# Deep Set Prediction Networks

arXiv: https://arxiv.org/abs/1906.06565 · HTML: https://mlsanity.com/paper/1906.06565/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2019.

## Built on by (most cited first, 30 of 71)

- [GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement](https://mlsanity.com/paper/2104.09958/) (2021)
- [SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data](https://mlsanity.com/paper/2103.15619/) (2021)
- [Visual Representation Learning Does Not Generalize Strongly Within the Same Domain](https://mlsanity.com/paper/2107.08221/) (2021)
- [Improving Object-centric Learning with Query Optimization](https://mlsanity.com/paper/2210.08990/) (2022)
- [Learning Disentangled Representations in the Imaging Domain](https://mlsanity.com/paper/2108.12043/) (2021)
- [Low Dimensional Invariant Embeddings for Universal Geometric Learning](https://mlsanity.com/paper/2205.02956/) (2022)
- [Top-N: Equivariant set and graph generation without exchangeability](https://mlsanity.com/paper/2110.02096/) (2021)
- [Neural Injective Functions for Multisets, Measures and Graphs via a Finite Witness Theorem](https://mlsanity.com/paper/2306.06529/) (2023)
- [Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learning](https://mlsanity.com/paper/2210.10880/) (2022)
- [The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider](https://mlsanity.com/paper/2105.14027/) (2021)
- [From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication](https://mlsanity.com/paper/2310.01211/) (2023)
- [Learning Efficient Multi-Agent Cooperative Visual Exploration](https://mlsanity.com/paper/2110.05734/) (2021)
- [Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Exploration](https://mlsanity.com/paper/2301.03398/) (2023)
- [Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation](https://mlsanity.com/paper/2111.12193/) (2021)
- [Boosting Object Representation Learning via Motion and Object Continuity](https://mlsanity.com/paper/2211.09771/) (2022)
- [Unknown Object Segmentation from Stereo Images](https://mlsanity.com/paper/2103.06796/) (2021)
- [Unlocking Slot Attention by Changing Optimal Transport Costs](https://mlsanity.com/paper/2301.13197/) (2023)
- [Prefix-Tree Decoding for Predicting Mass Spectra from Molecules](https://mlsanity.com/paper/2303.06470/) (2023)
- [multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning](https://mlsanity.com/paper/2106.01354/) (2021)
- [A Survey on Influence Maximization: From an ML-Based Combinatorial Optimization](https://mlsanity.com/paper/2211.03074/) (2022)
- [Object-Centric Learning with Slot Mixture Module](https://mlsanity.com/paper/2311.04640/) (2023)
- [PolyOculus: Simultaneous Multi-view Image-based Novel View Synthesis](https://mlsanity.com/paper/2402.17986/) (2024)
- [On permutation-invariant neural networks](https://mlsanity.com/paper/2403.17410/) (2024)
- [Multimodal Fusion Refiner Networks](https://mlsanity.com/paper/2104.03435/) (2021)
- [Rethinking Deep Thinking: Stable Learning of Algorithms using Lipschitz Constraints](https://mlsanity.com/paper/2410.23451/) (2024)
- [SLASH: Embracing Probabilistic Circuits into Neural Answer Set Programming](https://mlsanity.com/paper/2110.03395/) (2021)
- [Conditional set generation using Seq2seq models](https://mlsanity.com/paper/2205.12485/) (2022)
- [Robust and Controllable Object-Centric Learning through Energy-based Models](https://mlsanity.com/paper/2210.05519/) (2022)
- [Let There Be Order: Rethinking Ordering in Autoregressive Graph Generation](https://mlsanity.com/paper/2305.15562/) (2023)
- [SGOOD: Substructure-enhanced Graph-Level Out-of-Distribution Detection](https://mlsanity.com/paper/2310.10237/) (2023)

## Abstract (arXiv)

Current approaches for predicting sets from feature vectors ignore the unordered nature of sets and suffer from discontinuity issues as a result. We propose a general model for predicting sets that properly respects the structure of sets and avoids this problem. With a single feature vector as input, we show that our model is able to auto-encode point sets, predict the set of bounding boxes of objects in an image, and predict the set of attributes of these objects.