Leveraging Image Augmentation for Object Manipulation: Towards Interpretable Controllability in Object-Centric Learning
This work addresses the binding problem in computer vision for researchers, offering incremental improvements in interpretable control over object representations.
The paper tackles the problem of limited interpretability and interactivity in object-centric learning by introducing SlotAug, a method that uses image augmentation to achieve interpretable controllability over object slots, with empirical and theoretical validation showing its effectiveness.
The binding problem in artificial neural networks is actively explored with the goal of achieving human-level recognition skills through the comprehension of the world in terms of symbol-like entities. Especially in the field of computer vision, object-centric learning (OCL) is extensively researched to better understand complex scenes by acquiring object representations or slots. While recent studies in OCL have made strides with complex images or videos, the interpretability and interactivity over object representation remain largely uncharted, still holding promise in the field of OCL. In this paper, we introduce a novel method, Slot Attention with Image Augmentation (SlotAug), to explore the possibility of learning interpretable controllability over slots in a self-supervised manner by utilizing an image augmentation strategy. We also devise the concept of sustainability in controllable slots by introducing iterative and reversible controls over slots with two proposed submethods: Auxiliary Identity Manipulation and Slot Consistency Loss. Extensive empirical studies and theoretical validation confirm the effectiveness of our approach, offering a novel capability for interpretable and sustainable control of object representations.