The DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.
LDConv: Linear deformable convolution for improving convolutional neural networks
Open accessAbstract
Neural networks based on convolutional operations have achieved remarkable results in the field of deep learning , but there are two inherent flaws in standard convolutional operations. On the one hand, the convolution operation is confined to a local window, so it cannot capture information from other locations, and its sampled shapes is fixed. On the other hand, the size of the convolutional kernel is fixed to k × k, which is a fixed square shape, and the number of parameters tends to grow squarely with size. Although Deformable Convolution (Deformable Conv) address the problem of fixed sampling of standard convolutions, the number of parameters also tends to grow in a squared manner, and Deformable Conv do not explore the effect of different initial sample shapes on network performance. In response to the above questions, the Linear Deformable Convolution (LDConv) is explored in this work, which gives the convolution kernel an arbitrary number of parameters and arbitrary sampled shapes to provide richer options for the trade-off between network overhead and performance. In LDConv, a novel coordinate generation algorithm is defined to generate different initial sampled positions for convolutional kernels of arbitrary size. To adapt to changing targets, offsets are introduced to adjust the shape of the samples at each position. LDConv corrects the growth trend of the number of parameters for standard convolution and Deformable Conv to a linear growth. Compared to Deformable Conv, LDConv provides richer choices and can be equivalent to deformable convolution when the number of parameters of LDConv is set to the square of K. Differently, this paper also explores the effect of neural networks by using LDConv with the same size and different initial sampling shapes. LDConv completes the process of efficient feature extraction by irregular convolutional operations and brings more exploration options for convolutional sampled shapes. Object detection experiments on representative datasets COCO2017, VOC 7 + 12, and VisDrone-DET2021 fully demonstrate the advantages of LDConv. LDConv is a plug-and-play convolutional operation that can replace the convolutional operation to improve network performance. The code for the relevant tasks can be found at https://github.com/CV-ZhangXin/LDConv .
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
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
CBAM: Convolutional Block Attention Module
Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_1 · Cited by 25,853
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2022) · arXiv · doi:10.48550/arxiv.2207.02696 · Cited by 13,205
YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors
Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00721 · Cited by 13,198 · cited 1×
“To verify the advantages of LDConv, we conduct rich target detection experiments based on advanced YOLOv5 [41], YOLOv7 [42] and YOLOv8 [19] respectively.”
MethodDeformable Convolutional Networks
Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., & Wei, Y. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.89 · Cited by 7,513 · cited 5×
“Deformable Conv [11, 12] enhances network performance by using the offset to flexibly adjust the sampled shape of the convolution kernel, which adapts to the change of the target.”
BackgroundMethodInfluentialThe Pascal Visual Object Classes Challenge: A Retrospective
Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-014-0733-5 · Cited by 7,139
Coordinate Attention for Efficient Mobile Network Design
Hou, Q., Zhou, D., & Feng, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01350 · Cited by 6,961
International Conference on Learning Representations (ICLR 2013)
松尾, 豊. (2013) · 人工知能学会誌 = Journal of Japanese Society for Artificial Intelligence · Cited by 6,286
Detection and tracking meet drones challenge
Zhu, P., Wen, L., Du, D., Bian, X., Fan, H., Hu, Q., & Ling, H. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3119563 · Cited by 1,336 · cited 1×
“Object detection experiments on representative datasets VOC [25], COCO2017 [26], VisDrone-DET2021 [27] fully demonstrate the advantages of LDConv.”
BackgroundDetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
Qiao, S., Chen, L.-C., & Yuille, A. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01008 · Cited by 1,245 · cited 1×
“…can effectively improve network performance. and Table 5 Moreover, to highlight the advantages of the LDConv, novel convolutional methods are compared, such as SAConv [43], SPDConv [44], RFAConv [30], FasterBlock [23], GSConv-Neck [24] and related works CKConv [36], Flex-Conv [37] and DCLS [38].”
MethodCoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation
Xie, Y., Zhang, J., Shen, C., & Xia, Y. (2021) · arXiv · doi:10.48550/arxiv.2103.03024 · Cited by 654
Deep Learning for Network Traffic Monitoring and Analysis (NTMA): A Survey
Abbasi, M., Shahraki, A., & Taherkordi, A. (2021) · Computer Communications · doi:10.1016/j.comcom.2021.01.021 · Cited by 442
A biological image classification method based on improved CNN
Qin, J., Pan, W., Xiang, X., Tan, Y., & Hou, G. (2020) · Ecological Informatics · doi:10.1016/j.ecoinf.2020.101093 · Cited by 149
Improved YOLOX-X based UAV aerial photography object detection algorithm
Wang, X., He, N., Hong, C. H., Wang, Q., & Chen, M. (2023) · Image and Vision Computing · doi:10.1016/j.imavis.2023.104697 · Cited by 131
Deformable convolution and coordinate attention for fast cattle detection
Yang, W., Wu, J., Zhang, J., Gao, K., Du, R., Wu, Z. J., Firkat, E., & Li, D. (2023) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2023.108006 · Cited by 125
A lightweight dead fish detection method based on deformable convolution and YOLOV4
Zhao, S., Zhang, S., Lu, J., Wang, H., Yu, F. W., Shi, C., Li, D., & Zhao, R. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.107098 · Cited by 108
Distortion-aware CNNs for Spherical Images
Zhao, Q., Zhu, C., Dai, F., Ma, Y., Jin, G., & Zhang, Y. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/167 · Cited by 80
Context-Adaptive Neural Network-Based Prediction for Image Compression
Dumas, T., Roumy, A., & Guillemot, C. M. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2934565 · Cited by 75
Yang, E., Zhou, W., Qian, X., Lei, J., & Yu, L. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106729 · Cited by 52
Resolution Learning in Deep Convolutional Networks Using Scale-Space Theory
Pintea, S. L., Tömen, N., Goes, S. F., Loog, M., & van Gemert, J. C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3115001 · Cited by 51
Dilated convolution with learnable spacingsPreprint
Khalfaoui-Hassani, I., Pellegrini, T., & Masquelier, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.03740 · Cited by 47
CKConv: Continuous Kernel Convolution For Sequential Data
Romero, D. W., Kuzina, A., Bekkers, E. J., Tomczak, J. M., & Hoogendoorn, M. (2021) · arXiv · doi:10.48550/arxiv.2102.02611 · Cited by 39 · cited 2×
“…can effectively improve network performance. and Table 5 Moreover, to highlight the advantages of the LDConv, novel convolutional methods are compared, such as SAConv [43], SPDConv [44], RFAConv [30], FasterBlock [23], GSConv-Neck [24] and related works CKConv [36], Flex-Conv [37] and DCLS [38].”
MethodDeep image compression based on multi-scale deformable convolution
Li, D., Li, Y., Sun, H., & Yu, L. (2022) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2022.103573 · Cited by 17
Song, T., Zhang, X., Yang, D., Ye, Y., Liu, C., Zhou, J. N., & Song, Y. (2023) · Image and Vision Computing · doi:10.1016/j.imavis.2023.104855 · Cited by 11
Self-citationYOLO based deep learning on needle-type dashboard recognition for autopilot maneuvering system
Chang, C., Liou, Y.-D., Huang, Y., et al. (2022) · Measurement and Control · doi:10.1177/00202940221115199 · Cited by 5
Metadata
- Authors
- Zhang, X., Song, Y., Song, T., Yang, D., Ye, Y., Zhou, J., & Zhang, L.
- Venue
- Image and Vision Computing
- Publisher
- Elsevier BV
- Published
- 2024-09
- Volume
- 149
- Pages
- 105190
- ISSN
- 0262-8856 (ISSN-L)
- OpenAlex
- W4400859202
- Cited by
- 268
- References
- 25
- FWCI
- 37.86
- Type
- journal article
- Language
- en
- Open access
- hybrid
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.