Small Object Detection in Traffic Scenes Based on Attention Feature Fusion
Open accessThe DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Abstract
There are many small objects in traffic scenes, but due to their low resolution and limited information, their detection is still a challenge. Small object detection is very important for the understanding of traffic scene environments. To improve the detection accuracy of small objects in traffic scenes, we propose a small object detection method in traffic scenes based on attention feature fusion. First, a multi-scale channel attention block (MS-CAB) is designed, which uses local and global scales to aggregate the effective information of the feature maps. Based on this block, an attention feature fusion block (AFFB) is proposed, which can better integrate contextual information from different layers. Finally, the AFFB is used to replace the linear fusion module in the object detection network and obtain the final network structure. The experimental results show that, compared to the benchmark model YOLOv5s, this method has achieved a higher mean Average Precison (mAP) under the premise of ensuring real-time performance. It increases the mAP of all objects by 0.9 percentage points on the validation set of the traffic scene dataset BDD100K, and at the same time, increases the mAP of small objects by 3.5%.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939
Wang, X., Girshick, R., Gupta, A., & He, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00813 · Cited by 11,596
YOLOv4: Optimal Speed and Accuracy of Object Detection
Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020) · arXiv · doi:10.48550/arxiv.2004.10934 · Cited by 10,307
EfficientDet: Scalable and Efficient Object Detection
Tan, M., Pang, R., & Le, Q. V. (2019) · arXiv · Cited by 9,841 · cited 1×
“proposed EfficientDet [21], which is a weighted bi-directional feature pyramid network (BiFPN) and a composite scale expansion method to refresh the mAP of the MS COCO dataset.”
Howard, A., Sandler, M., Chen, B., Wang, W., Chen, L.-C., Tan, M., Chu, G., Vasudevan, V., Zhu, Y., Pang, R., et al. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00140 · Cited by 9,708
CBAM: Convolutional Block Attention Module
Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018) · arXiv · doi:10.48550/arxiv.1807.06521 · Cited by 6,261 · cited 1×
“The first separately predicts the features of multiple scales before fusion, and then the obtained prediction results are processed comprehensively, such as in SSD [4], multi-scale CNN [33], etc.”
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., & Ren, D. (2019) · arXiv · doi:10.48550/arxiv.1911.08287 · Cited by 5,313 · cited 1×
“The bounding box regression loss uses the complete intersection over union (CIoU) loss [49], and both the confidence loss and classification loss use the binary cross-entropy (BCE) with logits loss (BCEWithLogitsLoss).”
SGDR: Stochastic Gradient Descent with Warm Restarts
Loshchilov, I., & Hutter, F. (2016) · arXiv · doi:10.48550/arxiv.1608.03983 · Cited by 5,309
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., & Ren, D. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6999 · Cited by 5,288
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
Wang, C.-Y., Mark Liao, H.-Y., Wu, Y.-H., Chen, P.-Y., Hsieh, J.-W., & Yeh, I.-H. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00203 · Cited by 5,265
CCNet: Criss-Cross Attention for Semantic Segmentation
Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., & Liu, W. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00069 · Cited by 3,045
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10578-9_23 · Cited by 3,034
Jocher, G., Stoken, A., Borovec, J., NanoCode012, ChristopherSTAN, Changyu, L., Laughing, Hogan, A., Lorenzomammana, Tkianai, et al. (2020) · Zenodo · doi:10.5281/zenodo.3983579 · Cited by 2,738
ultralytics/yolov5: v4.0 - nn.SiLU() activations, Weights & Biases logging, PyTorch Hub integration
Jocher, G., Stoken, A., Borovec, J., NanoCode012, ChristopherSTAN, Changyu, L., Laughing, Tkianai, YxNONG, Hogan, A., et al. (2021) · Zenodo · doi:10.5281/zenodo.4418161 · Cited by 2,738
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
Yu, F., Chen, H., Wang, X., Xian, W., Chen, Y., Liu, F., Madhavan, V., & Darrell, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00271 · Cited by 2,641 · cited 2×
“In this paper, the object detection task is oriented towards traffic scenes, and thus the experimental part mainly used the BDD100K dataset [47], while the PASCAL VOC dataset [48] was used as an auxiliary validation dataset.”
GCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond
Cao, Y., Xu, J., Lin, S., Wei, F., & Hu, H. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00246 · Cited by 2,307 · cited 1×
“proposed the global context network (GCNet) [28], which uses a relatively small amount of calculations to optimize the global context modeling capabilities.”
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
Goyal, P., Dollár, P., Girshick, R., Noordhuis, P., Wesolowski, L., Kyrola, A., Tulloch, A., Jia, Y., & He, K. (2017) · arXiv · doi:10.48550/arxiv.1706.02677 · Cited by 2,294 · cited 1×
“Five indicators commonly used in the field of object detection, namely, precision, recall, mAP, frames per second (FPS), and the number of parameters, were used to quantitatively evaluate the accuracy of the model [7].”
DSSD : Deconvolutional Single Shot Detector
Fu, C.-Y., Liu, W., Ranga, A., Tyagi, A., & Berg, A. C. (2017) · arXiv · doi:10.48550/arxiv.1701.06659 · Cited by 1,624
A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
Cai, Z., Fan, Q., Feris, R. S., & Vasconcelos, N. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_22 · Cited by 1,605 · cited 1×
“In this section, we briefly introduce the benchmark model YOLOv5s, then elaborate on the principle and structure of the proposed MS-CAB, and finally present the AFFB based on MS-CAB.”
Dai, Y., Gieseke, F., Oehmcke, S., Wu, Y., & Barnard, K. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00360 · Cited by 1,274 · cited 1×
“Based on the idea of combining local and global features in the convolutional neural networks adopted in ParseNet [42] and multi-scale channel attention [43], we propose MS-CAB, with the main difference being that we use 1× 1 convolution rather than kernels of different sizes to control the channel attention scale.”
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017) · arXiv · doi:10.48550/arxiv.1708.02002 · Cited by 1,227
An Analysis of Scale Invariance in Object Detection - SNIP
Singh, B., & Davis, L. S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00377 · Cited by 913
Concurrent Spatial and Channel ‘Squeeze & Excitation’ in Fully Convolutional Networks
Roy, A. G., Navab, N., & Wachinger, C. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-00928-1_48 · Cited by 869
CCNet: Criss-Cross Attention for Semantic Segmentation
Huang, Z., Wang, X., Wei, Y., Huang, L., Shi, H., Liu, W., & Huang, T. S. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3007032 · Cited by 524
Learning Spatial Fusion for Single-Shot Object Detection
Liu, S., Huang, D., & Wang, Y. (2019) · arXiv · doi:10.48550/arxiv.1911.09516 · Cited by 517 · cited 1×
“In this section, we briefly introduce the benchmark model YOLOv5s, then elaborate on the principle and structure of the proposed MS-CAB, and finally present the AFFB based on MS-CAB.”
Light-Head R-CNN: In Defense of Two-Stage Object Detector
Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., & Sun, J. (2017) · arXiv · doi:10.48550/arxiv.1711.07264 · Cited by 292
Zhou, X., Wang, D., & Krähenbühl, P. (2019) · arXiv · doi:10.48550/arxiv.1904.07850 · Cited by 288 · cited 1×
“Its special feature is the novel criss-cross attention module, which can obtain contextual information from remote dependencies in a more effective way.”
Cited by
Small-object detection based on YOLOv5 in autonomous driving systems
Mahaur, B., & Mishra, K. K. (2023) · Pattern Recognition Letters · doi:10.1016/j.patrec.2023.03.009 · Cited by 260
Dynamic YOLO for small underwater object detection
Chen, J., & Er, M. J. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10788-1 · Cited by 110
“Several attention-based feature fusion networks have been proposed to enhance this capability (Lian et al. 2021; Qin et al. 2020).”
Enhanced YOLOv5: An Efficient Road Object Detection Method
Chen, H., Chen, Z., & Yu, H. (2023) · Sensors · doi:10.3390/s23208355 · Cited by 49
Kumar, S., Singh, S. K., Varshney, S., Singh, S., Kumar, P., Kim, B.-G., & Ra, I.-H. (2023) · Sustainability · doi:10.3390/su152416869 · Cited by 46
Metadata
- Authors
- Lian, J., Yin, Y., Li, L., Wang, Z., & Zhou, Y.
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2021-04-26
- Volume
- 21
- Issue
- 9
- Pages
- 3031
- ISSN
- 1424-8220 (ISSN-L)
- OpenAlex
- W3157144426
- Cited by
- 73
- References
- 31
- FWCI
- 4.76
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.