Class-Specific Semantic Reconstruction for Open Set Recognition

Huang, Hongzhi; Wang, Yu; Hu, Qinghua; Cheng, Ming–Ming

doi:10.1109/tpami.2022.3200384

Cited by 29 publications

(9 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, known classes are assumed to have higher probabilities, lower energies, and smaller reconstruction errors than unknown classes. Simultaneously, a fixed threshold tuned in the training dataset is widely employed, such as the accuracy to maintain 95% of the images in the training dataset as known ( Huang et al., 2022 ). This fixed one can be deemed at the dataset level and the class-level threshold has been recently considered in that different known classes probably behave diversely ( Wang et al., 2022a ).…”

Section: Limited Datasetmentioning

confidence: 99%

Embracing limited and imperfect training datasets: opportunities and challenges in plant disease recognition using deep learning

Xu,

Kim,

Yang

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

Recent advancements in deep learning have brought significant improvements to plant disease recognition. However, achieving satisfactory performance often requires high-quality training datasets, which are challenging and expensive to collect. Consequently, the practical application of current deep learning–based methods in real-world scenarios is hindered by the scarcity of high-quality datasets. In this paper, we argue that embracing poor datasets is viable and aims to explicitly define the challenges associated with using these datasets. To delve into this topic, we analyze the characteristics of high-quality datasets, namely, large-scale images and desired annotation, and contrast them with the limited and imperfect nature of poor datasets. Challenges arise when the training datasets deviate from these characteristics. To provide a comprehensive understanding, we propose a novel and informative taxonomy that categorizes these challenges. Furthermore, we offer a brief overview of existing studies and approaches that address these challenges. We point out that our paper sheds light on the importance of embracing poor datasets, enhances the understanding of the associated challenges, and contributes to the ambitious objective of deploying deep learning in real-world applications. To facilitate the progress, we finally describe several outstanding questions and point out potential future directions. Although our primary focus is on plant disease recognition, we emphasize that the principles of embracing and analyzing poor datasets are applicable to a wider range of domains, including agriculture. Our project is public available at https://github.com/xml94/EmbracingLimitedImperfectTrainingDatasets.

show abstract

Section: Limited Datasetmentioning

confidence: 99%

Embracing limited and imperfect training datasets: opportunities and challenges in plant disease recognition using deep learning

Xu,

Kim,

Yang

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…Specifically, methods based on prediction probability [25], [26] reject unknown samples with low probability. Methods based on reconstruction error [27], [28] assume that generative models trained on known classes cannot reconstruct unknown samples effectively. Uncertainty-based methods [29] directly model the uncertainty of samples and identify those with high uncertainty as unknown classes.…”

Section: B Open Set Recognitionmentioning

confidence: 99%

Towards open-set text recognition via label-to-prototype learning

Liu

Yang²,

Qin³

et al. 2023

Pattern Recognition

View full text Add to dashboard Cite

“…(i) As for the first group that learns known-class discriminative representations, the existing DNN-based OSR methods can be roughly divided into four types: score-based methods [21,52,53], distance-based methods [22, 31, 32, 35-38, 42, 47, 54, 55], reconstruction-based methods [24][25][26]33], and others [28-30, 34, 39-41, 50, 51].…”

Section: B Inductive Methodsmentioning

confidence: 99%

“…Huang et al [33] integrated prototype learning and reconstruction, they proposed to reconstruct class-specific semantic feature maps rather than instance-specific images for boosting the semantic discriminability of the model. They modeled an autoencoder for each known class in the latent space, which was used to reconstruct the feature maps extracted by the backbone encoder from the input images.…”

Section: B Inductive Methodsmentioning

confidence: 99%

“…-As seen from Tables I and II, most of the comparative methods both with more powerful backbones and even with simpler architectures outperform the methods with more lightweight backbones in most cases, demonstrating that a powerful backbone is helpful for boosting the model discriminability. Although a more powerful backbone generally leads to higher model complexity, which limits the architecture complexity, it can still combine with some elaborate-designed modules such as attention mechanisms in HAN-OSFGR [39], comprehensive data augmentation in Cross-Entropy+ [53], lightweight reconstruction in CSSR [33] and MoEP-AE [63], prototype constraints in PMAL [32], outlier exposure in Class-inclusion [43], feature generation in OpenGAN [64] and IT-OSR-TransP [105], etc., for further improving the model performance. -As seen from Tables I and II, if a method yields a higher ACC, it generally also achieves a higher AUROC.…”

Section: Comparisonmentioning

confidence: 99%

See 1 more Smart Citation

A study on open set recognition methods

Sun¹

View full text Add to dashboard Cite

Ling Keck-Voon. He constantly encouraged and supported me throughout my Ph.D. career. He has helped me a lot in how to do academic research, in-depth thinking, and manuscript writing. I would like to thank Professor Lin Guoshen for his patient guidance and for leading me into the wonderful world of deep learning. Also, I would like to thank Nanyang Technological University, National Research Foundation Singapore, and SMRT Corporation for funding my education and research.

show abstract

Class-Specific Semantic Reconstruction for Open Set Recognition

Cited by 29 publications

References 26 publications

Embracing limited and imperfect training datasets: opportunities and challenges in plant disease recognition using deep learning

Embracing limited and imperfect training datasets: opportunities and challenges in plant disease recognition using deep learning

Towards open-set text recognition via label-to-prototype learning

A study on open set recognition methods

Contact Info

Product

Resources

About