Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames
This work addresses the challenge of composable abstraction discovery for machine learning systems, offering incremental improvements in capturing spatial symmetries to enhance object discovery efficiency.
The paper tackles the problem of object discovery in visual data by addressing the inadequate capture of spatial symmetries in slot-based neural networks, which leads to sample inefficiency. The result is a method incorporating slot-centric reference frames that achieves large gains in data efficiency and improvements across synthetic benchmarks and a real-world dataset.
Automatically discovering composable abstractions from raw perceptual data is a long-standing challenge in machine learning. Recent slot-based neural networks that learn about objects in a self-supervised manner have made exciting progress in this direction. However, they typically fall short at adequately capturing spatial symmetries present in the visual world, which leads to sample inefficiency, such as when entangling object appearance and pose. In this paper, we present a simple yet highly effective method for incorporating spatial symmetries via slot-centric reference frames. We incorporate equivariance to per-object pose transformations into the attention and generation mechanism of Slot Attention by translating, scaling, and rotating position encodings. These changes result in little computational overhead, are easy to implement, and can result in large gains in terms of data efficiency and overall improvements to object discovery. We evaluate our method on a wide range of synthetic object discovery benchmarks namely CLEVR, Tetrominoes, CLEVRTex, Objects Room and MultiShapeNet, and show promising improvements on the challenging real-world Waymo Open dataset.