Brave: Byzantine-Resilient and Privacy-Preserving Peer-to-Peer Federated Learningby Zhangchen Xu, Fengqing Jiang, Luyao Niu, Jinyuan Jia,…
Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformerby Teru Nagamori, Sayaka Shiota, Hitoshi KiyaFirst…
Do Vision and Language Encoders Represent the World Similarly?by Mayug Maniparambil, Raiymbek Akshulakov, Yasser Abdelaziz…
Benchmark Analysis of Various Pre-trained Deep Learning Models on ASSIRA Cats and Dogs Datasetby Galib…
A Large-Scale Empirical Study on Improving the Fairness of Image Classification Modelsby Junjie Yang, Jiajun…
On the Stability of a non-hyperbolic nonlinear map with non-bounded set of non-isolated fixed points…
Understanding the Detrimental Class-level Effects of Data Augmentationby Polina Kirichenko, Mark Ibrahim, Randall Balestriero, Diane…
ProbMCL: Simple Probabilistic Contrastive Learning for Multi-label Visual Classificationby Ahmad Sajedi, Samir Khaki, Yuri A.…
Freeze the backbones: A Parameter-Efficient Contrastive Approach to Robust Medical Vision-Language Pre-trainingby Jiuming Qin, Che…
Class Relevance Learning For Out-of-distribution Detectionby Butian Xiong, Liguang Zhou, Tin Lun Lam, Yangsheng XuFirst…