Learning Discriminative Model Prediction for Tracking

The current strive towards end-to-end trainable computer vision systems imposes major challenges for the task of visual tracking. In contrast to most other vision problems, tracking requires the learning of a robust target-specific appearance model online, during the inference stage. To be end-to-end trainable, the online learning of the target model thus needs to be embedded in the tracking architecture itself. Due to the imposed challenges, the popular Siamese paradigm simply predicts a target feature template, while ignoring the background appearance information during inference. Consequently, the predicted model possesses limited target-background discriminability. We develop an end-to-end tracking architecture, capable of fully exploiting both target and background appearance information for target model prediction. Our architecture is derived from a discriminative learning loss by designing a dedicated optimization process that is capable of predicting a powerful model in only a few iterations. Furthermore, our approach is able to learn key aspects of the discriminative loss itself. The proposed tracker sets a new state-of-the-art on 6 tracking benchmarks, achieving an EAO score of 0.440 on VOT2018, while running at over 40 FPS. The code and models are available at https://github.com/visionml/pytracking.

PDF Abstract ICCV 2019 PDF ICCV 2019 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Object Tracking FE108 DiMP Success Rate 57.1 # 5
Averaged Precision 85.1 # 6
Visual Object Tracking GOT-10k DiMP Average Overlap 61.1 # 33
Success Rate 0.5 71.7 # 29
Visual Object Tracking LaSOT DiMP-50 Precision 68.7 # 25
Visual Object Tracking LaSOT DiMP AUC 56.8 # 37
Normalized Precision 65.0 # 29
Precision 56.7 # 29
Visual Object Tracking TrackingNet DiMP-50 Normalized Precision 80.1 # 25
Accuracy 74.0 # 27

Methods


No methods listed for this paper. Add relevant methods here