AccLoc: Anchor-Free and two-stage detector for accurate object localization

Current anchor-free object detectors have obtained detection performances comparable to those of anchor-based object detectors while avoiding the weaknesses of anchor designs. However, two issues limit the localization performance. First, such anchor-free detectors have one stage that predicts the classification and localization results directly. A large regression space reduces the localization performance of such methods. Second, most of the existing detectors extract features which are ineffective for accurate localization. In this paper, for the first issue, we propose two-stage networks to predict regression results stage by stage, thereby reducing the scope of the prediction space. For the second issue, we design two novel modules with the aim of extracting effective features for accurate localization. Experimental results validate that each module in our approach is effective and validate that our approach has better object localization performance than previous related and advanced methods.