# SAMCLR: Contrastive pre-training on complex scenes using SAM for view sampling

Source: [SAMCLR: Contrastive pre-training on complex scenes using SAM for view sampling](<https://www.sota2.com/research/paper/68fa71031e209131cea4e8d7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:55:42.510Z

Authors: Benjamin Missaoui, Chongbin Yuan

Published: 2023-10-23T09:16:04.000Z

## Abstract

In Computer Vision, self-supervised contrastive learning enforces similar representations between different views of the same image. The pre-training is most often performed on image classification datasets, like ImageNet, where images mainly contain a single class of objects. However, when dealing with complex scenes with multiple items, it becomes very unlikely for several views of the same image to represent the same object category. In this setting, we propose SAMCLR, an add-on to SimCLR which uses SAM to segment the image into semantic regions, then sample the two views from the same region. Preliminary results show empirically that when pre-training on Cityscapes and ADE20K, then evaluating on classification on CIFAR-10, STL10 and ImageNette, SAMCLR performs at least on par with, and most often significantly outperforms not only SimCLR, but also DINO and MoCo.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2310.14736>)

[PDF](<https://arxiv.org/pdf/2310.14736.pdf>)