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 present LSD-C, a novel method to identify clusters in an unlabeled dataset. Our algorithm first establishes pairwise connections in the feature space between the samples of the minibatch based on a similarity metric. Then it regroups in clusters the connected samples and enforces a linear separation between clusters. This is achieved by using the pairwise connections as targets together with a binary cross-entropy loss on the predictions that the associated pairs of samples belong to the same cluster. This way, the feature representation of the network will evolve such that similar samples in this feature space will belong to the same linearly separated cluster. Our method draws inspiration from recent semi-supervised learning practice and proposes to combine our clustering algorithm with self-supervised pretraining and strong data augmentation. We show that our approach significantly outperforms competitors on popular public image benchmarks including CIFAR 10/100, STL 10 and MNIST, as well as the document classification dataset Reuters 10K.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2006.10039")
get_code_for_paper("2006.10039")
have("2006.10039")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2006.10039.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2006.10039)
Connect an agent — have() is free.