Avoiding Lingering in Learning Active Recognition by Adversarial Disturbance

This paper considers the active recognition scenario, where the agent is empowered to intelligently acquire observations for better recognition. The agents usually compose two modules, i.e., the policy and the recognizer, to select actions and predict the category. While using ground-truth class labels to supervise the recognizer, the policy is typically updated with rewards determined by the current in-training recognizer, like whether achieving correct predictions. However, this joint learning process could lead to unintended solutions, like a collapsed policy that only visits views that the recognizer is already sufficiently trained to obtain rewards, which harms the generalization ability. We call this phenomenon lingering to depict the agent being reluctant to explore challenging views during training. Existing approaches to tackle the exploration-exploitation trade-off could be ineffective as they usually assume reliable feedback during exploration to update the estimate of rarely-visited states. This assumption is invalid here as the reward from the recognizer could be insufficiently trained.To this end, our approach integrates another adversarial policy to constantly disturb the recognition agent during training, forming a competing game to promote active explorations and avoid lingering. The reinforced adversary, rewarded when the recognition fails, contests the recognition agent by turning the camera to challenging observations. Extensive experiments across two datasets validate the effectiveness of the proposed approach regarding its recognition performances, learning efficiencies, and especially robustness in managing environmental noises.