# Slot Contrastive Networks: A Contrastive Approach for Representing Objects

arXiv: https://arxiv.org/abs/2007.09294 · HTML: https://mlsanity.com/paper/2007.09294/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jul 2020.

## Built on by (most cited first, 9 of 9)

- [Generalization and Robustness Implications in Object-Centric Learning](https://mlsanity.com/paper/2107.00637/) (2021)
- [Neural Systematic Binder](https://mlsanity.com/paper/2211.01177/) (2022)
- [Inductive Biases for Object-Centric Representations in the Presence of Complex Textures](https://mlsanity.com/paper/2204.08479/) (2022)
- [Contrastive Conditional Neural Processes](https://mlsanity.com/paper/2203.03978/) (2022)
- [Towards Self-Supervised Learning of Global and Object-Centric Representations](https://mlsanity.com/paper/2203.05997/) (2022)
- [Robust and Controllable Object-Centric Learning through Energy-based Models](https://mlsanity.com/paper/2210.05519/) (2022)
- [Evaluating Disentanglement of Structured Representations](https://mlsanity.com/paper/2101.04041/) (2021)
- [Exploring the Role of the Bottleneck in Slot-Based Models Through Covariance Regularization](https://mlsanity.com/paper/2306.02577/) (2023)
- [The Impact of Negative Sampling on Contrastive Structured World Models](https://mlsanity.com/paper/2107.11676/) (2021)

## Abstract (arXiv)

Unsupervised extraction of objects from low-level visual data is an important goal for further progress in machine learning. Existing approaches for representing objects without labels use structured generative models with static images. These methods focus a large amount of their capacity on reconstructing unimportant background pixels, missing low contrast or small objects. Conversely, we present a new method that avoids losses in pixel space and over-reliance on the limited signal a static image provides. Our approach takes advantage of objects' motion by learning a discriminative, time-contrastive loss in the space of slot representations, attempting to force each slot to not only capture entities that move, but capture distinct objects from the other slots. Moreover, we introduce a new quantitative evaluation metric to measure how "diverse" a set of slot vectors are, and use it to evaluate our model on 20 Atari games.