Alert button
Picture for Yuki Tanaka

Yuki Tanaka

Alert button

Evaluating generation of chaotic time series by convolutional generative adversarial networks

May 26, 2023
Yuki Tanaka, Yutaka Yamaguti

Figure 1 for Evaluating generation of chaotic time series by convolutional generative adversarial networks
Figure 2 for Evaluating generation of chaotic time series by convolutional generative adversarial networks
Figure 3 for Evaluating generation of chaotic time series by convolutional generative adversarial networks
Figure 4 for Evaluating generation of chaotic time series by convolutional generative adversarial networks

To understand the ability and limitations of convolutional neural networks to generate time series that mimic complex temporal signals, we trained a generative adversarial network consisting of deep convolutional networks to generate chaotic time series and used nonlinear time series analysis to evaluate the generated time series. A numerical measure of determinism and the Lyapunov exponent, a measure of trajectory instability, showed that the generated time series well reproduce the chaotic properties of the original time series. However, error distribution analyses showed that large errors appeared at a low but non-negligible rate. Such errors would not be expected if the distribution were assumed to be exponential.

Viaarxiv icon

Non-iterative optimization of pseudo-labeling thresholds for training object detection models from multiple datasets

Oct 19, 2022
Yuki Tanaka, Shuhei M. Yoshida, Makoto Terao

Figure 1 for Non-iterative optimization of pseudo-labeling thresholds for training object detection models from multiple datasets
Figure 2 for Non-iterative optimization of pseudo-labeling thresholds for training object detection models from multiple datasets
Figure 3 for Non-iterative optimization of pseudo-labeling thresholds for training object detection models from multiple datasets
Figure 4 for Non-iterative optimization of pseudo-labeling thresholds for training object detection models from multiple datasets

We propose a non-iterative method to optimize pseudo-labeling thresholds for learning object detection from a collection of low-cost datasets, each of which is annotated for only a subset of all the object classes. A popular approach to this problem is first to train teacher models and then to use their confident predictions as pseudo ground-truth labels when training a student model. To obtain the best result, however, thresholds for prediction confidence must be adjusted. This process typically involves iterative search and repeated training of student models and is time-consuming. Therefore, we develop a method to optimize the thresholds without iterative optimization by maximizing the $F_\beta$-score on a validation dataset, which measures the quality of pseudo labels and can be measured without training a student model. We experimentally demonstrate that our proposed method achieves an mAP comparable to that of grid search on the COCO and VOC datasets.

* 2022 IEEE International Conference on Image Processing (ICIP), 2022, pp. 1676-1680  
* ICIP2022 
Viaarxiv icon