# Self-supervised Learning of Contextualized Local Visual Embeddings

Source: [Self-supervised Learning of Contextualized Local Visual Embeddings](<https://www.sota2.com/research/paper/68fa70cd1e209131cea4d427>)

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

Data updated: 2025-10-26T01:50:52.513Z

Authors: Thalles Santos Silva, Helio Pedrini, Ad\\'in Ram\\'irez Rivera

Published: 2023-10-01T00:13:06.000Z

## Abstract

We present Contextualized Local Visual Embeddings (CLoVE), a self-supervised convolutional-based method that learns representations suited for dense prediction tasks. CLoVE deviates from current methods and optimizes a single loss function that operates at the level of contextualized local embeddings learned from output feature maps of convolution neural network (CNN) encoders. To learn contextualized embeddings, CLoVE proposes a normalized mult-head self-attention layer that combines local features from different parts of an image based on similarity. We extensively benchmark CLoVE's pre-trained representations on multiple datasets. CLoVE reaches state-of-the-art performance for CNN-based architectures in 4 dense prediction downstream tasks, including object detection, instance segmentation, keypoint detection, and dense pose estimation.

## 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/2310.00527>)

[PDF](<https://arxiv.org/pdf/2310.00527.pdf>)
