Ocean: Object-aware Anchor-free Tracking
- URL: http://arxiv.org/abs/2006.10721v2
- Date: Thu, 9 Jul 2020 17:00:21 GMT
- Title: Ocean: Object-aware Anchor-free Tracking
- Authors: Zhipeng Zhang, Houwen Peng, Jianlong Fu, Bing Li, Weiming Hu
- Abstract summary: 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.
- Score: 75.29960101993379
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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
https://github.com/researchmm/TracKit.
Related papers
- Target-Aware Tracking with Long-term Context Attention [8.20858704675519]
Long-term context attention (LCA) module can perform extensive information fusion on the target and its context from long-term frames.
LCA uses the target state from the previous frame to exclude the interference of similar objects and complex backgrounds.
Our tracker achieves state-of-the-art performance on multiple benchmarks, with 71.1% AUC, 89.3% NP, and 73.0% AO on LaSOT, TrackingNet, and GOT-10k.
arXiv Detail & Related papers (2023-02-27T14:40:58Z) - RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object
Detection [45.10513110142015]
Current anchor-based or anchor-free label assignment paradigms incur many outlier tiny-sized ground truth samples.
We propose a Gaussian Receptive Field based Label Assignment (RFLA) strategy for tiny object detection.
Our approach outperforms the state-of-the-art competitors with 4.0 AP points on the AI-TOD dataset.
arXiv Detail & Related papers (2022-08-18T09:35:56Z) - ObjectBox: From Centers to Boxes for Anchor-Free Object Detection [14.75815792682734]
We present ObjectBox, a novel single-stage anchor-free and highly generalizable object detection approach.
As opposed to both existing anchor-based and anchor-free detectors, we use only object center locations as positive samples.
We evaluate our method on MS-COCO 2017 and PASCAL VOC 2012 datasets, and compare our results to state-of-the-art methods.
arXiv Detail & Related papers (2022-07-14T15:10:29Z) - Context-aware Visual Tracking with Joint Meta-updating [11.226947525556813]
We propose a context-aware tracking model to optimize the tracker over the representation space, which jointly meta-update both branches by exploiting information along the whole sequence.
The proposed tracking method achieves an EAO score of 0.514 on VOT2018 with the speed of 40FPS, demonstrating its capability of improving the accuracy and robustness of the underlying tracker with little speed drop.
arXiv Detail & Related papers (2022-04-04T14:16:00Z) - ByteTrack: Multi-Object Tracking by Associating Every Detection Box [51.93588012109943]
Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos.
Most methods obtain identities by associating detection boxes whose scores are higher than a threshold.
We present a simple, effective and generic association method, called BYTE, tracking BY associaTing every detection box instead of only the high score ones.
arXiv Detail & Related papers (2021-10-13T17:01:26Z) - Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection [60.522877583407904]
Current anchor-free object detectors are quite simple and effective yet lack accurate label assignment methods.
We present Pseudo-Intersection-over-Union(Pseudo-IoU): a simple metric that brings more standardized and accurate assignment rule into anchor-free object detection frameworks.
Our method achieves comparable performance to other recent state-of-the-art anchor-free methods without bells and whistles.
arXiv Detail & Related papers (2021-04-29T02:48:47Z) - Learning Spatio-Temporal Transformer for Visual Tracking [108.11680070733598]
We present a new tracking architecture with an encoder-decoder transformer as the key component.
The whole method is end-to-end, does not need any postprocessing steps such as cosine window and bounding box smoothing.
The proposed tracker achieves state-of-the-art performance on five challenging short-term and long-term benchmarks, while running real-time speed, being 6x faster than Siam R-CNN.
arXiv Detail & Related papers (2021-03-31T15:19:19Z) - Learning to Track with Object Permanence [61.36492084090744]
We introduce an end-to-end trainable approach for joint object detection and tracking.
Our model, trained jointly on synthetic and real data, outperforms the state of the art on KITTI, and MOT17 datasets.
arXiv Detail & Related papers (2021-03-26T04:43:04Z) - End-to-end Deep Object Tracking with Circular Loss Function for Rotated
Bounding Box [68.8204255655161]
We introduce a novel end-to-end deep learning method based on the Transformer Multi-Head Attention architecture.
We also present a new type of loss function, which takes into account the bounding box overlap and orientation.
arXiv Detail & Related papers (2020-12-17T17:29:29Z)
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.