Aravindh Mahendran, Thomas Kipf, Sjoerd Van Steenkiste, Ondrej Biza, Gamaleldin Elsayed, Mehdi Sajjadi
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 selfsupervised 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 Tetrominoes, CLEVR-Tex, Objects Room and MultiShapeNet, and show promising improvements on the challenging realworld Waymo Open dataset.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2302.04973")
get_code_for_paper("2302.04973")
have("2302.04973")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2302.04973.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2302.04973)
Connect an agent — have() is free.