Data Transformation Insights in Self-supervision with Clustering Tasks
arXiv:2002.07384
Abstract
Self-supervision is key to extending use of deep learning for label scarce domains. For most of self-supervised approaches data transformations play an important role. However, up until now the impact of transformations have not been studied. Furthermore, different transformations may have different impact on the system. We provide novel insights into the use of data transformation in self-supervised tasks, specially pertaining to clustering. We show theoretically and empirically that certain set of transformations are helpful in convergence of self-supervised clustering. We also show the cases when the transformations are not helpful or in some cases even harmful. We show faster convergence rate with valid transformations for convex as well as certain family of non-convex objectives along with the proof of convergence to the original set of optima. We have synthetic as well as real world data experiments. Empirically our results conform with the theoretical insights provided.
References in corpus (9)
- Contrastive Multiview Coding
- Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank
- On Graduated Optimization for Stochastic Non-Convex Problems
- Less is More: Surgical Phase Recognition with Less Annotations through Self-Supervised Pre-training of CNN-LSTM Networks
- Self-supervised Learning of Dense Shape Correspondence
- On the Importance of Visual Context for Data Augmentation in Scene Understanding
- Two Stream Self-Supervised Learning for Action Recognition
- Semi-supervised Learning: Fusion of Self-supervised, Supervised Learning, and Multimodal Cues for Tactical Driver Behavior Detection
- Towards a Hypothesis on Visual Transformation based Self-Supervision