.png){kind=icon}
.png){kind=icon}
Return
MINet: Meta-Learning Instance Identifiers for Video Object Detection
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2021.3099409.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recent advances in video object detection have characterized the exploration of temporal coherence across frames to enhance object detector. Nevertheless, previous solutions either rely on additional inputs (e.g., optical flow) to guide feature aggregation, or complex post-processing to associate bounding boxes. In this paper, we introduce a simple but effective design that learns instance identifiers for instance association in a meta-learning paradigm, which requires no auxiliary inputs or post-processing. Specifically, we present Meta-Learnt Instance Identifier Networks (namely MINet) that novelly meta-learns instance identifiers to recognize identical instances across frames in a single forward-pass, leading to the robust online linking of instances. Technically, depending on the detection results of previous frames, we teach MINet to learn the weights of an instance identifier on the fly, which can be well applied to up-coming frames. Such meta-learning paradigm enables instance identifiers to be flexibly adapted to novel frames at inference. Furthermore, MINet writes/updates the detection results of previous instances into memory and reads from memory when performing inference to encourage temporal consistency for video object detection. Our MINet is appealing in the sense that it is pluggable to any object detection model. Extensive experiments on ImageNet VID dataset demonstrate the superiority of MINet. More remarkably, by integrating MINet into Faster R-CNN, we achieve 80.2% mAP on ImageNet VID dataset.
Keywords:
Object detection
Feature extraction
Detectors
Proposals
Optical imaging
Robustness
History
Video object detection
meta learning
memory network
box association
Journal
IF:
13.7
Papers:
1.0W
Citations:
8.4W