Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Deep Set Prediction Networks
Authors: Yan Zhang, Jonathon Hare, Adam Prugel-Bennett
NeurIPS 2019 | Venue PDF | LLM Run Details | Input Tokens: 16,356 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,434 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate our model on several set prediction datasets (section 5). First, we demonstrate that the auto-encoder version of our model is sound on a set version of MNIST. Next, we use the CLEVR dataset to show that this works for general set prediction tasks. We predict the set of bounding boxes of objects in an image and we predict the set of object attributes in an image, both from a single feature vector. |
| Researcher Affiliation | Academia | Yan Zhang University of Southampton Southampton, UK EMAIL Jonathon Hare University of Southampton Southampton, UK EMAIL Adam Prügel-Bennett University of Southampton Southampton, UK EMAIL |
| Pseudocode | Yes | Algorithm 1 One forward pass of the set prediction algorithm within the training loop. |
| Open Source Code | Yes | We provide the PyTorch [18] source code to reproduce all experiments at https://github.com/Cyanogenoid/dspn. |
| Open Datasets | Yes | We begin with the task of auto-encoding a set version of MNIST. Next, we turn to the task of object detection on the CLEVR dataset [11] |
| Dataset Splits | Yes | Next, we turn to the task of object detection on the CLEVR dataset [11], which contains 70,000 training and 15,000 validation images. |
| Hardware Specification | No | No specific hardware details (e.g., GPU models, CPU types, memory) are provided for the experimental setup. |
| Software Dependencies | No | The paper mentions 'PyTorch [18]' but does not specify a version number for it or any other software dependencies. |
| Experiment Setup | Yes | In all experiments, we fix the hyperparameters of our model to T = 10, η = 800, λ = 0.1. Further details about the model architectures, training settings, and hyperparameters are given in Appendix B. |