Zone Evaluation: Revealing Spatial Bias in Object Detection

• URL: http://arxiv.org/abs/2310.13215v2
• Date: Sat, 1 Jun 2024 04:49:43 GMT
• Title: Zone Evaluation: Revealing Spatial Bias in Object Detection
• Authors: Zhaohui Zheng, Yuming Chen, Qibin Hou, Xiang Li, Ping Wang, Ming-Ming Cheng,
• Abstract summary: A fundamental limitation of object detectors is that they suffer from "spatial bias" We present a new zone evaluation protocol, which measures the detection performance over zones. For the first time, we provide numerical results, showing that the object detectors perform quite unevenly across the zones.
• Score: 69.59295428233844
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A fundamental limitation of object detectors is that they suffer from "spatial bias", and in particular perform less satisfactorily when detecting objects near image borders. For a long time, there has been a lack of effective ways to measure and identify spatial bias, and little is known about where it comes from and what degree it is. To this end, we present a new zone evaluation protocol, extending from the traditional evaluation to a more generalized one, which measures the detection performance over zones, yielding a series of Zone Precisions (ZPs). For the first time, we provide numerical results, showing that the object detectors perform quite unevenly across the zones. Surprisingly, the detector's performance in the 96% border zone of the image does not reach the AP value (Average Precision, commonly regarded as the average detection performance in the entire image zone). To better understand spatial bias, a series of heuristic experiments are conducted. Our investigation excludes two intuitive conjectures about spatial bias that the object scale and the absolute positions of objects barely influence the spatial bias. We find that the key lies in the human-imperceptible divergence in data patterns between objects in different zones, thus eventually forming a visible performance gap between the zones. With these findings, we finally discuss a future direction for object detection, namely, spatial disequilibrium problem, aiming at pursuing a balanced detection ability over the entire image zone. By broadly evaluating 10 popular object detectors and 5 detection datasets, we shed light on the spatial bias of object detectors. We hope this work could raise a focus on detection robustness. The source codes, evaluation protocols, and tutorials are publicly available at https://github.com/Zzh-tju/ZoneEval.

Related papers

• Towards Spatial Equilibrium Object Detection [88.9747319572368]
  In this paper, we study the spatial disequilibrium problem of modern object detectors. We propose to quantify this problem by measuring the detection performance over zones. This motivates us to design a more generalized measurement, termed Spatial equilibrium Precision.
  arXiv  Detail & Related papers  (2023-01-14T17:33:26Z)
• ImpDet: Exploring Implicit Fields for 3D Object Detection [74.63774221984725]
  We introduce a new perspective that views bounding box regression as an implicit function. This leads to our proposed framework, termed Implicit Detection or ImpDet. Our ImpDet assigns specific values to points in different local 3D spaces, thereby high-quality boundaries can be generated.
  arXiv  Detail & Related papers  (2022-03-31T17:52:12Z)
• Focus-and-Detect: A Small Object Detection Framework for Aerial Images [1.911678487931003]
  We propose a two-stage object detection framework called "Focus-and-Detect" The first stage generates clusters of objects constituting the focused regions. The second stage, which is also an object detector network, predicts objects within the focal regions. Results indicate that the proposed two-stage framework achieves an AP score of 42.06 on VisDrone validation dataset.
  arXiv  Detail & Related papers  (2022-03-24T10:43:56Z)
• Fast Rule-Based Clutter Detection in Automotive Radar Data [10.379073531824456]
  Automotive radar sensors output a lot of unwanted clutter or ghost detections. clutter detections occur in groups or at similar locations in multiple consecutive measurements. New algorithm for identifying such erroneous detections is presented.
  arXiv  Detail & Related papers  (2021-08-27T11:32:50Z)
• Slender Object Detection: Diagnoses and Improvements [74.40792217534]
  In this paper, we are concerned with the detection of a particular type of objects with extreme aspect ratios, namely textbfslender objects. For a classical object detection method, a drastic drop of $18.9%$ mAP on COCO is observed, if solely evaluated on slender objects.
  arXiv  Detail & Related papers  (2020-11-17T09:39:42Z)
• Bi-Dimensional Feature Alignment for Cross-Domain Object Detection [71.85594342357815]
  We propose a novel unsupervised cross-domain detection model. It exploits the annotated data in a source domain to train an object detector for a different target domain. The proposed model mitigates the cross-domain representation divergence for object detection.
  arXiv  Detail & Related papers  (2020-11-14T03:03:11Z)
• False Detection (Positives and Negatives) in Object Detection [1.0965065178451106]
  This study explores ways of reducing false positives and negatives with labelled data. In the process also discovered insufficient labelling in Openimage 2019 Object Detection dataset.
  arXiv  Detail & Related papers  (2020-08-16T20:09:05Z)
• SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing [131.04304632759033]
  Small and cluttered objects are common in real-world which are challenging for detection. In this paper, we first innovatively introduce the idea of denoising to object detection. Instance-level denoising on the feature map is performed to enhance the detection to small and cluttered objects.
  arXiv  Detail & Related papers  (2020-04-28T06:03:54Z)

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.