Transformation Coding: Simple Objectives for Equivariant Representations
We present a simple non-generative approach to deep representation learning that seeks equivariant deep embedding through simple objectives. In contrast to existing equivariant networks, our transformation coding approach does not constrain the choice of the feed-forward layer or the architecture and allows for an unknown group action on the input space. We introduce several such transformation coding objectives for different Lie groups such as the Euclidean, Orthogonal and the Unitary groups. When using product groups, the representation is decomposed and disentangled. We show that the presence of additional information on different transformations improves disentanglement in transformation coding. We evaluate the representations learnt by transformation coding both qualitatively and quantitatively on downstream tasks, including reinforcement learning.
Code (0)
등록된 구현이 없습니다.
Tasks
Disentanglementreinforcement-learningReinforcement Learning (RL)Representation LearningSimilar Papers 제목 키워드 기반
Learning Generalized Transformation Equivariant Representations via Autoencoding Transformations
Transformation Equivariant Representations (TERs) aim to capture the intrinsic visual structures that equivary to various transformations by expanding the notion of {\em translation} equivariance underlying the success o…
TranslationEqR: Equivariant Representations for Data-Efficient Reinforcement Learning
We study different notions of equivariance as an inductive bias in Reinforcement Learning (RL) and propose new mechanisms for recovering representations that are equivariant to both an agent’s action, and symmetry transf…
Atari GamesInductive Biasreinforcement-learningReinforcement Learning+1AVT: Unsupervised Learning of Transformation Equivariant Representations by Autoencoding Variational Transformations
The learning of Transformation-Equivariant Representations (TERs), which is introduced by Hinton et al. \cite{hinton2011transforming}, has been considered as a principle to reveal visual structures under various transfor…
DecoderPeCLR: Self-Supervised 3D Hand Pose Estimation from monocular RGB via Equivariant Contrastive Learning
Encouraged by the success of contrastive learning on image classification tasks, we propose a new self-supervised method for the structured regression task of 3D hand pose estimation. Contrastive learning makes use of un…
3D Hand Pose EstimationContrastive LearningHand Pose Estimationimage-classification+4Self-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+4