Interactron: Embodied Adaptive Object Detection

by   Klemen Kotar, et al.

Over the years various methods have been proposed for the problem of object detection. Recently, we have witnessed great strides in this domain owing to the emergence of powerful deep neural networks. However, there are typically two main assumptions common among these approaches. First, the model is trained on a fixed training set and is evaluated on a pre-recorded test set. Second, the model is kept frozen after the training phase, so no further updates are performed after the training is finished. These two assumptions limit the applicability of these methods to real-world settings. In this paper, we propose Interactron, a method for adaptive object detection in an interactive setting, where the goal is to perform object detection in images observed by an embodied agent navigating in different environments. Our idea is to continue training during inference and adapt the model at test time without any explicit supervision via interacting with the environment. Our adaptive object detection model provides a 11.8 point improvement in AP (and 19.1 points in AP50) over DETR, a recent, high-performance object detector. Moreover, we show that our object detection model adapts to environments with completely different appearance characteristics, and its performance is on par with a model trained with full supervision for those environments.


page 1

page 5

page 8

page 12


STFAR: Improving Object Detection Robustness at Test-Time by Self-Training with Feature Alignment Regularization

Domain adaptation helps generalizing object detection models to target d...

Comparison Detector: A novel object detection method for small dataset

Though the object detection has shown great success when the training se...

Deep Domain Adaptive Object Detection: a Survey

Deep learning (DL) based object detection has achieved great progress. T...

Exploring the Effectiveness of Dataset Synthesis: An application of Apple Detection in Orchards

Deep object detection models have achieved notable successes in recent y...

LabelEnc: A New Intermediate Supervision Method for Object Detection

In this paper we propose a new intermediate supervision method, named La...

Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels

Training with more data has always been the most stable and effective wa...

Please sign up or login with your details

Forgot password? Click here to reset