Loss Function Search for Face Recognition
- 1 Presented by
- 2 Introduction
- 3 Previous Work
- 4 Motivation
- 5 Problem Formulation
- 6 Results and Discussion
- 7 Conclusion
- 8 Critiques
- 9 References
Jan Lau, Anas Mahdi, Will Thibault, Jiwon Yang
Specifically for face recognition, L1 is modified such that wyTx is normalized and s represents the magnitude of wyTx:
This function is crucial in face recognition because it is used for enhancing feature discrimination. While there are different variations of the softmax loss function, they build upon the same structure as the equation above. Some of these variations will be discussed in detail in the later sections.
In this paper, the authors first identified that reducing the softmax probability is a key contribution to feature discrimination and designed two design search spaces (random and reward-guided method). They then evaluated their Random-Softmax and Search-Softmax approaches by comparing the results against other face recognition algorithms using nine popular face recognition benchmarks.
Margin-based (angular, additive, additive angular margins) soft-max loss functions are important in learning discriminative features in face recognition. There have been hand-crafted methods previously developed that require much effort such as A-softmax, V-softmax, AM-Softmax, and Arc-softmax. Li et al. proposed an AutoML for loss function search method also known as AM-LFS from a hyper-parameter optimization perspective . It automatically determines the search space by leveraging reinforcement learning to the search loss functions during the training process, though the drawback is the complex and unstable search space.
Previous algorithms for facial recognition frequently rely on CNNs that may include metric learning loss functions such as contrastive loss or triplet loss. Without sensitive sample mining strategies, the computational cost for these functions was high. This drawback prompts the redesign of classical softmax loss that cannot discriminate features. Multiple softmax loss functions have since been developed, and including margin-based formulations, they often require fine tuning of parameters and are susceptible to instability. Therefore, researchers need to put in a lot of effort in creating their method in the large design space. AM-LFS takes an optimization approach for selecting hyperparameters for the margin-based softmax functions, but its aforementioned drawbacks are caused by the lack of direction in designing the search space.
To solve the issues associated with hand-tuned softmax loss functions and AM-LFS, the authors attempt to reduce the softmax probability to improve feature discrimination when using margin-based softmax loss functions. The development of margin-based softmax loss with only one parameter required and an improved search space using reward-based method allows the authors to determine the best option for their loss function.
Analysis of Margin-based Softmax Loss
Based on the softmax probability and the margin-based softmax probability, the following function can be developed :
< insert equation >
"a" is considered as a modulating factor and "h(a,p) equation" is a modulating function . Therefore, regardless of the margin function (f), the minimization of the softmax probability will ensure success.
Compared to AM-LFS, this method involves only one parameter (a) that is also constrained, versus AM-LFS which has 2M parameters without constraints that specify the piecewise linear functions the method requires. Also, the piecewise linear functions of AM-LFS ("pm equation") may not be discriminative because it could be larger than the softmax probability.
Results and Discussion
Results on LFW, SLLFW, CALFW, CPLFW, AgeDB, DFP
Results on RFW
Results on MegaFace and Trillion-Pairs
In this paper, it is discussed that in order to enhance feature discrimination for face recognition, it is key to know how to reduce the softmax probability. To achieve this goal, unified formulation for the margin-based softmax losses is designed. Two search methods have been developed using a random and a reward-guided loss function and they were validated to be effective over six other methods using nine different test data sets.
- Thorough experimentation and comparison of results to state-of-the-art provided a convincing argument. - Datasets used did require some preprocessing, which may have improved the results beyond what the method otherwise would. - AM-LFS was created by the authors for experimentation (the code was not made public) so the comparison may not be accurate. - The test data set they used to test Search-Softmax and Random-Softmax are simple and they saturate in other methods. So the results of their methods didn’t show much advantage since they produce very similar results. More complicated data set needs to be tested to prove the method's reliability.
 X. Wang, S. Wang, C. Chi, S. Zhang and T. Mei, "Loss Function Search for Face Recognition", in International Conference on Machine Learning, 2020, pp. 1-10.
 Li, C., Yuan, X., Lin, C., Guo, M., Wu, W., Yan, J., and Ouyang, W. Am-lfs: Automl for loss function search. In Proceedings of the IEEE International Conference on Computer Vision, pp. 8410–8419, 2019. 2020].
 S. L. AI, “Reinforcement Learning algorithms - an intuitive overview,” Medium, 18-Feb-2019. [Online]. Available: https://medium.com/@SmartLabAI/reinforcement-learning-algorithms-an-intuitive-overview-904e2dff5bbc. [Accessed: 25-Nov-2020].
 “Reinforcement learning,” Wikipedia, 17-Nov-2020. [Online]. Available: https://en.wikipedia.org/wiki/Reinforcement_learning. [Accessed: 24-Nov-2020].
 B. Osiński, “What is reinforcement learning? The complete guide,” deepsense.ai, 23-Jul-2020. [Online]. Available: https://deepsense.ai/what-is-reinforcement-learning-the-complete-guide/. [Accessed: 25-Nov-2020].