# Convolutional Set Transformer

arXiv: https://arxiv.org/abs/2509.22889 · HTML: https://mlsanity.com/paper/2509.22889/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 53 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets](https://mlsanity.com/paper/1707.08819/) (2017)
- [On Learning Sets of Symmetric Elements](https://mlsanity.com/paper/2002.08599/) (2020)
- [On the Limitations of Representing Functions on Sets](https://mlsanity.com/paper/1901.09006/) (2019)
- [Universal Approximation of Functions on Sets](https://mlsanity.com/paper/2107.01959/) (2021)
- [FSPool: Learning Set Representations with Featurewise Sort Pooling](https://mlsanity.com/paper/1906.02795/) (2019)
- [Multi-view analysis of unregistered medical images using cross-view transformers](https://mlsanity.com/paper/2103.11390/) (2021)
- [Equilibrium Aggregation: Encoding Sets via Optimization](https://mlsanity.com/paper/2202.12795/) (2022)
- [Attention Fusion Reverse Distillation for Multi-Lighting Image Anomaly Detection](https://mlsanity.com/paper/2406.04573/) (2024)

## Abstract (arXiv)

We introduce the Convolutional Set Transformer (CST), a novel neural architecture designed to process image sets of arbitrary cardinality that are visually heterogeneous yet share high-level semantics - such as a common category, scene, or concept. Existing set-input networks, e.g., Deep Sets and Set Transformer, are limited to vector inputs and cannot directly handle 3D image tensors. As a result, they must be cascaded with a feature extractor, typically a CNN, which encodes images into embeddings before the set-input network can model inter-image relationships. In contrast, CST operates directly on 3D image tensors, performing feature extraction and contextual modeling simultaneously, thereby enabling synergies between the two processes. This design yields superior performance in tasks such as Set Classification and Set Anomaly Detection and further provides native compatibility with CNN explainability methods such as Grad-CAM, unlike competing approaches that remain opaque. Finally, we show that CSTs can be pre-trained on large-scale datasets and subsequently adapted to new domains and tasks through standard Transfer Learning schemes. To support further research, we release CST-15, a CST backbone pre-trained on ImageNet (https://github.com/chinefed/convolutional-set-transformer).