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.
We study image segmentation from an information-theoretic perspective, proposing a novel adversarial method that performs unsupervised segmentation by partitioning images into maximally independent sets. More specifically, we group image pixels into foreground and background, with the goal of minimizing predictability of one set from the other. An easily computed loss drives a greedy search process to maximize inpainting error over these partitions. Our method does not involve training deep networks, is computationally cheap, class-agnostic, and even applicable in isolation to a single unlabeled image. Experiments demonstrate that it achieves a new state-of-the-art in unsupervised segmentation quality, while being substantially faster and more general than competing approaches.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2012.07287")
get_code_for_paper("2012.07287")
have("2012.07287")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2012.07287.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2012.07287)
Connect an agent — have() is free.