dec 2023
Conference number: 37

Bibliographical note

Publisher Copyright:
© 2023 Neural information processing systems foundation. All rights reserved.

Fingerprint

Dive into the research topics of 'Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery'. Together they form a unique fingerprint.

Cite this