No Representation without Transformation
We extend the framework of variational autoencoders to represent transformations explicitly in the latent space. In the family of hierarchical graphical models that emerges, the latent space is populated by higher order objects that are inferred jointly with the latent representations they act on. To explicitly demonstrate the effect of these higher order objects, we show that the inferred latent transformations reflect interpretable properties in the observation space. Furthermore, the model is structured in such a way that in the absence of transformations, we can run inference and obtain generative capabilities comparable with standard variational autoencoders. Finally, utilizing the trained encoder, we outperform the baselines by a wide margin on a challenging out-of-distribution classification task.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Self-supervised Transformation Learning for Equivariant Representations
Unsupervised representation learning has significantly advanced various machine learning tasks. In the computer vision domain, state-of-the-art approaches utilize transformations like random crop and color jitter to achi…
Representation LearningSelf-Supervised Multi-View Learning via Auto-Encoding 3D Transformations
3D object representation learning is a fundamental challenge in computer vision to infer about the 3D world. Recent advances in deep learning have shown their efficiency in 3D object recognition, among which view-based m…
3D Object Classification3D Object RecognitionMULTI-VIEW LEARNINGObject+4Self-Supervised Contrastive Learning for Singing Voices
This study introduces self-supervised contrastive learning to acquire feature representations of singing voices. To acquire robust representations in an unsupervised manner, regular self-supervised contrastive learning t…
Contrastive LearningSinger IdentificationVocal technique classificationVideo Representation Learning by Recognizing Temporal Transformations
We introduce a novel self-supervised learning approach to learn representations of videos that are responsive to changes in the motion dynamics. Our representations can be learned from data without human annotation and p…
Action RecognitionRepresentation LearningSelf-Supervised LearningLearned Equivariant Rendering without Transformation Supervision
We propose a self-supervised framework to learn scene representations from video that are automatically delineated into objects and background. Our method relies on moving objects being equivariant with respect to their …