# Consistent Relative Confidence and Label-Free Model Selection for Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2108.11845 · HTML: https://mlsanity.com/paper/2108.11845/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 31 references that are in the map.
- First posted on arXiv 26 Aug 2021.

## Builds on (most cited first, 10 of 10)

- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019)
- [Neuroevolution in Deep Neural Networks: Current Trends and Future Challenges](https://mlsanity.com/paper/2006.05415/) (2020)
- [Dynamic Ensemble Modeling Approach to Nonstationary Neural Decoding in Brain-Computer Interfaces](https://mlsanity.com/paper/1911.00714/) (2019)
- [Sequential online prediction in the presence of outliers and change points: an instant temporal structure learning approach](https://mlsanity.com/paper/1907.06377/) (2019)
- [Robust Particle Filter by Dynamic Averaging of Multiple Noise Models](https://mlsanity.com/paper/1609.01336/) (2016)
- [Particle Filtering Methods for Stochastic Optimization with Application to Large-Scale Empirical Risk Minimization](https://mlsanity.com/paper/1807.08534/) (2018)
- [Robust Dynamic Multi-Modal Data Fusion: A Model Uncertainty Perspective](https://mlsanity.com/paper/2105.06018/) (2021)

## Built on by (most cited first, 1 of 1)

- [Use the Detection Transformer as a Data Augmenter](https://mlsanity.com/paper/2304.04554/) (2023)

## Abstract (arXiv)

In this paper, we are concerned with image classification with deep convolutional neural networks (CNNs). We focus on the following question: given a set of candidate CNN models, how to select the right one with the best generalization property for the current task? Current model selection methods all require access to a batch of labeled data for computing a pre-specified performance metric, such as the cross-entropy loss, the classification error rate and the negative log-likelihood. In many practical cases, labels are not available in time as labeling itself is a time-consuming and expensive task. To this end, we propose an approach to CNN model selection using only unlabeled data. We develop this method based on a principle termed consistent relative confidence. Experimental results on benchmark datasets demonstrate the effectiveness and efficiency of our method.