2000 character limit reached
Dendrogram distance: an evaluation metric for generative networks using hierarchical clustering (2311.16894v1)
Published 28 Nov 2023 in cs.LG and cs.CV
Abstract: We present a novel metric for generative modeling evaluation, focusing primarily on generative networks. The method uses dendrograms to represent real and fake data, allowing for the divergence between training and generated samples to be computed. This metric focus on mode collapse, targeting generators that are not able to capture all modes in the training set. To evaluate the proposed method it is introduced a validation scheme based on sampling from real datasets, therefore the metric is evaluated in a controlled environment and proves to be competitive with other state-of-the-art approaches.
- On the tradeoff between mode collapse and sample quality in generative adversarial networks. In 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP), pages 1184–1188. IEEE, 2018.
- M. Arjovsky and L. Bottou. Towards principled methods for training generative adversarial networks. Proceedings of the International Conference on Learning Representations, 2017.
- S. Barratt and R. Sharma. A note on the inception score. arXiv preprint arXiv:1801.01973, 2018.
- A. Borji. Pros and cons of gan evaluation measures. Computer Vision and Image Understanding, 179:41–65, 2019.
- G. Carlsson and F. MÊmoli. Characterization, stability and convergence of hierarchical clustering methods. Journal of machine learning research, 11(Apr):1425–1470, 2010.
- Mode regularized generative adversarial networks. arXiv preprint arXiv:1612.02136, 2016.
- Multi-scale generative adversarial network for improved evaluation of cell–cell interactions observed in organ-on-chip experiments. Neural Computing and Applications, pages 1–19, 2020.
- F. G. d. Costa. Employing nonlinear time series analysis tools with stable clustering algorithms for detecting concept drift on data streams. PhD thesis, Universidade de São Paulo, 2017.
- F. A. Faria and G. Carneiro. Why are generative adversarial networks so fascinating and annoying? In 2020 33rd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pages 1–8. IEEE, 2020.
- Generative adversarial nets. In Advances in Neural Information Processing Systems, pages 2672–2680, 2014.
- Deligan: Generative adversarial networks for diverse and limited data. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 166–174, 2017.
- Gans trained by a two time-scale update rule converge to a local nash equilibrium. arXiv preprint arXiv:1706.08500, 2017.
- Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 105–114, 2017.
- C. Luo. Understanding diffusion models: A unified perspective. arXiv preprint arXiv:2208.11970, 2022.
- Conditional image synthesis with auxiliary classifier gans. In Proceedings of the 34th International Conference on Machine Learning-Volume 70, pages 2642–2651, 2017.
- K. Parimala and S. Channappayya. Quality aware generative adversarial networks. In Advances in Neural Information Processing Systems, pages 2948–2958, 2019.
- Training deep networks from zero to hero: avoiding pitfalls and going beyond. In 2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pages 9–16. IEEE, 2021.
- Unsupervised representation learning with deep convolutional generative adversarial networks. In Proceedings of the International Conference on Learning Representations, 2016.
- Sketchformer: Transformer-based representation for sketched structure. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 14153–14162, 2020.
- Improved techniques for training gans. In Advances in neural information processing systems, pages 2234–2242, 2016.
- Scene designer: compositional sketch-based image retrieval with contrastive learning and an auxiliary synthesis task. Multimedia Tools and Applications, pages 1–23, 2022.
- How good is my gan? In Proceedings of the European Conference on Computer Vision (ECCV), pages 213–229, 2018.
- Veegan: Reducing mode collapse in gans using implicit variational learning. In Advances in Neural Information Processing Systems, pages 3308–3318, 2017.
- Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826, 2016.
- A note on the evaluation of generative models. In International Conference on Learning Representations (ICLR 2016), pages 1–10, 2016.
- High-resolution image synthesis and semantic manipulation with conditional gans. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018.
- An empirical study on evaluation metrics of generative adversarial networks. arXiv preprint arXiv:1806.07755, 2018.
- L.-C. Yang and A. Lerch. On the evaluation of generative models in music. Neural Computing and Applications, 32(9):4773–4784, 2020.
- Activation maximization generative adversarial nets. arXiv preprint arXiv:1703.02000, 2017.
- Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.