Gosia Lazuka, Andreea Simona Anghel, et al.
SC 2024
We propose a novel confidence scoring mechanism for deep neural networks based on a two-model paradigm involving a base model and a meta-model. The confidence score is learned by the meta-model observing the base model succeeding/failing at its task. As features to the meta-model, we investigate linear classifier probes inserted between the various layers of the base model. Our experiments demonstrate that this approach outperforms multiple baselines in a filtering task, i.e., task of rejecting samples with low confidence. Experimental results are presented using CIFAR-10 and CIFAR-100 dataset with and without added noise. We discuss the importance of confidence scoring to bridge the gap between experimental and real-world applications.
Gosia Lazuka, Andreea Simona Anghel, et al.
SC 2024
Natalia Martinez Gil, Dhaval Patel, et al.
UAI 2024
Shubhi Asthana, Pawan Chowdhary, et al.
KDD 2021
Baifeng Shi, Judy Hoffman, et al.
NeurIPS 2020