The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
When Object Detection Meets Knowledge Distillation: A Survey
Abstract
Object detection (OD) is a crucial computer vision task that has seen the development of many algorithms and models over the years. While the performance of current OD models has improved, they have also become more complex, making them impractical for industry applications due to their large parameter size. To tackle this problem, knowledge distillation (KD) technology was proposed in 2015 for image classification and subsequently extended to other visual tasks due to its ability to transfer knowledge learned by complex teacher models to lightweight student models. This paper presents a comprehensive survey of KD-based OD models developed in recent years, with the aim of providing researchers with an overview of recent progress in the field. We conduct an in-depth analysis of existing works, highlighting their advantages and limitations, and explore future research directions to inspire the design of models for related tasks. We summarize the basic principles of designing KD-based OD models, describe related KD-based OD tasks, including performance improvements for lightweight models, catastrophic forgetting in incremental OD, small object detection, and weakly/semi-supervised OD. We also analyze novel distillation techniques, i.e. different types of distillation loss, feature interaction between teacher and student models, etc. Additionally, we provide an overview of the extended applications of KD-based OD models on specific datasets, such as remote sensing images and 3D point cloud datasets. We compare and analyze the performance of different models on several common datasets and discuss promising directions for solving specific OD problems.
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
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
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
FCOS: Fully Convolutional One-Stage Object Detection
Tian, Z., Shen, C., Chen, H., & He, T. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00972 · Cited by 7,013
Object Detection With Deep Learning: A Review
Zhao, Z.-Q., Zheng, P., Xu, S.-T., & Wu, X. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2876865 · Cited by 5,545
Deep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01247-4 · Cited by 2,965 · cited 1×
“In recent years, following the development of region-based convolutional neural networks (RCNN), several OD models based on deep neural networks (DNN) have been successively proposed [1], [3].”
BackgroundDeep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2018) · arXiv · doi:10.48550/arxiv.1809.02165 · Cited by 2,965
YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., et al. (2022) · arXiv · doi:10.48550/arxiv.2209.02976 · Cited by 1,792 · cited 1×
“Moreover, in YOLOv6 [148], a simple self-distillation technique using a pre-trained student model as the teacher model is introduced to minimize the data distribution difference between the predictions of the teacher and student models.”
MethodA Comprehensive Overhaul of Feature Distillation
Heo, B., Kim, J., Yun, S., Park, H., Kwak, N., & Choi, J. Y. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00201 · Cited by 706
Localization Distillation for Dense Object Detection
Zheng, Z., Ye, R., Wang, P., Ren, D., Zuo, W., Hou, Q., & Cheng, M.-M. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00919 · Cited by 220 · cited 1×
“Therefore, to achieve location information distillation, Zheng et al. [74] developed the concept of the valuable localization region (VLR), which is different from the main distillation region determined by label assignment.”
BackgroundLi, D., Tasci, S., Ghosh, S., Zhu, J., Zhang, J., & Heck, L. (2019) · Proceedings of the 4th ACM/IEEE Symposium on Edge Computing · doi:10.1145/3318216.3363317 · Cited by 94 · cited 1×
“…the improved cross-entropy loss is used to replace the hard ground truth labels; in addition, the distillation loss on the old categories and the cross-entropy loss on the new categories are jointly optimized, allowing the model to achieve a good prediction of both the old and new categories [141].”
MethodIncremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning
Dong, N., Zhang, Y., Ding, M., & Lee, G. H. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i1.25129 · Cited by 62
Self-citation
Cited by
A comprehensive review of model compression techniques in machine learning
Dantas, P. V., Sabino da Silva, W., Cordeiro, L. C., & Carvalho, C. B. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05747-w · Cited by 261
Metadata
- Authors
- Li, Z., Xu, P., Chang, X., Yang, L., Zhang, Y., Yao, L., & Chen, X.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2023-08
- Volume
- 45
- Issue
- 8
- Pages
- 10555-10579
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W4327522797
- Cited by
- 185
- References
- 11
- FWCI
- 16.82
- Type
- journal article
- Language
- en
- Open access
- closed
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.