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.
Institute of Computer Science Osnabrück University Osnabrück, Germany · Department of Mathematics University of Wuppertal Wuppertal, Germany · Wayve London, United Kingdom