臺灣博碩士論文加值系統

　　電腦視覺技術發展至今已能處理諸多領域的應用問題，從自動駕駛、醫療影像判讀到交通流量計算。近年來以深度學習方法為熱門研究對象，在諸多應用問題如影像分類、物件偵測、語義分割等方面都較傳統方法表現優異，而深度學習方法的物件偵測方法多以兩階段偵測器R-CNN架構延伸，得益於人工先驗方法如錨框設計、後處理方法、標記指定，但也受限於參數調整和密集預測的處理。
本文欲討論深度學習物件偵測的後處理方法對預測表現的影響，以貪婪非極大值抑制(Greedy NMS)方法作為基準方法，與Soft NMS、Fast NMS、Cluster NMS、DIOU NMS、Confluence NMS、Weight NMS等方法相比在公開資料集 PASCAL VOC、MS COCO上的表現差異與優缺點，並從不同模型與資料集的表現、類別與幾何因素的錯誤數、參數敏感度、執行速度切入。發現不同指標的表現主要受模型與資料集影響，後處理方法間的主要差異在於偽陰性錯誤數和偽陽性錯誤數的權衡以及對分類機率門檻值、定位門檻值的敏感度，速度上的差異也受參數影響，而與演算法關係不大。

Computer vision has become a common technique in a variety of applications including autonomous vehicles, medical image recognition, and traffic flow monitoring. In recent years, deep learning is the most popular study area in this domain which is capable of solving multiple problems including image classification, object detection, semantic segmentation, etc. Studies have shown that they perform much better than the conventional methods. Most of object detection models are inspired from the architecture of two stage detector R-CNN, and make improvements with artificial prior methods e.g. anchor design, post processing methods, label assignment. However, these prior methods subject to parameter tuning and processing methods for dense predictions.
In this paper, we aim to investigate the effect of post processing methods to the performance of deep learning object detectors and discuss their differences and pros/cons from macro aspect of dataset/model combinations to micro aspect of categories and geometric factors and parameter sensitivity and speed. With Greedy NMS as the baseline method, we compare it to Soft NMS, Fast NMS, Cluster NMS, DIOU NMS, Confluence NMS, Weight NMS, with their performance on PASCAL VOC, MS COCO datasets. The results reveal that the performance of different metrics is primarily influenced by the models and datasets. The primary difference between different post-processing methods is how each method is capable of balancing false negative rate and false positive rate, as well as the sensitivity to classification probability thresholds and localization thresholds. In addition, time complexity depends only on the parameters and has little effect from the algorithms employed.

摘要 v
Abstract vii
目錄 ix
圖目錄 xi
表目錄 xv
第一章 前言 1
1.1 研究背景 1
1.2. 研究動機 6
第二章 相關文獻 7
2.1. 非極大值抑制與其變形 7
2.2. 物件偵測評估方法與指標 10
第三章 材料與方法 12
3.1.研究架構流程 12
3.2.實驗材料 13
3.2.1. 資料集介紹 13
3.2.2. 模型選擇 14
3.2.3. 後處理方法 14
3.3.評估指標 18
第四章 結果 20
4.1.資料集和模型與表現比較 20
4.1.1 表現比較 20
4.1.2 迴歸分析 22
4.2.類別和幾何因素與錯誤率比較 24
4.2.1 不同類別的錯誤比較 24
4.2.2 不同錯誤的幾何因素比較 26
4.2.3 迴歸分析 27
4.3. 參數敏感度 29
4.3.1 參數區間與表現變化比較 29
4.3.2 參數區間分組的雷文檢定 31
4.3.3 最佳參數比較 32
4.4. 處理速度 34
第五章 結論與討論 35
參考文獻 37

Ren, Shaoqing, et al. "Faster r-cnn: Towards real-time object detection with region proposal networks." Advances in neural information processing systems 28 (2015).
Redmon, Joseph, et al. "You only look once: Unified, real-time object detection." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
Tian, Zhi, et al. "Fcos: Fully convolutional one-stage object detection." Proceedings of the IEEE/CVF international conference on computer vision. 2019.
Lin, Tsung-Yi, et al. "Focal loss for dense object detection." Proceedings of the IEEE international conference on computer vision. 2017.
He, Kaiming, et al. "Deep residual learning for image recognition." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
Howard, Andrew G., et al. "Mobilenets: Efficient convolutional neural networks for mobile vision applications." arXiv preprint arXiv:1704.04861 (2017).
Lin, Tsung-Yi, et al. "Feature pyramid networks for object detection." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
He, Kaiming, et al. "Spatial pyramid pooling in deep convolutional networks for visual recognition." IEEE transactions on pattern analysis and machine intelligence 37.9 (2015): 1904-1916.
Liu, Wei, et al. "Ssd: Single shot multibox detector." European conference on computer vision. Springer, Cham, 2016.
Ge, Zheng, et al. "Yolox: Exceeding yolo series in 2021." arXiv preprint arXiv:2107.08430 (2021).
Carion, Nicolas, et al. "End-to-end object detection with transformers." European conference on computer vision. Springer, Cham, 2020.
Sun, Peize, et al. "Sparse r-cnn: End-to-end object detection with learnable proposals." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021.
Zheng, Zhaohui, et al. "Distance-IoU loss: Faster and better learning for bounding box regression." Proceedings of the AAAI conference on artificial intelligence. Vol. 34. No. 07. 2020.
Oksuz, Kemal, et al. "Rank & sort loss for object detection and instance segmentation." Proceedings of the IEEE/CVF international conference on computer vision. 2021.
N. Bodla, B. Singh, R. Chellappa and L. S. Davis, "Soft-NMS — Improving Object Detection with One Line of Code," 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 5562-5570, doi: 10.1109/ICCV.2017.593.
Shepley, Andrew & Falzon, Gregory & Kwan, Paul. (2020). Confluence: A Robust Non-IoU Alternative to Non-Maxima Suppression in Object Detection.
Hosang, Jan, Rodrigo Benenson, and Bernt Schiele. "Learning non-maximum suppression." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
Liu, Songtao, Di Huang, and Yunhong Wang. "Adaptive nms: Refining pedestrian detection in a crowd." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019.
Daniel Bolya, Chong Zhou, Fanyi Xiao, and Yong Jae Lee. YOLACT: Real-time instance segmentation. In Proc. IEEE Int. Conf. Comp. Vis., 2019.
Wang, Xinlong, et al. "Solov2: Dynamic and fast instance segmentation." Advances in Neural information processing systems 33 (2020): 17721-17732.
Zheng, Zhaohui, et al. "Enhancing geometric factors in model learning and inference for object detection and instance segmentation." IEEE Transactions on Cybernetics (2021).
Jiang, Borui, et al. "Acquisition of localization confidence for accurate object detection." Proceedings of the European conference on computer vision (ECCV). 2018.
He, Yihui, et al. "Bounding box regression with uncertainty for accurate object detection." Proceedings of the ieee/cvf conference on computer vision and pattern recognition. 2019.
H. Zhou, Z. Li, C. Ning and J. Tang, "CAD: Scale Invariant Framework for Real-Time Object Detection," 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), 2017, pp. 760-768, doi: 10.1109/ICCVW.2017.95.
Solovyev, Roman, Weimin Wang, and Tatiana Gabruseva. "Weighted boxes fusion: Ensembling boxes from different object detection models." Image and Vision Computing 107 (2021): 104117.
Zhou, Xingyi, Dequan Wang, and Philipp Krähenbühl. "Objects as points." arXiv preprint arXiv:1904.07850 (2019).
Sung, Flood, et al. "Learning to compare: Relation network for few-shot learning." Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.
Sun, Peize, et al. "What makes for end-to-end object detection?." International Conference on Machine Learning. PMLR, 2021.
Everingham, Mark, et al. "The pascal visual object classes (voc) challenge." International journal of computer vision 88.2 (2010): 303-338.
Lin, Tsung-Yi, et al. "Microsoft coco: Common objects in context." European conference on computer vision. Springer, Cham, 2014.
Shao, Shuai, et al. "Crowdhuman: A benchmark for detecting human in a crowd." arXiv preprint arXiv:1805.00123 (2018).
Griffin, Gregory, Alex Holub, and Pietro Perona. "Caltech-256 object category dataset." (2007).
Oksuz, Kemal, et al. "Localization recall precision (LRP): A new performance metric for object detection." Proceedings of the European Conference on Computer Vision (ECCV). 2018.
Hall, David, et al. "Probabilistic object detection: Definition and evaluation." Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2020.
Harakeh, Ali, and Steven L. Waslander. "Estimating and evaluating regression predictive uncertainty in deep object detectors." arXiv preprint arXiv:2101.05036 (2021).