# Exploit Clues from Views: Self-Supervised and Regularized Learning for Multiview Object Recognition

arXiv: https://arxiv.org/abs/2003.12735 · HTML: https://mlsanity.com/paper/2003.12735/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Mar 2020.

## Built on by (most cited first, 6 of 6)

- [Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias](https://mlsanity.com/paper/2101.07296/) (2021)
- [Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework](https://mlsanity.com/paper/2204.13207/) (2022)
- [Incremental 3D Semantic Scene Graph Prediction from RGB Sequences](https://mlsanity.com/paper/2305.02743/) (2023)
- [Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization](https://mlsanity.com/paper/2211.15059/) (2022)
- [PICASO: Permutation-Invariant Cascaded Attentional Set Operator](https://mlsanity.com/paper/2107.08305/) (2021)
- [Low-shot Object Learning with Mutual Exclusivity Bias](https://mlsanity.com/paper/2312.03533/) (2023)

## Abstract (arXiv)

Multiview recognition has been well studied in the literature and achieves decent performance in object recognition and retrieval task. However, most previous works rely on supervised learning and some impractical underlying assumptions, such as the availability of all views in training and inference time. In this work, the problem of multiview self-supervised learning (MV-SSL) is investigated, where only image to object association is given. Given this setup, a novel surrogate task for self-supervised learning is proposed by pursuing "object invariant" representation. This is solved by randomly selecting an image feature of an object as object prototype, accompanied with multiview consistency regularization, which results in view invariant stochastic prototype embedding (VISPE). Experiments shows that the recognition and retrieval results using VISPE outperform that of other self-supervised learning methods on seen and unseen data. VISPE can also be applied to semi-supervised scenario and demonstrates robust performance with limited data available. Code is available at https://github.com/chihhuiho/VISPE