IASA: An IoU-aware tracker with adaptive sample assignment

Abstract

Most of existing trackers develop tracking in a tracking head network, which is composed of classification branch and regression branch. However, they lack a meaningful exploration of how to define positive and negative samples during training, which can significantly affect tracking performance. Furthermore, they cannot provide a reliable ranking by using classification scores or a combination of classification and regression scores to obtain candidate locations. To address these issues, we propose an intersection over union (IoU) aware tracker with adaptive sample assignment (IASA). The IASA introduces an IoU-aware classification score to achieve a more accurate ranking for candidate tracking locations. We also propose a new loss function, IoU-focal loss, to train the anchor-free tracker IASA to predict the classification scores and introduce a star-shaped box feature representation to refine classification features. To explore the actual content of the training samples, we develop an adaptive sample assignment (ASA) strategy to divide the positive and negative samples according to the statistical characteristics of the sample IoUs. By combining these two proposed components, the IASA tracker treats the tracking task as a classification and a regression problem. It directly finds the candidate tracking location in the classification branch and then regresses the four distances from the location to the four sides of the tracking box. Experimental results show that the proposed IASA can achieve state-of-the-art performance on seven public datasets.