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 Shift Toward Open and Reproducible AI Research," Under Review, 2026. doi: 10.48550/arXiv.2606.16974..

Wrapped Cauchy Distributed Angular Softmax for Long-Tailed Visual Recognition

Authors: Boran Han

ICML 2023 | Venue PDF | LLM Run Details | Input Tokens: 28,565 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,623 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 Empirical results confirm label-aware behavior in these parameters and demonstrate WCDAS s superiority over other state-of-the-art softmaxbased methods in handling long-tailed visual recognition across multiple benchmark datasets.
Researcher Affiliation Industry Amazon Web Services, AI. Work done while at Shell.. Correspondence to: Boran Han <EMAIL>.
Pseudocode Yes Algorithm 1 Wrapped Cauchy Distributed Angular Softmax
Open Source Code Yes The code is public available.
Open Datasets Yes We also compared our approach with SOTA softmax-based methods (Section 4.4) using four large-scale long-tailed datasets: CIFAR10-LT/100-LT (Krizhevsky, 2009), Image Net-LT (Liu et al., 2019; Deng et al., 2009) and i Naturalist 2018 (Van Horn et al., 2018).
Dataset Splits No After training on the long-tailed dataset, we evaluate the models on the corresponding balanced test/validation dataset and report top-1 accuracy.
Hardware Specification No The paper does not specify the exact hardware used for experiments, such as specific GPU or CPU models.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup Yes All models are trained using SGD optimizer with momentum 0.9, weight decay 10 4. The learning rate decays by a cosine scheduler. Unless specified, we use 90 training epochs. Other hyper-parameters are listed in Appendix Table 5.