Papers › Contrastive Video Representation Learning via Adversarial Perturbations

Contrastive Video Representation Learning via Adversarial Perturbations

24 Jul 2018ECCV 2018 9arXiv:1807.09380archive 2025-07-28

Jue Wang, Anoop Cherian

Adversarial perturbations are noise-like patterns that can subtly change the data, while failing an otherwise accurate classifier. In this paper, we propose to use such perturbations within a novel contrastive learning setup to build negative samples, which are then used to produce improved video representations. To this end, given a well-trained deep model for per-frame video recognition, we first generate adversarial noise adapted to this model. Positive and negative bags are produced using the original data features from the full video sequence and their perturbed counterparts, respectively. Unlike the classic contrastive learning methods, we develop a binary classification problem that learns a set of discriminative hyperplanes -- as a subspace -- that will separate the two bags from each other. This subspace is then used as a descriptor for the video, dubbed \emph{discriminative subspace pooling}. As the perturbed features belong to data classes that are likely to be confused with the original features, the discriminative subspace will characterize parts of the feature space that are more representative of the original data, and thus may provide robust video representations. To learn such descriptors, we formulate a subspace learning objective on the Stiefel manifold and resort to Riemannian optimization methods for solving it efficiently. We provide experiments on several video datasets and demonstrate state-of-the-art results.

Paper PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action Recognition Binary Classification Contrastive Learning Representation Learning Riemannian optimization Video Recognition

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Action Recognition	HMDB-51	ADL+ResNet+IDT	Average accuracy of 3 splits	74.3	#43 of 77	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 Convolution Average Pooling Batch Normalization Bottleneck Residual Block Convolution Global Average Pooling Kaiming Initialization Max Pooling ReLU Residual Block Residual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections