Despite of the recent success of collective entity linking (EL) methods, these "global" inference methods may yield sub-optimal results when the "all-mention coherence" assumption breaks, and often suffer from high computational cost at the inference stage, due to the complex search space. In this paper, we propose a simple yet effective solution, called Dynamic Context Augmentation (DCA), for collective EL, which requires only one pass through the mentions in a document. DCA sequentially accumulates context information to make efficient, collective inference, and can cope with different local EL models as a plug-and-enhance module. We explore both supervised and reinforcement learning strategies for learning the DCA model. Extensive experiments show the effectiveness of our model with different learning settings, base models, decision orders and attention mechanisms.
Object detection methods fall into two categories, i.e., two-stage and single-stage detectors. The former is characterized by high detection accuracy while the latter usually has considerable inference speed. Hence, it is imperative to fuse their metrics for a better accuracy vs. speed trade-off. To this end, we propose a dual refinement network (DRN) to boost the performance of the single-stage detector. Inheriting from the advantages of two-stage approaches (i.e., two-step regression and accurate features for detection), anchor refinement and feature offset refinement are conducted in anchor-offset detection, where the detection head is comprised of deformable convolutions. Moreover, to leverage contextual information for describing objects, we design a multi-deformable head, in which multiple detection paths with different receptive field sizes devote themselves to detecting objects. Extensive experiments on PASCAL VOC and ImageNet VID datasets are conducted, and we achieve the state-of-the-art results and a better accuracy vs. speed trade-off, i.e., 81.4% mAP vs. 42.3 FPS on VOC2007 test set. Codes will be publicly available.