Unsupervised Learning of Structured Representations via Closed-Loop Transcription
This addresses the challenge of creating versatile representations for machine learning applications, though it is incremental as it builds on the existing closed-loop transcription framework.
The paper tackles the problem of learning a unified representation for both discriminative and generative tasks in an unsupervised setting, achieving classification performance close to state-of-the-art unsupervised discriminative methods and significantly higher image generation quality than state-of-the-art unsupervised generative models.
This paper proposes an unsupervised method for learning a unified representation that serves both discriminative and generative purposes. While most existing unsupervised learning approaches focus on a representation for only one of these two goals, we show that a unified representation can enjoy the mutual benefits of having both. Such a representation is attainable by generalizing the recently proposed \textit{closed-loop transcription} framework, known as CTRL, to the unsupervised setting. This entails solving a constrained maximin game over a rate reduction objective that expands features of all samples while compressing features of augmentations of each sample. Through this process, we see discriminative low-dimensional structures emerge in the resulting representations. Under comparable experimental conditions and network complexities, we demonstrate that these structured representations enable classification performance close to state-of-the-art unsupervised discriminative representations, and conditionally generated image quality significantly higher than that of state-of-the-art unsupervised generative models. Source code can be found at https://github.com/Delay-Xili/uCTRL.