Partially View-aligned Representation Learning with Noise-robust Contrastive Loss
Authors:
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1134-1143
Abstract
In real-world applications, it is common that only a portion of data is aligned across views due to spatial, temporal, or spatiotemporal asynchronism, thus leading to the so-called Partially View-aligned Problem (PVP). To solve such a less-touched problem without the help of labels, we propose simultaneously learning representation and aligning data using a noise-robust contrastive loss. In brief, for each sample from one view, our method aims to identify its within-category counterparts from other views, and thus the cross-view correspondence could be established. As the contrastive learning needs data pairs as input, we construct positive pairs using the known correspondences and negative pairs using random sampling. To alleviate or even eliminate the influence of the false negatives caused by random sampling, we propose a noise-robust contrastive loss that could adaptively prevent the false negatives from dominating the network optimization. To the best of our knowledge, this could be the first successful attempt of enabling contrastive learning robust to noisy labels. In fact, this work might remarkably enrich the learning paradigm with noisy labels. More specifically, the traditional noisy labels are defined as incorrect annotations for the supervised tasks such as classification. In contrast, this work proposes that the view correspondence might be false, which is remarkably different from the widely-accepted definition of noisy label. Extensive experiments show the promising performance of our method comparing with 10 state-of-the-art multi-view approaches in the clustering and classification tasks. The code will be publicly released at https://pengxi.me.Keywords
Funding Information
- Fundamental Research Funds for the Central Universities
- Beijing Nova Program
This publication has 20 references indexed in Scilit:
- Binary Multi-View ClusteringIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Triplet-Based Deep Hashing Network for Cross-Modal RetrievalIEEE Transactions on Image Processing, 2018
- Self-weighted Multiview Clustering with Multiple Graphs2017
- Latent Multi-view Subspace Clustering2017
- Multi-View Learning With Incomplete ViewsIEEE Transactions on Image Processing, 2015
- FaceNet: A unified embedding for face recognition and clustering2015
- Deep visual-semantic alignments for generating image descriptions2015
- Ensemble Projection for Semi-supervised Image Classification2013
- Dimensionality Reduction by Learning an Invariant Mapping2006
- A Bayesian Hierarchical Model for Learning Natural Scene Categories2005