Semantic Curiosity for Active Visual Learning

By Devendra Singh Chaplot, Helen Jiang, Saurabh Gupta, Abhinav Kumar Gupta. 2020

93 citations recorded by the source corpus.

In this paper, we study the task of embodied interactive learning for object detection. Given a set of environments (and some labeling budget), our goal is to learn an object detector by having an agent select what data to obtain labels for. How should an exploration policy decide which trajectory should be labeled? One possibility is to use a trained object detector's failure cases as an external reward. However, this will require labeling millions of frames required for training RL policies, which is infeasible. Instead, we explore a self-supervised approach for training our exploration policy by introducing a notion of semantic curiosity. Our semantic curiosity policy is based on a simple observation -- the detection outputs should be consistent. Therefore, our semantic curiosity rewards trajectories with inconsistent labeling behavior and encourages the exploration policy to explore such areas. The exploration policy trained via semantic curiosity generalizes to novel scenes and helps train an object detector that outperforms baselines trained with other possible alternatives such as random exploration, prediction-error curiosity, and coverage-maximizing exploration.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Few-Shot Continual Active Learning by a Robot (2022, methodology): “Most active learning techniques use uncertainty sampling to request labels for the most uncertain objects [15, 14, 16].”
A Survey of Embodied AI: From Simulators to Research Tasks (2021, methodology): “Curiosity has been used to generate more advancedd maps like semantic maps in recent work [66].”
Object Goal Navigation using Goal-Oriented Semantic Exploration (2020, background): “Concurrent work studies the use of similar semantic maps in learning exploration policies for improving object detection systems [10].”
NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration (2023, methodology): “These policies have been trained with reinforcement learning to maximize coverage, predicting semantically rich regions, intrinsic rewards [13, 14, 18, 19], or by using planning in conjunction with latent variable and affordance models [17, 20, 21].”
Embodied Semantic Scene Graph Generation (2021, background): “Furthermore, Chaplot et al. [20] studies the task of embodied interactive learning for object detection.”