CVLGApr 6, 2023

Self-Supervised Video Similarity Learning

arXiv:2304.03378v219 citationsh-index: 51Has Code
AI Analysis

It addresses video retrieval and detection problems for applications like content matching and event analysis, offering a novel method that outperforms prior labeled-data approaches.

The paper tackles video similarity learning by introducing S$^2$VS, a self-supervised approach that achieves state-of-the-art performance on multiple retrieval and detection tasks without labeled data, using a single universal model.

We introduce S$^2$VS, a video similarity learning approach with self-supervision. Self-Supervised Learning (SSL) is typically used to train deep models on a proxy task so as to have strong transferability on target tasks after fine-tuning. Here, in contrast to prior work, SSL is used to perform video similarity learning and address multiple retrieval and detection tasks at once with no use of labeled data. This is achieved by learning via instance-discrimination with task-tailored augmentations and the widely used InfoNCE loss together with an additional loss operating jointly on self-similarity and hard-negative similarity. We benchmark our method on tasks where video relevance is defined with varying granularity, ranging from video copies to videos depicting the same incident or event. We learn a single universal model that achieves state-of-the-art performance on all tasks, surpassing previously proposed methods that use labeled data. The code and pretrained models are publicly available at: https://github.com/gkordo/s2vs

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes