Researchers From MIT, Google, and Cornell Develop A Novel AI Framework That Distills Unsupervised Features Into High-Quality Discrete Semantic Labels

Recommendable! Impressive results. Unsupervised learning catches up with supervised learning in computer vision.

From the abstract:

"Unsupervised semantic segmentation aims to discover and localize semantically meaningful categories within image corpora without any form of annotation. To solve this task, algorithms must produce features for every pixel that are both semantically meaningful and compact enough to form distinct clusters. Unlike previous works which achieve this with a single end-to-end framework, we propose to separate feature learning from cluster compactification. Empirically, we show that current unsupervised feature learning frameworks already generate dense features whose correlations are semantically consistent. This observation motivates us to design STEGO (Self-supervised Transformer with Energy-based Graph Optimization), a novel framework that distills unsupervised features into high-quality discrete semantic labels. At the core of STEGO is a novel contrastive loss function that encourages features to form compact clusters while preserving their relationships across the corpora. STEGO yields a significant improvement over the prior state of the art ..."

Researchers From MIT and Cornell Develop STEGO (Self-Supervised Transformer With Energy-Based Graph Optimization): A Novel AI Framework That Distills Unsupervised Features Into High-Quality Discrete Semantic Labels - MarkTechPost

Unsupervised Semantic Segmentation by Distilling Feature Correspondences (open access)