Timezone: »

UAST: Uncertainty-Aware Siamese Tracking
Dawei Zhang · Yanwei Fu · Zhonglong Zheng

Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #123

Visual object tracking is basically formulated as target classification and bounding box estimation. Recent anchor-free Siamese trackers rely on predicting the distances to four sides for efficient regression but fail to estimate accurate bounding box in complex scenes. We argue that these approaches lack a clear probabilistic explanation, so it is desirable to model the uncertainty and ambiguity representation of target estimation. To address this issue, this paper presents an Uncertainty-Aware Siamese Tracker (UAST) by developing a novel distribution-based regression formulation with localization uncertainty. We exploit regression vectors to directly represent the discretized probability distribution for four offsets of boxes, which is general, flexible and informative. Based on the resulting distributed representation, our method is able to provide a probabilistic value of uncertainty. Furthermore, considering the high correlation between the uncertainty and regression accuracy, we propose to learn a joint representation head of classification and localization quality for reliable tracking, which also avoids the inconsistency of classification and quality estimation between training and inference. Extensive experiments on several challenging tracking benchmarks demonstrate the effectiveness of UAST and its superiority over other Siamese trackers.

Author Information

Dawei Zhang (Zhejiang Normal University)

Dawei Zhang is working toward the Ph.D. degree in college of mathematics and computer science of Zhejiang Normal University, China. His research interests cover deep learning and computer vision.

Yanwei Fu (Fudan university)
Zhonglong Zheng (Zhejiang Normal University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors