Object Permanence in Object Detection Leveraging Temporal Priors at Inference Time
This addresses the challenge of reliable object detection under occlusion for applications like real-world video analysis, though it is an incremental improvement on existing two-stage detectors.
The paper tackled the problem of object permanence in object detection by introducing a method that uses predictions from previous frames as proposals at inference time, improving detection performance by up to 10.3 mAP with minimal computational overhead.
Object permanence is the concept that objects do not suddenly disappear in the physical world. Humans understand this concept at young ages and know that another person is still there, even though it is temporarily occluded. Neural networks currently often struggle with this challenge. Thus, we introduce explicit object permanence into two stage detection approaches drawing inspiration from particle filters. At the core, our detector uses the predictions of previous frames as additional proposals for the current one at inference time. Experiments confirm the feedback loop improving detection performance by a up to 10.3 mAP with little computational overhead. Our approach is suited to extend two-stage detectors for stabilized and reliable detections even under heavy occlusion. Additionally, the ability to apply our method without retraining an existing model promises wide application in real-world tasks.