ViDT: An Efficient and Effective Fully Transformer-based Object Detector
This work addresses the need for efficient object detection in computer vision, though it is incremental as it builds on existing transformer architectures.
The authors tackled the problem of building an efficient and effective fully transformer-based object detector by integrating Vision and Detection Transformers (ViDT), achieving a best AP and latency trade-off on the COCO benchmark with 49.2 AP.
Transformers are transforming the landscape of computer vision, especially for recognition tasks. Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the first fully transformer-based architecture for image classification. In this paper, we integrate Vision and Detection Transformers (ViDT) to build an effective and efficient object detector. ViDT introduces a reconfigured attention module to extend the recent Swin Transformer to be a standalone object detector, followed by a computationally efficient transformer decoder that exploits multi-scale features and auxiliary techniques essential to boost the detection performance without much increase in computational load. Extensive evaluation results on the Microsoft COCO benchmark dataset demonstrate that ViDT obtains the best AP and latency trade-off among existing fully transformer-based object detectors, and achieves 49.2AP owing to its high scalability for large models. We will release the code and trained models at https://github.com/naver-ai/vidt