SiamCorners: Siamese Corner Networks for Visual Tracking

• URL: http://arxiv.org/abs/2104.07303v1
• Date: Thu, 15 Apr 2021 08:23:30 GMT
• Title: SiamCorners: Siamese Corner Networks for Visual Tracking
• Authors: Kai Yang, Zhenyu He, Wenjie Pei, Zikun Zhou, Xin Li, Di Yuan and Haijun Zhang
• Abstract summary: We propose a simple yet effective anchor-free tracker (named Siamese corner networks, SiamCorners) By tracking a target as a pair of corners, we avoid the need to design the anchor boxes. SiamCorners achieves a 53.7% AUC on NFS30 and a 61.4% AUC on UAV123, while still running at 42 frames per second (FPS)
• Score: 39.43480791427431
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The current Siamese network based on region proposal network (RPN) has attracted great attention in visual tracking due to its excellent accuracy and high efficiency. However, the design of the RPN involves the selection of the number, scale, and aspect ratios of anchor boxes, which will affect the applicability and convenience of the model. Furthermore, these anchor boxes require complicated calculations, such as calculating their intersection-over-union (IoU) with ground truth bounding boxes.Due to the problems related to anchor boxes, we propose a simple yet effective anchor-free tracker (named Siamese corner networks, SiamCorners), which is end-to-end trained offline on large-scale image pairs. Specifically, we introduce a modified corner pooling layer to convert the bounding box estimate of the target into a pair of corner predictions (the bottom-right and the top-left corners). By tracking a target as a pair of corners, we avoid the need to design the anchor boxes. This will make the entire tracking algorithm more flexible and simple than anchorbased trackers. In our network design, we further introduce a layer-wise feature aggregation strategy that enables the corner pooling module to predict multiple corners for a tracking target in deep networks. We then introduce a new penalty term that is used to select an optimal tracking box in these candidate corners. Finally, SiamCorners achieves experimental results that are comparable to the state-of-art tracker while maintaining a high running speed. In particular, SiamCorners achieves a 53.7% AUC on NFS30 and a 61.4% AUC on UAV123, while still running at 42 frames per second (FPS).

Related papers

• Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Tracking [54.124445709376154]
  We propose a novel asymmetric Siamese tracker named textbfAsymTrack for efficient tracking. Building on this architecture, we devise an efficient template modulation mechanism to inject crucial cues into the search features. Experiments demonstrate that AsymTrack offers superior speed-precision trade-offs across different platforms.
  arXiv  Detail & Related papers  (2025-03-01T14:44:54Z)
• OSP2B: One-Stage Point-to-Box Network for 3D Siamese Tracking [7.868399549570768]
  Two-stage point-to-box network acts as a critical role in the recent popular 3D Siamese tracking paradigm. We propose a simple yet effective one-stage point-to-box network for point cloud-based 3D single object tracking. By integrating the derived classification scores with the center-ness scores, the resulting network can effectively suppress interference proposals.
  arXiv  Detail & Related papers  (2023-04-23T08:52:36Z)
• MixFormer: Mixing Features across Windows and Dimensions [68.86393312123168]
  Local-window self-attention performs notably in vision tasks, but suffers from limited receptive field and weak modeling capability issues. This is mainly because it performs self-attention within non-overlapped windows and shares weights on the channel dimension. We combine local-window self-attention with depth-wise convolution in a parallel design, modeling cross-window connections to enlarge the receptive fields.
  arXiv  Detail & Related papers  (2022-04-06T03:13:50Z)
• TAP-Net: Transport-and-Pack using Reinforcement Learning [25.884588673613244]
  We introduce the transport-and-pack(TAP) problem, a frequently encountered instance of real-world packing. We develop a neural optimization solution based on reinforcement learning. We show that our network generalizes well to larger problem instances, when trained on small-sized inputs.
  arXiv  Detail & Related papers  (2020-09-03T06:20:17Z)
• Corner Proposal Network for Anchor-free, Two-stage Object Detection [174.59360147041673]
  The goal of object detection is to determine the class and location of objects in an image. This paper proposes a novel anchor-free, two-stage framework which first extracts a number of object proposals. We demonstrate that these two stages are effective solutions for improving recall and precision.
  arXiv  Detail & Related papers  (2020-07-27T19:04:57Z)
• Ocean: Object-aware Anchor-free Tracking [75.29960101993379]
  The regression network in anchor-based methods is only trained on the positive anchor boxes. We propose a novel object-aware anchor-free network to address this issue. Our anchor-free tracker achieves state-of-the-art performance on five benchmarks.
  arXiv  Detail & Related papers  (2020-06-18T17:51:39Z)
• Accurate Anchor Free Tracking [9.784386353369483]
  This paper develops the first Anchor Free Siamese Network (AFSN) A target object is defined by a bounding box center, tracking offset, and object size. We compare AFSN to the best anchor-based trackers with source codes available for each benchmark.
  arXiv  Detail & Related papers  (2020-06-13T04:42:32Z)
• Siamese Keypoint Prediction Network for Visual Object Tracking [11.25492557077732]
  We propose the Siamese keypoint prediction network (SiamKPN) to address these challenges. SiamKPN benefits from a cascade heatmap strategy for coarse-to-fine prediction modeling. It performs well against state-of-the-art trackers for visual object tracking on four benchmark datasets.
  arXiv  Detail & Related papers  (2020-06-07T08:11:06Z)
• Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible Noises [87.53808756910452]
  A cooling-shrinking attack method is proposed to deceive state-of-the-art SiameseRPN-based trackers. Our method has good transferability and is able to deceive other top-performance trackers such as DaSiamRPN, DaSiamRPN-UpdateNet, and DiMP.
  arXiv  Detail & Related papers  (2020-03-21T07:13:40Z)
• Siamese Box Adaptive Network for Visual Tracking [100.46025199664642]
  We propose a simple yet effective visual tracking framework (named Siamese Box Adaptive Network, SiamBAN) SiamBAN directly classifies objects and regresses their bounding boxes in a unified convolutional network (FCN) SiamBAN achieves state-of-the-art performance and runs at 40 FPS, confirming its effectiveness and efficiency.
  arXiv  Detail & Related papers  (2020-03-15T05:58:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.