Effect of Annotation Errors on Drone Detection with YOLOv3

2020-07-28
Following the recent advances in deep networks, object detection and tracking algorithms with deep learning backbones have been improved significantly; however, this rapid development resulted in the necessity of large amounts of annotated labels. Even if the details of such semi-automatic annotation processes for most of these datasets are not known precisely, especially for the video annotations, some automated labeling processes are usually employed. Unfortunately, such approaches might result with erroneous annotations. In this work, different types of annotation errors for object detection problem are simulated and the performance of a popular state-of-the-art object detector, YOLOv3, with erroneous annotations during training and testing stages is examined. Moreover, some inevitable annotation errors in Anti-UAV Challenge dataset is also examined in this manner, while proposing a solution to correct such annotation errors of this valuable data set.

Suggestions

Effect of quantization on the performance of deep networks
Kütükcü, Başar; Bozdağı Akar, Gözde.; Department of Electrical and Electronics Engineering (2020)
Deep neural networks performed greatly for many engineering problems in recent years. However, power and memory hungry nature of deep learning algorithm prevents mobile devices to benefit from the success of deep neural networks. The increasing number of mobile devices creates a push to make deep network deployment possible for resource-constrained devices. Quantization is a solution for this problem. In this thesis, different quantization techniques and their effects on deep networks are examined. The tech...
Effects of 3D Registration on Subspace Based Face Recognition Methods
USTUN, Bulent; Halıcı, Uğur; ULUSOY PARNAS, İLKAY (2008-04-22)
The effect of 3D registation is examined through various subspace based recognition algorithms. Iterative Closest Point (ICP) algorithm and its variations are used for registration and Eigenface, Fisherface, NMF (Nonnegative Matrix Factorization) and ICA (Independent Component Analysis) are used for recognition. It is observed that ICP and its variations converges to the place on the database FRGC v. 1 used. Among the recognition algorithms Fisher-face and ICA are performed better than the others.
A pixel-by-pixel learned lossless image compression method with parallel decoding
Gümüş, Sinem; Kamışlı, Fatih; Department of Electrical and Electronics Engineering (2022-7)
The success of deep learning in computer vision applications has led to the use of learning based algorithms also in image compression. Learning based lossless image compression algorithms can be divided into three categories, namely, pixel-by-pixel (or masked convolution based) algorithms, prior based algorithms and latent representation based algorithms. In the pixel-by-pixel algorithms, each pixel’s probability distribution is obtained by processing the previously coded left and upper neighbouring pixels...
Effect of some software design patterns on real time software performance
Ayata, Mesut; Bilgen, Semih; Department of Information Systems (2010)
In this thesis, effects of some software design patterns on real time software performance will be investigated. In real time systems, performance requirements are critical. Real time system developers usually use functional languages to meet the requirements. Using an object oriented language may be expected to reduce performance. However, if suitable software design patterns are applied carefully, the reduction in performance can be avoided. In this thesis, appropriate real time software performance metri...
Detection of clean samples in noisy labelled datasets via analysis of artificially corrupted samples
Yıldırım, Botan; Ulusoy, İlkay; Department of Electrical and Electronics Engineering (2022-8-22)
Recent advances in supervised deep learning methods have shown great successes in image classification but these methods are known to owe their success to massive amount of data with reliable labels. However, constructing large-scale datasets inevitably results with varying levels of label noise which degrades performance of the supervised deep learning based classifiers. In this thesis, we make an analysis of sample selection based label noise robust approaches by providing extensive experimental evaluatio...
Citation Formats
A. Köksal and A. A. Alatan, “Effect of Annotation Errors on Drone Detection with YOLOv3,” 2020, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/34835.