paper-with-me

홈 › Papers

Revealing the Two Sides of Data Augmentation: An Asymmetric Distillation-based Win-Win Solution for Open-Set Recognition

2024-04-28 · Yunbing Jia, Xiaoyu Kong, Fan Tang, Yixing Gao, WeiMing Dong, Yi Yang

In this paper, we reveal the two sides of data augmentation: enhancements in closed-set recognition correlate with a significant decrease in open-set recognition. Through empirical investigation, we find that multi-sample-based augmentations would contribute to reducing feature discrimination, thereby diminishing the open-set criteria. Although knowledge distillation could impair the feature via imitation, the mixed feature with ambiguous semantics hinders the distillation. To this end, we propose an asymmetric distillation framework by feeding teacher model extra raw data to enlarge the benefit of teacher. Moreover, a joint mutual information loss and a selective relabel strategy are utilized to alleviate the influence of hard mixed samples. Our method successfully mitigates the decline in open-set and outperforms SOTAs by 2%~3% AUROC on the Tiny-ImageNet dataset and experiments on large-scale dataset ImageNet-21K demonstrate the generalization of our method.

📄 PDF Abstract BibTeX arXiv:2404.19527

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationKnowledge DistillationOpen Set Learning

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Learning from All Sides: Diversified Positive Augmentation via Self-distillation in Recommendation

2023-08-15 · Chong Liu, Xiaoyang Liu, Ruobing Xie, Lixin Zhang 외

Personalized recommendation relies on user historical behaviors to provide user-interested items, and thus seriously struggles with the data sparsity issue. A powerful positive item augmentation is beneficial to address …

AllDiversityRecommendation SystemsRetrieval

Understanding the Effect of Data Augmentation on Knowledge Distillation

2023-05-21 · Ziqi Wang, Chi Han, Wenxuan Bao, Heng Ji

Knowledge distillation (KD) requires sufficient data to transfer knowledge from large-scale teacher models to small-scale student models. Therefore, data augmentation has been widely used to mitigate the shortage of data…

Data AugmentationKnowledge Distillation

Single Trajectory Distillation for Accelerating Image and Video Style Transfer

2024-12-25 · Sijie Xu, Runqi Wang, Wei Zhu, Dejia Song 외

Diffusion-based stylization methods typically denoise from a specific partial noise state for image-to-image and video-to-video tasks. This multi-step diffusion process is computationally expensive and hinders real-world…

Style TransferVideo Style Transfer

Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translation

2022-03-16 · ACL 2022 5 · Tsz Kin Lam, Shigehiko Schamoni, Stefan Riezler

End-to-end speech translation relies on data that pair source-language speech inputs with corresponding translations into a target language. Such data are notoriously scarce, making synthetic data augmentation by back-tr…

Data AugmentationKnowledge DistillationTranslation

Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm

2023-07-25 · Hexuan Deng, Xin Zhang, Meishan Zhang, Xuebo Liu 외

In this paper, we conduct a holistic exploration of the Universal Decompositional Semantic (UDS) Parsing. We first introduce a cascade model for UDS parsing that decomposes the complex parsing task into semantically appr…

AttributeData AugmentationSemantic Parsing