Trained Model Fusion for Object Detection using Gating Network
This work addresses the challenge of integrating multiple camera sources in real-world video surveillance systems, though it appears incremental as it builds on existing transfer learning and fusion techniques.
The paper tackles the problem of transfer learning in video surveillance systems with multiple source domains by proposing a model fusion method using a gating network, achieving high accuracy in object detection tasks as demonstrated on traffic surveillance datasets.
The major approaches of transfer learning in computer vision have tried to adapt the source domain to the target domain one-to-one. However, this scenario is difficult to apply to real applications such as video surveillance systems. As those systems have many cameras installed at each location regarded as source domains, it is difficult to identify the proper source domain. In this paper, we introduce a new transfer learning scenario that has various source domains and one target domain, assuming video surveillance system integration. Also, we propose a novel method for automatically producing a high accuracy model by fusing models trained at various source domains. In particular, we show how to apply a gating network to fuse source domains for object detection tasks, which is a new approach. We demonstrate the effectiveness of our method through experiments on traffic surveillance datasets.