Predefined Prototypes for Intra-Class Separation and Disentanglement
Prototypical Learning is based on the idea that there is a point (which we call prototype) around which the embeddings of a class are clustered. It has shown promising results in scenarios with little labeled data or to design explainable models. Typically, prototypes are either defined as the average of the embeddings of a class or are designed to be trainable. In this work, we propose to predefine prototypes following human-specified criteria, which simplify the training pipeline and brings different advantages. Specifically, in this work we explore two of these advantages: increasing the inter-class separability of embeddings and disentangling embeddings with respect to different variance factors, which can translate into the possibility of having explainable predictions. Finally, we propose different experiments that help to understand our proposal and demonstrate empirically the mentioned advantages.
Code (0)
등록된 구현이 없습니다.
Tasks
DisentanglementExplainable ModelsSimilar Papers 제목 키워드 기반
A Deep Positive-Negative Prototype Approach to Integrated Prototypical Discriminative Learning
This paper proposes a novel Deep Positive-Negative Prototype (DPNP) model that combines prototype-based learning (PbL) with discriminative methods to improve class compactness and separability in deep neural networks. Wh…
FedORGP: Guiding Heterogeneous Federated Learning with Orthogonality Regularization on Global Prototypes
Federated Learning (FL) has emerged as an essential framework for distributed machine learning, especially with its potential for privacy-preserving data processing. However, existing FL frameworks struggle to address st…
Federated LearningPrivacy PreservingA Robust Negative Learning Approach to Partial Domain Adaptation Using Source Prototypes
This work proposes a robust Partial Domain Adaptation (PDA) framework that mitigates the negative transfer problem by incorporating a robust target-supervision strategy. It leverages ensemble learning and includes divers…
Domain AdaptationEnsemble LearningPartial Domain AdaptationPseudo LabelDisentanglement Then Reconstruction: Learning Compact Features for Unsupervised Domain Adaptation
Recent works in domain adaptation always learn domain invariant features to mitigate the gap between the source and target domains by adversarial methods. The category information are not sufficiently used which causes t…
DisentanglementDomain AdaptationUnsupervised Domain AdaptationHYPO: Hyperspherical Out-of-Distribution Generalization
Out-of-distribution (OOD) generalization is critical for machine learning models deployed in the real world. However, achieving this can be fundamentally challenging, as it requires the ability to learn invariant feature…
Out-of-Distribution Generalization