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 of Convolutional Neural Networks (CNNs). For this purpose, we present both deterministic AutoEncoding Transformations (AET) and probabilistic AutoEncoding Variational Transformations (AVT) models to learn visual representations from generic groups of transformations. While the AET is trained by directly decoding the transformations from the learned representations, the AVT is trained by maximizing the joint mutual information between the learned representation and transformations. This results in Generalized TERs (GTERs) equivariant against transformations in a more general fashion by capturing complex patterns of visual structures beyond the conventional linear equivariance under a transformation group. The presented approach can be extended to (semi-)supervised models by jointly maximizing the mutual information of the learned representation with both labels and transformations. Experiments demonstrate the proposed models outperform the state-of-the-art models in both unsupervised and (semi-)supervised tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
TranslationSimilar Papers 제목 키워드 기반
AVT: 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…
DecoderESCL: Equivariant Self-Contrastive Learning for Sentence Representations
Previous contrastive learning methods for sentence representations often focus on insensitive transformations to produce positive pairs, but neglect the role of sensitive transformations that are harmful to semantic repr…
Contrastive LearningMulti-Task LearningSemantic Textual SimilaritySentenceAETv2: AutoEncoding Transformations for Self-Supervised Representation Learning by Minimizing Geodesic Distances in Lie Groups
Self-supervised learning by predicting transformations has demonstrated outstanding performances in both unsupervised and (semi-)supervised tasks. Among the state-of-the-art methods is the AutoEncoding Transformations (A…
Representation LearningSelf-Supervised LearningFLAT: Few-Shot Learning via Autoencoding Transformation Regularizers
One of the most significant challenges facing a few-shot learning task is the generalizability of the (meta-)model from the base to the novel categories. Most of existing few-shot learning models attempt to address this …
Data AugmentationFew-Shot LearningNovel ConceptsCo-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring In Data
Equivariance is a nice property to have as it produces much more parameter efficient neural architectures and preserves the structure of the input through the feature mapping. Even though some combinations of transformat…
Object RecognitionRotated MNIST