# Generalized 3D Self-supervised Learning Framework via Prompted Foreground-Aware Feature Contrast

arXiv: https://arxiv.org/abs/2303.06388 · HTML: https://mlsanity.com/paper/2303.06388/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 83 references that are in the map.
- First posted on arXiv 11 Mar 2023.

## Builds on (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Self-Supervised Pretraining of 3D Features on any Point-Cloud](https://mlsanity.com/paper/2101.02691/) (2021)
- [PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds](https://mlsanity.com/paper/2103.14635/) (2021)
- [Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations](https://mlsanity.com/paper/2207.05027/) (2022)
- [Refine and Represent: Region-to-Object Representation Learning](https://mlsanity.com/paper/2208.11821/) (2022)
- [An Integrated LiDAR-SLAM System for Complex Environment with Noisy Point Clouds](https://mlsanity.com/paper/2212.05705/) (2022)

## Built on by (most cited first, 2 of 2)

- [PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds](https://mlsanity.com/paper/2311.04501/) (2023)
- [SVCNet: Scribble-based Video Colorization Network with Temporal Aggregation](https://mlsanity.com/paper/2303.11591/) (2023)

## Abstract (arXiv)

Contrastive learning has recently demonstrated great potential for unsupervised pre-training in 3D scene understanding tasks. However, most existing work randomly selects point features as anchors while building contrast, leading to a clear bias toward background points that often dominate in 3D scenes. Also, object awareness and foreground-to-background discrimination are neglected, making contrastive learning less effective. To tackle these issues, we propose a general foreground-aware feature contrast FAC++ framework to learn more effective point cloud representations in pre-training. FAC++ consists of two novel contrast designs to construct more effective and informative contrast pairs. The first is building positive pairs within the same foreground segment where points tend to have the same semantics. The second is that we prevent over-discrimination between 3D segments/objects and encourage grouped foreground-to-background distinctions at the segment level with adaptive feature learning in a Siamese correspondence network, which adaptively learns feature correlations within and across point cloud views effectively. Moreover, we have designed the foreground-prompted regional sampling to enhance more balanced foreground-aware learning, which is termed FAC++. Visualization with point activation maps shows that our contrast pairs capture clear correspondences among foreground regions during pre-training. Quantitative experiments also show that FAC++ achieves superior knowledge transfer and data efficiency in various downstream 3D semantic segmentation, instance segmentation as well as object detection tasks. All codes, data, and models are available at: https://github.com/KangchengLiu/FAC_Foreground_Aware_Contrast