Wrapped Cauchy Distributed Angular Softmax for Long-Tailed Visual Recognition

Authors: Boran Han

ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

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 <boranhan@amazon.com>.
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.