Towards Efficient Training with Negative Samples in Visual Tracking

TL;DR

This paper proposes a novel training strategy for visual object tracking that incorporates negative samples and a distribution-based head to improve efficiency, reduce overfitting, and enhance performance with less data.

Contribution

It introduces Joint learning with Negative samples (JN), a new training approach that effectively handles negative samples and employs a distribution-based bounding box head for better tracking accuracy.

Findings

Achieves 75.8% AO on GOT-10k

Attains 84.1% AUC on TrackingNet

Outperforms larger models trained on more data

Abstract

Current state-of-the-art (SOTA) methods in visual object tracking often require extensive computational resources and vast amounts of training data, leading to a risk of overfitting. This study introduces a more efficient training strategy to mitigate overfitting and reduce computational requirements. We balance the training process with a mix of negative and positive samples from the outset, named as Joint learning with Negative samples (JN). Negative samples refer to scenarios where the object from the template is not present in the search region, which helps to prevent the model from simply memorizing the target, and instead encourages it to use the template for object location. To handle the negative samples effectively, we adopt a distribution-based head, which modeling the bounding box as distribution of distances to express uncertainty about the target's location in the presence of negative samples, offering an efficient way to manage the mixed sample training. Furthermore, our approach introduces a target-indicating token. It encapsulates the target's precise location within the template image. This method provides exact boundary details with negligible computational cost but improving performance. Our model, JN-256, exhibits superior performance on challenging benchmarks, achieving 75.8% AO on GOT-10k and 84.1% AUC on TrackingNet. Notably, JN-256 outperforms previous SOTA trackers that utilize larger models and higher input resolutions, even though it is trained with only half the number of data sampled used in those works.