Conditioning non-linear and infinite-dimensional diffusion processes
Authors: Elizabeth L. Baker, Gefan Yang, Michael Severinsen, Christy Hipsley, Stefan Sommer
NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We consider two main setups. Firstly we look at Brownian motion between shapes and use this to evaluate our method, since for Brownian motion we have a closed form solution for the score function. We then apply this to problems from the shape space literature. There, they are interested in stochastic bridges between shapes which has applications within medical imaging and evolutionary biology [Gerig et al., 2001, Arnaudon et al., 2017, 2023]. We expand on that body of work, by allowing shapes to be treated as infinite-dimensional objects when bridging, as in the non-stochastic case [Younes, 2019]. Until now, this was impossible for stochastic shape paths, since the theory for this was missing. |
| Researcher Affiliation | Academia | Elizabeth Louise Baker Department of Computer Science, University of Copenhagen elba@di.ku.dkGefan Yang Department of Computer Science, University of Copenhagen gy@di.ku.dkMichael L. Severinsen Globe Institute, University of Copenhagen michael.baand@sund.ku.dkChristy Anna Hipsley Department of Biology, University of Copenhagen christy.hipsley@bio.ku.dkStefan Sommer Department of Computer Science, University of Copenhagen sommer@di.ku.dk |
| Pseudocode | No | The paper refers to an 'algorithm in Heng et al. [2021]' and describes aspects of its implementation (e.g., neural network structure in Figure 7), but it does not include any pseudocode or a clearly labeled algorithm block within its own text. |
| Open Source Code | Yes | The code used for our training and experiments can be found at https://github.com/libbylbaker/infsdebridge and further details on experiments can be found in Appendix B. |
| Open Datasets | Yes | The Lepidoptera images originate from five closely related species within the genus Papilio from the Papilionidae family [Kawahara et al., 2023]. The images are obtained through gbif.org [gbif.org, 2023], filtering within preserved material from museum collections. |
| Dataset Splits | No | The paper mentions training on target shapes and butterfly means but does not explicitly provide details on how the dataset was split into training, validation, and test sets, such as percentages or specific sample counts. |
| Hardware Specification | Yes | All the training and evaluation computations were done with one NVIDIA RTX 4090 GPU and one Intel(R) Xeon(R) CPU E5-2650 v4 @ 2.20GHz. |
| Software Dependencies | Yes | The images are segmented with the Python packages Segment Anything [Kirillov et al., 2023] and Grounding Dino [Liu et al., 2023]... The alignment and the mean consensus shape were obtained by using the R package Geomorph v. 4.06 [Adams and Otarola-Castillo, 2013]. |
| Experiment Setup | Yes | We train on batches of 50 SDE trajectories, with 40 batches per epoch. For training details see Appendix B.1... We used the Adam optimiser for the training, with a starting learning rate of 0.0001 and 500 warmup steps. After warming up, the learning rate decreases cosinely until it reaches 1e-6. |