FIANET: VIDEO OBJECT DETECTION VIA JOINT FEATURE-LEVEL AND INSTANCE-LEVEL AGGREGATION

Video object detection task is challenging due to the non-rigid and rigid appearance deformations in videos. Most of the typical competitive methods are to enhance per-frame features through aggregating lots of previous and future frames. But feature-level aggregation isn’t robust to rigid deformations such as occlusion and rare postures. In this paper, we propose an online video object detection method with joint feature-level aggregation and instance-level aggregation network (FIANet). Besides feature-level aggregation, we design a spatial-temporal instance calibration module (STIC) to aggregate the instance as a whole, which can reduce the interference of local distorted and missed pixels. Joint feature-level and instance-level aggregation can work collaboratively to overcome different deformations. Only using less previous frames, our method can achieve 81.6% mAP with relatively high speed on ImageNet VID, which is state-of-the-art compared with causal and non-causal methods.