Organizations: School of Electronic Information, Huzhou College, Huzhou, 313000, China · School of Electronic Science and Engineering, South China Normal University, Foshan, 528225, China · School of Physics and Information Engineering, Guangdong University of Education, Guangzhou, 510303, China · independent researcher, Lijiang, 674200, China
Deep learning-based object detection models are highly dependent on the quality of annotated training data. However, large-scale datasets often contain inevitable label noise, with bounding box localization errors being a prevalent and impactful form in object detection. While label noise handling techniques are well-studied for image classification, their adaptation to the more complex problem of bounding box errors remains underexplored. To address this, we propose a novel Smooth Bounding Box (SBB) strategy to mitigate the adverse effects of bounding box annotation inaccuracies. Our key insight is that annotation errors are often linked to annotator factors rather than specific image content, allowing for a statistical correction approach. Based on object size distribution within datasets, we implement the SBB strategy through two methods: 1) Global Scaling Correction (GSC), which applies a uniform scaling factor to estimate and correct a global average error; and 2) Interval Scaling Correction (ISC), which categorizes objects by size into intervals and estimates a dedicated correction factor for each, enabling more precise, fine-grained calibration. For efficient optimization of multiple parameters in ISC, we design a tailored model fine-tuning strategy. Furthermore, we introduce a Normalized Residual Fluctuation (NRF) metric to quantitatively assess the smoothing effect and training stability. Extensive experiments on multiple benchmarks demonstrate that our method consistently enhances detection accuracy across various model architectures. Both GSC and ISC achieve significant performance improvements over strong baselines, including the latest YOLOv11n, without adding inference overhead. The codes are available at https://github.com/Acui001/SBB.git.
Figures & tables
Fig. 1: Illustration of anchor box calibration during training. Uncertainty is introduced to the bounding box label through smooth expansion and contraction operations (indicated by orange boxes). For each predicted box, we calculate its IoU with the original ground truth and the two smoothed variants, then select the highest IoU value to calibrate the regression target.
Fig. 2: Schematic of the dataset error and the proposed SBB strategy. The annotated ground truth is smoothed in two ways: expansion and contraction (indicated by the orange bounding boxes), which brings the expanded bounding box closer to the ideal bounding box, effectively minimizing annotation errors.
Fig. 3: Diagram of the object size distribution in the PASCAL VOC dataset, using both coarse and fine interval divisions to represent the dataset distribution. The fine interval divisions split the object into 100 intervals, each with a relative size of 0.01 (represented by the orange bars), while the coarse interval divisions divide the object into 5 intervals, each with a relative size of 0.2 (represented by the blue bars). The horizontal axis represents the relative size β ; the orange bars correspond to the left vertical axis, while the light blue bars correspond to the right vertical axis.
Fig. 4: The relative size distribution across multiple classes in the PASCAL VOC dataset, including nine categories namely bottle, bicycle, cow, pottedplant, train, sheep, TV, cat and dog. The fine interval divisions split the object into 100 intervals, each with a relative size of 0.01 (represented by the orange bars), while the coarse interval divisions divide the object into 10 intervals, each with a relative size of 0.1 (represented by the blue bars). The horizontal axis represents the relative size β ; the orange bars correspond to the left vertical axis, while the light blue bars correspond to the right vertical axis. The object relative sizes follow an uneven distribution, with most objects concentrated within the narrow [0, 0.1] range, exhibiting a pronounced unimodal peak.
Fig. 5: Diagram of the proposed SBB strategy. The left portion shows the global error estimation pipeline for the complete dataset, while the right portion displays the size-stratified local estimation approach. The interval count (hyperparameter αo ) can be tuned based on available computing resources during deployment.
Method
mAPtest@50–95(%)
mAPtest@50(%)
YOLO11n
61.945
81.641
YOLO11n + GSC
62.496 ( 0.889% ↑ )
82.007 ( 0.448% ↑ )
YOLOv8
60.689
80.776
YOLOv8 + GSC
60.897 ( 0.343% ↑ )
81.390 ( 0.760% ↑ )
YOLOv5
58.708
79.694
YOLOv5 + GSC
58.670(-0.006% ↓ )
79.698 ( 0.005% ↑ )
TABLE I: Experimental results of GSC. We employe YOLO11n, YOLOv8 and YOLOv5 as our baseline models and conducted comprehensive retraining experiments across varying values of the smooth factor α , respectively. We compare two important performance metrics for object detection, mAP@50-95 and mAP@50-95, with the best-performing configuration highlighted in bold.
Fig. 6: Variation trends of both mAP@50-95 scores and their corresponding percentage improvements across different smooth factor values.
Fig. 7: Comparison of detection accuracy across all 20 classes in the PASCAL VOC dataset, along with the corresponding performance gains relative to the YOLO11n baseline, using a smooth factor of α=13.80 .
Fig. 8: Comprehensive statistical analysis of objects across different 10 intervals during the smooth factor optimization process. The numbers in the bottom row represent the smooth factors corresponding to the interval where the objects achieved optimal detection performance (without considering the overall detection performance). The Y-axis shows the relative improvement in mAP@50-95 achieved compared to the baseline.
Fig. 9: mAP@50-95 curves on the validation set during the model training process are shown. The black curve represents the baseline YOLO11n, while the blue curve represents the SBB method with α=1.70 (the worst smooth factor which exhibited negative effects), and the SBB method with α=13.80 (the best smooth factor which archived positive effects). The process of the blue curve surpassing the black curve is clearly visible in the green magnifying window.
Fig. 10: Variation of our method’s first-epoch bounding box loss across different α values. The dashed line indicates the baseline’s first-epoch loss.
Method
NRF
mAP@ 50-95
losstrain
lossval
Baseline(YOLO11n)
0.002869
0.051160
0.0031870
Our ( α=1.70 )
0.002503 ↓
0.006663 ↓
0.003200 ↑
Our ( α=13.80 )
0.002482 ↓
0.005945 ↓
0.002659 ↓
TABLE II: NRF values evaluated across multiple metrics, including mAP@50-95, training loss, and validation loss throughout the model training process.
Method
Smooth Factor ( α )
1
2
3
4
5
6
7
8
9
TFS
61.673
61.631
61.542
61.804
61.840
62.063
61.614
62.512
61.822
FT
61.624
61.513
61.542
61.596
61.254
61.432
61.486
61.386
61.621
RT
62.371
62.137
62.285
61.998
62.287
62.185
62.266
62.220
62.252
TABLE III: mAPval@50-95 results for the three training methods (TFS, FT, RT) with smooth factors ranging from 1 to 9 on dataset PASCAL VOC. The mAPval@50-95 for the baseline YOLO11n is 61.911.
Baseline
Interval
Smooth Factor ( α )
1
2
3
4
5
6
7
8
9
YOLO11n (61.911)
[0.0,0.1]
61.673
61.631
61.542
61.804
61.84
62.063
61.614
62.512 ↑
61.822
[0.1,0.3]
62.746
62.718
62.806
62.573
62.778
62.673
62.649
62.909 ↑
62.762
[0.3,0.5]
62.717
62.679
62.698
61.54
62.781
62.514
61.476
61.532
62.575
[0.5,0.7]
61.688
62.63
61.542
62.605
61.548
62.824
61.605
61.605
62.581
[0.7,1.0]
61.602
61.606
62.576
62.667
61.605
61.605
62.810
62.780
62.507
TABLE IV: mAPval@50-95 results obtained by retraining and fine-tuning the models (include YOLO11n, YOLOv8, YOLOv5) using different smooth factors within the range [1, 9]. The results in the gray region (i.e., the interval [0, 0.1]) were obtained using the TFS training method, while the other results were obtained using the RT method. The data in the [0.1, 0.3] interval were fine-tuned based on the optimal results already achieved in [0, 0.1], and the interval [0.3, 0.5] was fine-tuned based on the optimal results in [0.1, 0.3]. The same approach was applied to the other intervals.
Baseline
Interval
[0, 0.1]
[0.1, 0.3]
[0.3, 0.5]
[0.5, 0.7]
[0.7, 1]
YOLO11n
8
8
0
0
0
YOLOv8n
3
4
5
0
4
YOLOv5n
6
4
2
5
0
TABLE V: The optimal smooth factor value for each interval on dataset PASCAL VOC. A value of 0 presents that the objects in the corresponding interval do not use the SBB operation.
Dataset
Method
mAPtest@50–95(%)
mAPtest@50(%)
VOC
YOLO11n
61.945
81.641
YOLO11n + ISC
62.872 ( 2.415% ) ↑
82.334 ( 1.039% ) ↑
YOLOv8
60.689
80.776
YOLOv8 + ISC
61.519 ( 2.254% ) ↑
81.390 ( 0.940% ) ↑
YOLOv5
58.707
79.694
YOLOv5 + ISC
60.072 ( 3.690% ) ↑
80.899 ( 1.897% ) ↑
TABLE VI: Experimental results of ISC on the PASCAL VOC and COCO datasets. We employ YOLO11n, YOLOv8, and YOLOv5 as our baseline models and conducted comprehensive retraining experiments across various values of the smooth factor. We compare two important performance metrics for object detection, mAP@50 and mAP@50-95, with the best-performing ones highlighted in bold.
Fig. 11: The detection accuracy (mAP@50-95) on the PASCAL VOC dataset across different intervals is shown below. The dark blue, green, and light blue bars correspond to the results of the baseline, YOLOv11n+ISC (with parameters from Table V ), and the GSC method, respectively.
Annotation errors are widespread in computer vision datasets and can significantly degrade the performance of systems trained on them, particularly in complex tasks such as object detection. Several approaches exist to identify annotation errors, including training-free feature-space methods which provide a fast and interpretable way to analyze annotations. However, the behavior on object detection annotations, which include semantic and spatial information, remains largely unexplored. In this work we analyze the applicability of feature-space-based approaches for detecting annotation errors in object detection datasets. By adapting an existing feature-space method, we show that such approaches reliably expose semantic mislabel, while positional errors remain difficult to detect. We evaluate this behavior across multiple pretrained embedding models, synthetic noise types (symmetric, asymmetric, and positional), and real-world annotation errors using VOC2012 and KITTI. All code and real-world corruptions are publicly available at the following repository: https://github.com/ ChristianSieberichs/BoundingBox_corruption_detection
Christian Sieberichs, Simon Geerkens, Thomas Waschulzik +2
University of Applied Sciences Düsseldorf · Siemens Mobility GmbH · Goethe University Frankfurt
Bounding-box regression is a fundamental component of object detection, playing a critical role in precise object localization. Existing Intersection-over-Union (IoU)-based loss functions extend the IoU objective by incorporating geometric penalties, such as center-distance and aspect-ratio mismatch, to improve bounding-box regression. However, these penalties typically remain fixed throughout training and do not account for the optimization dynamics in which predicted boxes initially exhibit large center-distance and shape errors, with later stages focusing on improving overlap with the ground truth. To address this limitation, we introduce MoEIoU, a mixture-of-experts based regression loss that jointly models overlap, center alignment, and aspect-ratio mismatch. MoEIoU aggregates these components using a log-sum-exp function, which emphasizes the dominant localization error while maintaining smooth contributions from other terms. Additionally, a curriculum-based weighting schedule is employed to prioritize correcting box position and shape in early training stages and improving overlap in later stages. We evaluated proposed MoEIoU on PASCAL VOC, HRIPCB, and MS COCO using multiple YOLO architectures, along with large-scale simulation experiments. It consistently outperforms standard and recent state-of-the-art losses, demonstrating faster convergence and improved localization accuracy. We further show that this adaptive aggregation improves existing IoU-based losses, yielding consistent gains and providing more effective optimization guidance for bounding-box regression in object detection frameworks.
Vinay Edula, Priyanka Bagade
Department of Computer Science and Engineering Indian Institute of Technology Kanpur Kanpur, U.P, India
While object detection has advanced through improved architectures and open-vocabulary models, we provide strong evidence that benchmark quality is limited by annotation incompleteness. Across four widely used datasets (COCO, Pascal VOC, Cityscapes, KITTI), re-annotation reveals substantial increases in annotated objects (e.g., up to +60% on KITTI and +40% on COCO), driven primarily by previously unlabeled small, occluded, or densely packed instances. While some differences arise from dataset-specific annotation conventions, we consistently find that missing annotations are the main source of label errors across all datasets. To achieve high data quality, we introduce a scalable annotation pipeline that emphasizes high recall and captures ambiguity through soft labels aggregated from at least 11 annotators per object. The resulting annotations improve coverage and align well with human calibration. We show that benchmark performance is highly sensitive to annotation quality, although model rankings remain largely stable. We introduce two large-scale benchmarks: (i) an uncertainty-aware object detection benchmark, and (ii) a label error detection benchmark grounded in real label errors. We show that current detectors are strongly depended on annotation quality and are misaligned with human perception. Current label error detection methods, which have been shown to perform well on synthetic noise, struggle to achieve high recall and precision on real label errors. Our results highlight the need for future object detection benchmarks to move beyond deterministic annotations toward high-recall, uncertainty-aware evaluation that maximizes valid instances and better reflects real-world ambiguity.
Sarina Penquitt, Jonathan Klees, Antonia van Betteray +4
Institute of Computer Science Osnabrück University Osnabrück, Germany · Department of Mathematics University of Wuppertal Wuppertal, Germany · Wayve London, United Kingdom