paper-with-me

Papers

Learning Representational Invariances for Data-Efficient Action Recognition

2021-03-30 · Yuliang Zou, Jinwoo Choi, Qitong Wang, Jia-Bin Huang

Data augmentation is a ubiquitous technique for improving image classification when labeled data is scarce. Constraining the model predictions to be invariant to diverse data augmentations effectively injects the desired representational invariances to the model (e.g., invariance to photometric variations) and helps improve accuracy. Compared to image data, the appearance variations in videos are far more complex due to the additional temporal dimension. Yet, data augmentation methods for videos remain under-explored. This paper investigates various data augmentation strategies that capture different video invariances, including photometric, geometric, temporal, and actor/scene augmentations. When integrated with existing semi-supervised learning frameworks, we show that our data augmentation strategy leads to promising performance on the Kinetics-100/400, Mini-Something-v2, UCF-101, and HMDB-51 datasets in the low-label regime. We also validate our data augmentation strategy in the fully supervised setting and demonstrate improved performance.

📄 PDF Abstract BibTeX arXiv:2103.16565

Code (1)

vt-vl-lab/video-data-aug 공식 구현 pytorch

Tasks

Action RecognitionData Augmentationimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Understanding Cross-Model Perceptual Invariances Through Ensemble Metamers

2025-04-02 · Lukas Boehm, Jonas Leo Mueller, Christoffer Loeffler, Leo Schwinn 외

Understanding the perceptual invariances of artificial neural networks is essential for improving explainability and aligning models with human vision. Metamers - stimuli that are physically distinct yet produce identica…

Composable Augmentation Encoding for Video Representation Learning

2021-04-01 · ICCV 2021 10 · Chen Sun, Arsha Nagrani, Yonglong Tian, Cordelia Schmid

We focus on contrastive methods for self-supervised video representation learning. A common paradigm in contrastive learning is to construct positive pairs by sampling different data views for the same instance, with dif…

Action RecognitionContrastive LearningRepresentation LearningTemporal Action Localization

Measuring Representational Robustness of Neural Networks Through Shared Invariances

2022-06-23 · Vedant Nanda, Till Speicher, Camila Kolling, John P. Dickerson 외

A major challenge in studying robustness in deep learning is defining the set of ``meaningless'' perturbations to which a given Neural Network (NN) should be invariant. Most work on robustness implicitly uses a human as …

Rethinking the Augmentation Module in Contrastive Learning: Learning Hierarchical Augmentation Invariance with Expanded Views

2022-06-01 · CVPR 2022 1 · Junbo Zhang, Kaisheng Ma

A data augmentation module is utilized in contrastive learning to transform the given data example into two views, which is considered essential and irreplaceable. However, the predetermined composition of multiple data …

Contrastive LearningData Augmentation

What Should Not Be Contrastive in Contrastive Learning

2020-08-13 · ICLR 2021 1 · Tete Xiao, Xiaolong Wang, Alexei A. Efros, Trevor Darrell

Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. However, these methods implicitly assume a …

AllContrastive Learning