Implicit Object Recognition via Reinforcement Learning in Out-Of-Domain Scenarios
Kenji Koga, Rei Kawakami · 2025
Object detection in novel environments faces a significant challenge due to its reliance on extensive annotated datasets. This paper addresses this challenge by introducing a reinforcement learning (RL)-based framework that eliminates the need for labeled data while enabling implicit object detection. Our approach integrates an open-set object detector within the vision encoder of an RL agent, allowing detection to emerge naturally during task-driven interaction with the environment. By fine-tuning the vision model using Low-Rank Adaptation (LoRA), we achieve efficient and targeted adaptation to the unique visual characteristics of the environment without the computational burden of full retraining. Unlike traditional supervised methods, our RL-driven approach inherently learns to recognize and adapt to objects through interaction, achieving robust detection accuracy and frequency improvements for objects outside the scope of conventional pre-trained datasets. Experimental results demonstrate the efficacy of this annotation-free method, offering a scalable solution for object detection in diverse and evolving environments.