ObjectBox: From Centers to Boxes for Anchor-Free Object Detection

• URL: http://arxiv.org/abs/2207.06985v1
• Date: Thu, 14 Jul 2022 15:10:29 GMT
• Title: ObjectBox: From Centers to Boxes for Anchor-Free Object Detection
• Authors: Mohsen Zand, Ali Etemad, Michael Greenspan
• Abstract summary: 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.
• Score: 14.75815792682734
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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, which are more biased toward specific object scales in their label assignments, we use only object center locations as positive samples and treat all objects equally in different feature levels regardless of the objects' sizes or shapes. Specifically, our label assignment strategy considers the object center locations as shape- and size-agnostic anchors in an anchor-free fashion, and allows learning to occur at all scales for every object. To support this, we define new regression targets as the distances from two corners of the center cell location to the four sides of the bounding box. Moreover, to handle scale-variant objects, we propose a tailored IoU loss to deal with boxes with different sizes. As a result, our proposed object detector does not need any dataset-dependent hyperparameters to be tuned across datasets. We evaluate our method on MS-COCO 2017 and PASCAL VOC 2012 datasets, and compare our results to state-of-the-art methods. We observe that ObjectBox performs favorably in comparison to prior works. Furthermore, we perform rigorous ablation experiments to evaluate different components of our method. Our code is available at: https://github.com/MohsenZand/ObjectBox.

Related papers

• Object-Centric Multiple Object Tracking [124.30650395969126]
  This paper proposes a video object-centric model for multiple-object tracking pipelines. It consists of an index-merge module that adapts the object-centric slots into detection outputs and an object memory module. Benefited from object-centric learning, we only require sparse detection labels for object localization and feature binding.
  arXiv  Detail & Related papers  (2023-09-01T03:34:12Z)
• YUDO: YOLO for Uniform Directed Object Detection [0.0]
  This paper presents an efficient way of detecting directed objects by predicting their center coordinates and direction angle. Since the objects are of uniform size, the proposed model works without predicting the object's width and height.
  arXiv  Detail & Related papers  (2023-08-08T19:18:20Z)
• LocPoseNet: Robust Location Prior for Unseen Object Pose Estimation [69.70498875887611]
  LocPoseNet is able to robustly learn location prior for unseen objects. Our method outperforms existing works by a large margin on LINEMOD and GenMOP.
  arXiv  Detail & Related papers  (2022-11-29T15:21:34Z)
• One-Shot General Object Localization [43.88712478006662]
  OneLoc is a general one-shot object localization algorithm. OneLoc efficiently finds the object center and bounding box size by a special voting scheme. Experiments show that the proposed method achieves state-of-the-art overall performance on two datasets.
  arXiv  Detail & Related papers  (2022-11-24T03:14:04Z)
• 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)
• CenterNet++ for Object Detection [174.59360147041673]
  Bottom-up approaches are as competitive as the top-down and enjoy higher recall. Our approach, named CenterNet, detects each object as a triplet keypoints (top-left and bottom-right corners and the center keypoint) On the MS-COCO dataset, CenterNet with Res2Net-101 and Swin-Transformer achieves APs of 53.7% and 57.1%, respectively.
  arXiv  Detail & Related papers  (2022-04-18T16:45:53Z)
• Learning Open-World Object Proposals without Learning to Classify [110.30191531975804]
  We propose a classification-free Object Localization Network (OLN) which estimates the objectness of each region purely by how well the location and shape of a region overlaps with any ground-truth object. This simple strategy learns generalizable objectness and outperforms existing proposals on cross-category generalization.
  arXiv  Detail & Related papers  (2021-08-15T14:36:02Z)
• Active Perception for Ambiguous Objects Classification [7.837959746116199]
  In the real world, we can find ambiguous objects that do not allow exact classification and detection from a single view. We propose a framework that, given a single view of an object, provides the coordinates of a next viewpoint to discriminate the object against similar ones, if any, and eliminates ambiguities. We validate our approach with a Franka Emika Panda robot and common household objects featured with ambiguities.
  arXiv  Detail & Related papers  (2021-08-02T09:12:34Z)
• Oriented Bounding Boxes for Small and Freely Rotated Objects [7.6997148655751895]
  A novel object detection method is presented that handles freely rotated objects of arbitrary sizes. The method encodes the precise location and orientation of features of the target objects at grid cell locations. Evaluations on the xView and DOTA datasets show that the proposed method uniformly improves performance over existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-04-24T02:04:49Z)
• Objects are Different: Flexible Monocular 3D Object Detection [87.82253067302561]
  We propose a flexible framework for monocular 3D object detection which explicitly decouples the truncated objects and adaptively combines multiple approaches for object depth estimation. Experiments demonstrate that our method outperforms the state-of-the-art method by relatively 27% for the moderate level and 30% for the hard level in the test set of KITTI benchmark.
  arXiv  Detail & Related papers  (2021-04-06T07:01:28Z)
• 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)

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.