NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
Open accessAbstract
Current state-of-the-art convolutional architectures for object detection are manually designed. Here we aim to learn a better architecture of feature pyramid network for object detection. We adopt Neural Architecture Search and discover a new feature pyramid architecture in a novel scalable search space covering all cross-scale connections. The discovered architecture, named NAS-FPN, consists of a combination of top-down and bottom-up connections to fuse features across scales. NAS-FPN, combined with various backbone models in the RetinaNet framework, achieves better accuracy and latency tradeoff compared to state-of-the-art object detection models. NAS-FPN improves mobile detection accuracy by 2 AP compared to state-of-the-art SSDLite with MobileNetV2 model in [32] and achieves 48.3 AP which surpasses Mask R-CNN [10] detection accuracy with less computation time.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
When designing a detection model, NAS can reduce the need for human intervention on the design of the network backbone and anchor boxes.
“When designing a detection model, NAS can reduce the need for human intervention on the design of the network backbone and anchor boxes [149-155].”
From Object Detection in 20 Years: A Survey (2023) · cites this paper as [151]
Section 3 (Method; page unavailable) says NAS searches the feature pyramid architecture for object detection, which supports reduced manual design for that component. It also says the backbone follows RetinaNet’s original design; the passages do not show a search of anchor boxes. The claim extends the paper’s result to components it did not report searching. (LLM, conf=0.88)
Experimental — accuracy not yet measuredUnder a similar accuracy constraint, EfficientDet uses 28x fewer FLOPs than YOLOv3, 30x fewer FLOPs than RetinaNet, and 19x fewer FLOPs than ResNet-based NAS-FPN.
“Under similar accuracy constraint, our EfficientDet uses 28x fewer FLOPs than YOLOv3 [34], 30x fewer FLOPs than RetinaNet [24], and 19x fewer FLOPs than the recent ResNet based NAS-FPN [10].”
From EfficientDet: Scalable and Efficient Object Detection (2019) · cites this paper as [10]
The Introduction identifies NAS-FPN as working with ResNet backbones, and the ‘Architectures for high detection accuracy’ section discusses its accuracy–FLOPs tradeoff. The cited paper does not compare NAS-FPN with EfficientDet or establish the claimed 19× FLOPs difference. The YOLOv3 and RetinaNet comparisons have separate citations in the citing sentence. (LLM, conf=0.83)
Experimental — accuracy not yet measuredNAS-FPN requires thousands of GPU hours during search, and the resulting feature network is irregular and thus difficult to interpret.
“Although it achieves better performance, NAS-FPN requires thousands of GPU hours during search, and the resulting feature network is irregular and thus difficult to interpret.”
From EfficientDet: Scalable and Efficient Object Detection (2019) · cites this paper as [10]
Section 4.2 reports one hour of TPU training per proxy task, a pool of 100 TPUs, and a selected architecture first sampled at about 8,000 search steps. That supports a costly search, but not the stated figure in GPU hours. The paper visualizes the discovered architecture (Figures 6–7) but does not say it is irregular or difficult to interpret; its reported detection gains support the opening performance comparison. (LLM, conf=0.86)
Experimental — accuracy not yet measuredNAS-FPN uses Neural Architecture Search to generate an uninterpretable FPN structure with more excellent performance.
“NAS-FPN [10] uses Neural Architecture Search (NAS) technology to generate an uninterpretable FPN structure with more excellent performance.”
From MME-YOLO: Multi-Sensor Multi-Level Enhanced YOLO for Robust Vehicle Detection in Traffic Surveillance (2020) · cites this paper as [10]
The Method section says NAS-FPN uses neural architecture search to discover an FPN architecture, and the Conclusion reports improved detection performance. The copy does not describe the resulting structure as uninterpretable; Section 4.2 instead discusses recognizable cross-scale connections in the discovered architectures. Page numbers were not provided. (LLM, conf=0.87)
Experimental — accuracy not yet measuredOn high-accuracy regime, EfficientDet consistently outperforms recent object detectors [10, 45] with much fewer parameters and FLOPs.
“On high-accuracy regime, our EfficientDet also consistently outperforms recent object detectors [10, 45] with much fewer parameters and FLOPs.”
From EfficientDet: Scalable and Efficient Object Detection (2019) · cites this paper as [10]
Previous scaling methods are usually ineffective because they only focus on a single or limited scaling dimension.
“These methods are usually ineffective since they only focus on a single or limited scaling dimensions.”
From EfficientDet: Scalable and Efficient Object Detection (2019) · cites this paper as [10]
Section 4.3 describes scaling NAS-FPN by changing the backbone, the number of repeated pyramid networks, and feature dimensions. The Introduction and Section 2.1 discuss limitations of earlier feature-pyramid designs, but no passage says previous scaling methods are usually ineffective because they focus on only one or a few scaling dimensions. The cited claim could not be verified in our copy. (LLM, conf=0.74)
Experimental — accuracy not yet measuredRepeated FPN+PANet achieves slightly better accuracy than NASFPN but requires more parameters and FLOPs.
“While repeated FPN+PANet achieves slightly better accuracy than NASFPN [10], it also requires more parameters and FLOPs.”
From EfficientDet: Scalable and Efficient Object Detection (2019) · cites this paper as [10]
The Introduction (page unavailable) says PANet adds a bottom-up pathway to FPN, but gives no comparison between repeated FPN+PANet and NAS-FPN. The high-accuracy architecture section compares NAS-FPN with FPN baselines, not repeated FPN+PANet; searches for PANet and the claimed accuracy, parameter, and FLOP comparison found no passage establishing it. (LLM, conf=0.74)
Experimental — accuracy not yet measuredRL-based or EA-based NAS frameworks explore a large discrete search space, requiring huge computational resources and thousands of GPU days.
“The RL-based or EA-based NAS frameworks explore the optimal architecture in a large, discrete search space, so they demand huge amount of computational resource and take thousands of GPU days [166] to search for a neural architecture.”
From Bringing ai to edge: from deep learning’s perspective (2022) · cites this paper as [166]
For 100,000 network architectures generated using DARTS and measured on Nvidia Jetson Xavier, models with the same latency can differ in FLOPs by up to 26% (461 to 623 FLOPs at 120 ms latency).
“Fig. 11 shows the latency of 100000 network architectures generated using DARTS [166] which are measured on Nvidia Jetson Xavier [203], where we can see that the models with the same latency may differ in the number of FLOPs by up to 26% (from 461 FLOPs to 623 FLOPs with latency 120ms)”
From Bringing ai to edge: from deep learning’s perspective (2022) · cites this paper as [166]
For the same set of architectures, models with the same FLOPs can have latency ranging from below 80 ms to 120 ms.
“the models with the same FLOPs perform different latency ranging from below 80ms up to 120ms.”
From Bringing ai to edge: from deep learning’s perspective (2022) · cites this paper as [166]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
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 · see citing works
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 · see citing works
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 · see citing works
Self-citationFocal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581 · see citing works
Self-citationProximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625 · see citing works
Stacked Hourglass Networks for Human Pose Estimation
Newell, A., Yang, K., & Deng, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46484-8_29 · Cited by 5,634 · see citing works
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196 · see citing works
MnasNet: Platform-Aware Neural Architecture Search for Mobile
Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., & Le, Q. V. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00293 · Cited by 3,416 · see citing works
Self-citationFocal 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 · see citing works
Self-citationLaplacian Pyramid Reconstruction and Refinement for Semantic Segmentation
Ghiasi, G., & Fowlkes, C. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46487-9_32 · Cited by 502 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 34
- B. Baker, O. Gupta, N. Naik, and R. Raskar. Designing neu- ral network architectures using reinforcement learning. In ICLR, 2016. 2
- T. Bolukbasi, J. Wang, O. Dekel, and V. Saligrama. Adaptive neural networks for efficient inference. In ICML, 2017. 2
- L.-C. Chen, M. D. Collins, Y. Zhu, G. Papandreou, B. Zoph, F. Schroff, H. Adam, and J. Shlens. Searching for effi- cient multi-scale architectures for dense image prediction. In NIPS, 2018. 2
- R. J. L.-S. D. Ooro-Rubio, M. Niepert. Learning short-cut connections for object counting. BMVC, 2018. 2
- T. Elsken, J. H. Metzen, and F. Hutter. Neural architecture search: A survey. arXiv preprint arXiv:1808.05377, 2018. 2 · arXiv
- C. Fu, W. Liu, A. Ranga, A. Tyagi, and A. C. Berg. DSSD : Deconvolutional single shot detector. CoRR, abs/1701.06659, 2017. · arXiv
- G. Ghiasi, T. Lin, and Q. V. Le. DropBlock: A regularization method for convolutional networks. NIPS, 2018. 4, 6, 8
- K. He, G. Gkioxari, P. Dollár, and R. Girshick. Mask R- CNN. In ICCV, 2017. 1, 2, 8
- G. Huang, D. Chen, T. Li, F. Wu, L. van der Maaten, and K. Weinberger. Multi-scale dense networks for resource ef- ficient image classification. In ICLR, 2018. 4
- G. Huang, D. Chen, T. Li, F. Wu, L. van der Maaten, and K. Q. Weinberger. Multi-scale dense networks for resource efficient image classification. In ICLR, 2017. 2
- G. Huang, Z. Liu, and K. Q. Weinberger. Densely connected convolutional networks. In CVPR, 2017. 1
- T. Kong, F. Sun, W. Huang, and H. Liu. Deep feature pyra- mid reconfiguration for object detection. In ECCV, 2018. 2
- T. Kong, F. Sun, A. Yao, H. Liu, M. Lu, and Y. Chen. RON: reverse connection with objectness prior networks for object detection. In CVPR, 2017. 2
- H. Law and J. Deng. Cornernet: Detecting objects as paired keypoints. In ECCV, 2018. 8
- C.-Y. Lee, S. Xie, P. Gallagher, Z. Zhang, and Z. Tu. Deeply- supervised nets. In AISTATS, 2015. 4
- H. Li, P. Xiong, J. An, and L. Wang. Pyramid attention net- work for semantic segmentation. BMVC, 2018. 4
- Z. Li, C. Peng, G. Yu, X. Zhang, Y. Deng, and J. Sun. Detnet: A backbone network for object detection. In ECCV, 2018. 1
- C. Liu, B. Zoph, J. Shlens, W. Hua, L.-J. Li, L. Fei-Fei, A. Yuille, J. Huang, and K. Murphy. Progressive neural ar- chitecture search. In ECCV, 2017. 2
- S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia. Path aggregation network for instance segmentation. In CVPR, 2018. 1, 2
- W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg. SSD: single shot multibox detector. In ECCV, 2016. 1
- N. D. B. B. Md Amirul Islam, Mrigank Rochan and Y. Wang. Gated feedback refinement network for dense image label- ing. CVPR, 2017. 2
- E. Real, A. Aggarwal, Y. Huang, and Q. V. Le. Regularized evolution for image classifier architecture search. In AAAI, 2018. 2, 5
- J. Redmon and A. Farhadi. Yolov3: An incremental improve- ment. arXiv preprint arXiv:1804.02767, 2018. 8 · arXiv
- M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.- C. Chen. MobileNetV2: inverted residuals and linear bottl. CVPR, 2019. 1, 2, 7, 8
- J.-Y. S. M.-C. K. S.-J. K. Seung-Wook Kim, Hyong- Keun Kook. Parallel feature pyramid network for object de- tection. ECCV, 2018. 2
- S. Teerapittayanon, B. McDanel, and H. Kung. Branchynet: Fast inference via early exiting from deep neural networks. In ICPR, pages 2464-2469. IEEE, 2016. 2
- S. Woo, S. Hwang, and I. S. Kweon. StairNet: top-down semantic aggregation for accurate one shot detection. In WACV, 2018. 2
- D. K. Yonghyun Kim, Bong-Nam Kang. San: Learning re- lationship between convolutional features for multi-scale ob- ject detection. ECCV, 2018. 2
- F. Yu, D. Wang, E. Shelhamer, and T. Darrell. Deep layer aggregation. In CVPR, 2018. 2
- S. Zhang, L. Wen, X. Bian, Z. Lei, and S. Z. Li. Single-shot refinement neural network for object detection. In CVPR, 2018. 2, 8
- Q. Zhao, T. Sheng, Y. Wang, Z. Tang, Y. Chen, L. Cai, and H. Ling. M2det: A single-shot object detector based on multi-level feature pyramid network. AAAI, 2019. 2
- P. Zhou, B. Ni, C. Geng, J. Hu, and Y. Xu. Scale- transferrable object detection. In CVPR, 2018. 2
- B. Zoph and Q. V. Le. Neural architecture search with rein- forcement learning. In ICLR, 2017. 2, 3, 4, 5
- B. Zoph, V. Vasudevan, J. Shlens, and Q. V. Le. Learning transferable architectures for scalable image recognition. In CVPR, 2018. 2, 3, 4
Cited by
Sorted by citations
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 · see citing works
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 · see citing works
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 · see citing works
A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects
Li, Z., Liu, F., Yang, W., Peng, S., & Zhou, J. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3084827 · Cited by 5,273 · see citing works
“[189] proposed NAS-FPN by applying NAS to feature pyramid structure search of object detection.”
BackgroundMethodObject Detection in 20 Years: A Survey
Zou, Z., Chen, K., Shi, Z., Guo, Y., & Ye, J. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3238524 · Cited by 3,689 · see citing works
“When designing a detection model, NAS can reduce the need for human intervention in the design of the network backbone and anchor boxes [149], [150], [151], [152], [153], [154], [155].”
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 · see citing works
Deformable DETR: Deformable Transformers for End-to-End Object Detection
Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020) · arXiv · doi:10.48550/arxiv.2010.04159 · Cited by 1,837 · see citing works
“Recently, NAS-FPN (Ghiasi et al., 2019) and Auto-FPN (Xu et al., 2019) are proposed to automatically design cross-scale connections via neural architecture search.”
MethodYOLOv6: 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 · see citing works
“In practice, the feature integration at multiple scales has been proved to be a critical and effective part of object detection [9, 21, 24, 40].”
BackgroundRecent advances in deep learning for object detection
Wu, X., Sahoo, D., & Hoi, S. C. H. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.01.085 · Cited by 1,047 · see citing works
A survey and performance evaluation of deep learning methods for small object detection
Liu, Y., Sun, P., Wergeles, N., & Shang, Y. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.114602 · Cited by 665 · see citing works
A review of object detection based on deep learning
Xiao, Y., Tian, Z., Yu, J., Zhang, Y., Liu, S., Du, S., & Lan, X. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-08976-6 · Cited by 584 · see citing works
EfficientDet: Scalable and Efficient Object Detection
Tan, M., Pang, R., & Le, Q. V. (2019) · arXiv · Cited by 9,841 · see citing works
“Recently, NAS-FPN [5] employs neural architecture search to search for better cross-scale feature network topology, but it requires thousands of GPU hours during search and the found network is irregular and difficult to interpret or modify, as shown in Figure 2(c).”
BackgroundMethodInfluentialSelf-citationGShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
Lepikhin, D., Lee, H., Xu, Y., Chen, D., Firat, O., Huang, Y., Krikun, M., Shazeer, N., & Chen, Z. (2020) · arXiv · doi:10.48550/arxiv.2006.16668 · Cited by 412 · see citing works
A review on modern defect detection models using DCNNs – Deep convolutional neural networks
Tulbure, A.-A., Tulbure, A.-A., & Dulf, E.-H. (2022) · Journal of Advanced Research · doi:10.1016/j.jare.2021.03.015 · Cited by 372 · see citing works
CBNet: A Novel Composite Backbone Network Architecture for Object Detection
Liu, Y., Wang, Y., Wang, S., Liang, T., Zhao, Q., Tang, Z., & Ling, H. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6834 · Cited by 280 · see citing works
LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search
Yan, B., Peng, H., Wu, K., Wang, D., Fu, J., & Lu, H. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01493 · Cited by 277 · see citing works
NAS-FCOS: Fast Neural Architecture Search for Object Detection
Wang, N., Gao, Y., Chen, H., Wang, P., Tian, Z., Shen, C., & Zhang, Y. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01196 · Cited by 258 · see citing works
Auto-FPN: Automatic Network Architecture Adaptation for Object Detection Beyond Classification
Xu, A., Yao, A., Li, A., Liang, A., & Zhang, A. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00675 · Cited by 228 · see citing works
End-to-End Object Detection with Fully Convolutional Network
Wang, J., Song, L., Li, Z., Sun, H., Sun, J., & Zheng, N. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01559 · Cited by 235 · see citing works
“Albeit they allow end-toend learning in principle, they are only demonstrated effectiveness on some small datasets and not against the modern baselines [46, 8].”
BackgroundDetNAS: Backbone Search for Object Detection
Chen, Y., Yang, T., Zhang, X., Meng, G., Xiao, X., & Sun, J. (2019) · arXiv · doi:10.48550/arxiv.1903.10979 · Cited by 205 · see citing works
Bringing ai to edge: from deep learning’s perspective
Liu, D., Kong, H., Luo, X., Liu, W., & Subramaniam, R. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.04.141 · Cited by 171 · see citing works
“The successful application of NAS on image classification inspires researchers to explore the potential application of NAS on other CV tasks, like NAS-FPN [157] and NAS-FCOS [159] for object detection and AdversarialNAS [161] for GAN.”
MethodPAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text
Wang, W., Xie, E., Li, X., Liu, X., Liang, D., Zhibo, Y., Lu, T., & Shen, C. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3077555 · Cited by 140 · see citing works
PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices
Yu, G., Chang, Q., Lv, W., Xu, C., Cui, C., Ji, W., Dang, Q., Deng, K., Wang, G., Du, Y., et al. (2021) · arXiv · doi:10.48550/arxiv.2111.00902 · Cited by 112 · see citing works
“NAS-FPN[33] searches for feature pyramid networks (FPN).”
Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection
Guo, J., Han, K., Wang, Y., Zhang, C., Yang, Z., Wu, H., Chen, X., & Xu, C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01142 · Cited by 110 · see citing works
A vehicle detection method based on disparity segmentation
Li, S., Chen, J., Peng, W., Shi, X., & Bu, W. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14360-x · Cited by 102 · see citing works
SP-NAS: Serial-to-Parallel Backbone Search for Object Detection
Jiang, C., Xu, H., Zhang, W., Liang, X., & Li, Z. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01188 · Cited by 67 · see citing works
Zhu, J., Li, X., Jin, P., Xu, Q., Sun, Z., & Song, X. (2020) · Sensors · doi:10.3390/s21010027 · Cited by 51 · see citing works
“NAS-FPN [10] uses Neural Architecture Search (NAS) technology to generate an uninterpretable FPN structure with more excellent performance.”
MethodShamsolmoali, P., Chanussot, J., Zareapoor, M., Zhou, H., & Yang, J. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3106442 · Cited by 44 · see citing works
A deep learning-based interactive medical image segmentation framework with sequential memory
Mikhailov, I., Chauveau, B., Bourdel, N., & Bartoli, A. (2024) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2024.108038 · Cited by 15 · see citing works
- Authors
- Ghiasi, G., Lin, T.-Y., & Le, Q. V.
- Affiliations
- Google (United States) (US)
- Venue
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 7029-7038
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2936599103
- Cited by
- 2,099
- References
- 10
- Citations by year
- 2026: 173 · 2025: 340 · 2024: 358 · 2023: 342 · 2022: 318 · 2021: 347 · 2020: 190 · 2019: 31
- FWCI
- 72.21
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- neural architecture search, feature pyramid network, object detection, cross-scale feature fusion, RetinaNet, accuracy-latency trade-off
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
