Yuya Yoshikawa, Yutaro Shigeto, Masashi Shimbo, Akikazu Takeuchi
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.
Barlow Twins and VICReg are self-supervised representation learning models that use regularizers to decorrelate features. Although these models are as effective as conventional representation learning models, their training can be computationally demanding if the dimension 𝑑 of the projected embeddings is high. As the regularizers are defined in terms of individual elements of a cross-correlation or covariance matrix, computing the loss for 𝑛 samples takes 𝑂 (𝑛𝑑 2 ) time. In this paper, we propose a relaxed decorrelating regularizer that can be computed in 𝑂 (𝑛𝑑 log 𝑑) time by Fast Fourier Transform. We also propose an inexpensive technique to mitigate undesirable local minima that develop with the relaxation. The proposed regularizer exhibits accuracy comparable to that of existing regularizers in downstream tasks, whereas their training requires less memory and is faster for large 𝑑. The source code is available. 1 * Equal contribution.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2301.01569")
get_code_for_paper("2301.01569")
have("2301.01569")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2301.01569.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2301.01569)
Connect an agent — have() is free.