Self-Supervised Tracking via Target-Aware Data Synthesis

doi:10.1109/TNNLS.2022.3231537

Self-Supervised Tracking via Target-Aware Data Synthesis

2024-07-01

4

OA

AI

DOI：10.1109/TNNLS.2022.3231537

Original

Original request for help

Save

Abstract

En 中文

While deep-learning-based tracking methods have achieved substantial progress, they entail large-scale and high-quality annotated data for sufficient training. To eliminate expensive and exhaustive annotation, we study self-supervised (SS) learning for visual tracking. In this work, we develop the crop-transform-paste operation, which is able to synthesize sufficient training data by simulating various appearance variations during tracking, including appearance variations of objects and background interference. Since the target state is known in all synthesized data, existing deep trackers can be trained in routine ways using the synthesized data without human annotation. The proposed target-aware data-synthesis method adapts existing tracking approaches within a SS learning framework without algorithmic changes. Thus, the proposed SS learning mechanism can be seamlessly integrated into existing tracking frameworks to perform training. Extensive experiments show that our method: 1) achieves favorable performance against supervised (Su) learning schemes under the cases with limited annotations; 2) helps deal with various tracking challenges such as object deformation, occlusion (OCC), or background clutter (BC) due to its manipulability; 3) performs favorably against the state-of-the-art unsupervised tracking methods; and 4) boosts the performance of various state-of-the-art Su learning frameworks, including SiamRPN++, DiMP, and TransT.

Keywords:

Target tracking

Training

Visualization

Annotations

Training data

Learning systems

Task analysis

Crop-transform-paste

self-supervised (SS) learning

visual tracking

Self-Supervised Tracking via Target-Aware Data Synthesis

Abstract

Journal

Organization