Notice: 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. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Projective Equivariant Networks via Second-order Fundamental Differential Invariants
Authors: Yikang Li, Yeqing Qiu, Yuxuan Chen, Lingshen He, Lexiang Hu, Zhouchen Lin
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Empirical results on the projectively transformed STL-10 and Imagenette datasets show that PDINet achieves improvements of 11.39% and 5.66% in accuracy over the respective standard baselines under out-of-distribution settings, demonstrating its strong generalization to complex geometric transformations. |
| Researcher Affiliation | Academia | 1State Key Lab of General AI, School of Intelligence Science and Technology, Peking University 2School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen 3Shenzhen Research Institute of Big Data 4Khoury College of Computer Sciences, Northeastern University 5Institute for Artificial Intelligence, Peking University |
| Pseudocode | No | The paper describes methods through mathematical formulations and textual descriptions, but no explicit pseudocode or algorithm blocks are provided. |
| Open Source Code | Yes | Our code is available at https://github.com/Liyk127/PDINet. |
| Open Datasets | Yes | STL-10 [Coates et al., 2011] is a dataset containing 5000 training images and 8000 test images. Each image has a resolution of 96 96 with RGB channels. |
| Dataset Splits | Yes | STL-10 [Coates et al., 2011] is a dataset containing 5000 training images and 8000 test images. ... Imagenette is a ten-class subset of the Image Net dataset [Deng et al., 2009], consisting of 9469 training images and 3925 test images. |
| Hardware Specification | Yes | All experiments are conducted on a single NVIDIA RTX 3090 GPU. |
| Software Dependencies | No | The paper mentions software like SGD optimizer, Adam optimizer, Adam W optimizer, and torchstat, but does not specify their version numbers. |
| Experiment Setup | Yes | We train the models for 1000 epochs using SGD optimizer with Nesterov momentum of 0.9 and a batch size of 64. The initial learning rate is set to 0.1 and decayed by a factor of 0.2 at epochs 300, 400, 600, and 800. |