# On the Surprising Effectiveness of Transformers in Low-Labeled Video Recognition

Source: [On the Surprising Effectiveness of Transformers in Low-Labeled Video Recognition](<https://www.sota2.com/research/paper/68fa6dbc1e209131cea3bb07>)

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

Data updated: 2025-10-26T00:42:13.334Z

Authors: Farrukh Rahman, \\"Omer Mubarek, Zsolt Kira

Published: 2022-09-15T17:12:30.000Z

## Abstract

Recently vision transformers have been shown to be competitive with convolution-based methods (CNNs) broadly across multiple vision tasks. The less restrictive inductive bias of transformers endows greater representational capacity in comparison with CNNs. However, in the image classification setting this flexibility comes with a trade-off with respect to sample efficiency, where transformers require ImageNet-scale training. This notion has carried over to video where transformers have not yet been explored for video classification in the low-labeled or semi-supervised settings. Our work empirically explores the low data regime for video classification and discovers that, surprisingly, transformers perform extremely well in the low-labeled video setting compared to CNNs. We specifically evaluate video vision transformers across two contrasting video datasets (Kinetics-400 and SomethingSomething-V2) and perform thorough analysis and ablation studies to explain this observation using the predominant features of video transformer architectures. We even show that using just the labeled data, transformers significantly outperform complex semi-supervised CNN methods that leverage large-scale unlabeled data as well. Our experiments inform our recommendation that semi-supervised learning video work should consider the use of video transformers in the future.

## 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/2209.07474>)

[PDF](<https://arxiv.org/pdf/2209.07474.pdf>)
