Hard Negative Samples Emphasis Tracker without Anchors

Abstract

Trackers based on Siamese network have shown tremendous success, because of their balance between accuracy and speed. Nevertheless, with tracking scenarios becoming more and more sophisticated, most existing Siamese-based approaches ignore the addressing of the problem that distinguishes the tracking target from hard negative samples in the tracking phase. The features learned by these networks lack of discrimination, which significantly weakens the robustness of Siamese-based trackers and leads to suboptimal performance. To address this issue, we propose a simple yet efficient hard negative samples emphasis method, which constrains Siamese network to learn features that are aware of hard negative samples and enhance the discrimination of embedding features. Through a distance constraint, we force to shorten the distance between exemplar vector and positive vectors, meanwhile, enlarge the distance between exemplar vector and hard negative vectors. Furthermore, we explore a novel anchor-free tracking framework in a per-pixel prediction fashion, which can significantly reduce the number of hyper-parameters and simplify the tracking process by taking full advantage of the representation of convolutional neural network. Extensive experiments on six standard benchmark datasets demonstrate that the proposed method can perform favorable results against state-of-the-art approaches.

arXiv commentaccepted by ACM Mutlimedia Conference, 2020

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
• Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
• Learning Spatially Regularized Correlation Filters for Visual Tracking
• UnitBox: An Advanced Object Detection Network
• Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Tracking
• Context-aware Deep Feature Compression for High-speed Visual Tracking
• SiamVGG: Visual Tracking using Deeper Siamese Networks

Cited by in corpus (1)

• Domain Adaptive SiamRPN++ for Object Tracking in the Wild