Towards Accurate Pixel-wise Object Tracking by Attention Retrieval

TL;DR

This paper introduces an attention retrieval network and multi-stage segmentation to improve pixel-wise object tracking accuracy, effectively reducing background clutter influence and achieving state-of-the-art results at real-time speed.

Contribution

The paper proposes a novel attention retrieval network and multi-resolution segmentation approach that enhance pixel-wise tracking accuracy by mitigating background interference.

Findings

Achieved state-of-the-art performance on VOT2020 benchmark.

Surpassed SiamMask by significant margin on multiple datasets.

Operates at 40 fps, enabling real-time tracking.

Abstract

The encoding of the target in object tracking moves from the coarse bounding-box to fine-grained segmentation map recently. Revisiting de facto real-time approaches that are capable of predicting mask during tracking, we observed that they usually fork a light branch from the backbone network for segmentation. Although efficient, directly fusing backbone features without considering the negative influence of background clutter tends to introduce false-negative predictions, lagging the segmentation accuracy. To mitigate this problem, we propose an attention retrieval network (ARN) to perform soft spatial constraints on backbone features. We first build a look-up-table (LUT) with the ground-truth mask in the starting frame, and then retrieves the LUT to obtain an attention map for spatial constraints. Moreover, we introduce a multi-resolution multi-stage segmentation network (MMS) to further weaken the influence of background clutter by reusing the predicted mask to filter backbone features. Our approach set a new state-of-the-art on recent pixel-wise object tracking benchmark VOT2020 while running at 40 fps. Notably, the proposed model surpasses SiamMask by 11.7/4.2/5.5 points on VOT2020, DAVIS2016, and DAVIS2017, respectively. We will release our code at https://github.com/researchmm/TracKit.