Ocean: Object-aware Anchor-free Tracking

By Zhipeng Zhang, Houwen Peng. European Conference on Computer Vision, 2020

824 citations recorded by the source corpus.

Anchor-based Siamese trackers have achieved remarkable advancements in accuracy, yet the further improvement is restricted by the lagged tracking robustness. We find the underlying reason is that the regression network in anchor-based methods is only trained on the positive anchor boxes (i.e., $IoU \geq0.6$). This mechanism makes it difficult to refine the anchors whose overlap with the target objects are small. In this paper, we propose a novel object-aware anchor-free network to address this issue. First, instead of refining the reference anchor boxes, we directly predict the position and scale of target objects in an anchor-free fashion. Since each pixel in groundtruth boxes is well trained, the tracker is capable of rectifying inexact predictions of target objects during inference. Second, we introduce a feature alignment module to learn an object-aware feature from predicted bounding boxes. The object-aware feature can further contribute to the classification of target objects and background. Moreover, we present a novel tracking framework based on the anchor-free model. The experiments show that our anchor-free tracker achieves state-of-the-art performance on five benchmarks, including VOT-2018, VOT-2019, OTB-100, GOT-10k and LaSOT. The source code is available at this https URL.

View Paper: https://www.semanticscholar.org/paper/7ad8ed0a7b6d9eafc5af60911aae23fd833e37c3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Xin Chen
2. Martin Danelljan
3. Dong Wang
4. Huchuan Lu
5. Botao Ye
6. Wanli Ouyang
7. Liting Lin
8. Luc Van Gool

Citations in the corpus

• Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking (2022, background): “The compared trackers include SiamFC [2](ECCVW16), ATOM [11] (CVPR19), SiamRPN++ [42](CVPR19), DiMP [3](ICCV19), SiamFC++ [42] (AAAI20), Ocean [49](ECCV20), SiamBAN [9](CVPR20), SiamAtt [45] (CVPR 20), TransT [38](CVPR21), TrDiMP [39](CVPR21), KeepTrack [27](ICCV21), STARKS [43](ICCV21), AutoMatch [”
• SeqTrack: Sequence to Sequence Learning for Visual Object Tracking (2023, methodology): “For example, SiamRPN [27] and its follow-up works [3, 7, 48, 55, 58] adopt classification heads for object localization and regression heads for scale estimation, as sketched in Fig.”
• Is First Person Vision Challenging for Object Tracking? (2020, unknown): “Trackers based on siamese networks [8, 91, 36, 15, 48, 80, 90, 92] emerge as the fastest trackers, thanks to their non-reliance of online adaptation mechanisms.”
• Learning Spatio-Temporal Transformer for Visual Tracking (2021, methodology): “Most of offline Siamese trackers [2, 26, 25, 60, 29] belong to the spatial-only ones, which consider the object tracking as a template-matching between the initial template and the current search region.”
• Learning Target Candidate Association to Keep Track of What Not to Track (2021, background): “Keep Keep Alpha Siam Super STM Pr DM Track Track Refine TransT R-CNN TrDiMP Dimp Track DiMP Track LTMU DiMP Ocean Fast [47] [6] [42] [43] [11] [23] [16] [55] [10] [3] [54]”
• STMTrack: Template-free Visual Tracking with Space-time Memory Networks (2021, methodology): “We test our tracker on the testing set of LaSOT [5], and compare it with twelve competitive methods: LTMU [3], DiMP-50 [1], Occean [21], SiamFC++ [18], GlobalTrack [8], SiamCAR [6], ATOM [4], SiamBAN [2], SiamRPN++ [10], UpdateNet [20], ROAM++ [19], and VITAL [16].”
• SwinTrack: A Simple and Strong Baseline for Transformer Tracking (2021, background): “Later, numerous extensions have been presented to improve [26], including deeper backbone network [25], multi-stage architecture [16, 17], anchor-free Siamese trackers [46].”
• AiATrack: Attention in Attention for Transformer Visual Tracking (2022, background): “Over the past few years, Siamese trackers [2,35,34,67], which regards the visual tracking task as a one-shot matching problem, have gained enormous popularity.”
• Graph Attention Tracking (2020, unknown): “Ocean [36] further applies an online-updating module to dynamically adapt the tracker.”
• Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework (2022, methodology): “Earlier Siamese trackers [1, 26, 50] and discriminative trackers [2, 7] belong to Fig.”
• Transformer Tracking (2021, methodology): “In this subsection, we compare our TransT method with twelve state-of-the-art trackers published in 2020 (SiamR-CNN [39], Ocean [48], KYS [3], DCFST [49],”
• Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark (2021, background): “only, achieves comparable performance with local search trackers [44, 69], but worse than state-of-the-art.”