Abstract
We propose a new paradigm of the detection task that is anchor-box free and NMS free. Although the current state-of-the-art model that based on region proposed method has been well-acknowledged for years, however as the basis of RPN, NMS cannot solve the problem of low recall in complicated occlusion situation. This situation is particularly critical when it faces up to complex occlusion. We proposed to use weak-supervised segmentation multimodal annotations to achieve a highly robust object detection performance without NMS. In such cases, we utilize poor annotated Bounding Box annotations to perform a robust object detection performance in the difficult circumstance. We have avoided all hyperparameters related to anchor boxes and NMS. Our proposed model has outperformed previous anchor-based one-stage and multi-stage detectors with the advantage of being much simpler. We have reached a state-of-the-art performance in both accuracies, recall rate.
Abstract (translated by Google)
URL
http://arxiv.org/abs/1904.13300