Is There Mode Collapse? A Case Study on Face Generation and Its Black-box Calibration
Generative adversarial networks (GANs) nowadays are capable of producing im-ages of incredible realism. One concern raised is whether the state-of-the-artGAN’s learned distribution still suffers from mode collapse. Existing evaluation metrics for image synthesis focus on low-level perceptual quality. Diversity tests of samples from GANs are usually conducted qualitatively on a small scale. In this work, we devise a set of statistical tools, that are broadly applicable to quantitatively measuring the mode collapse of GANs. Strikingly, we consistently observe strong mode collapse on several state-of-the-art GANs using our toolset. We analyze possible causes, and for the first time present two simple yet effective “black-box” methods to calibrate the GAN learned distribution, without accessing either model parameters or the original training data.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityFace GenerationImage GenerationSimilar Papers 제목 키워드 기반
Generalized Neural Collapse for a Large Number of Classes
Neural collapse provides an elegant mathematical characterization of learned last layer representations (a.k.a. features) and classifier weights in deep classification models. Such results not only provide insights but a…
Face RecognitionRetrievalReal time face recognition using adaboost improved fast PCA algorithm
This paper presents an automated system for human face recognition in a real time background world for a large homemade dataset of persons face. The task is very difficult as the real time background subtraction in an im…
Face RecognitionOn the Role of Neural Collapse in Meta Learning Models for Few-shot Learning
Meta-learning frameworks for few-shot learning aims to learn models that can learn new skills or adapt to new environments rapidly with a few training examples. This has led to the generalizability of the developed model…
Few-Shot LearningMeta-LearningOn the Robustness of Neural Collapse and the Neural Collapse of Robustness
Neural Collapse refers to the curious phenomenon in the end of training of a neural network, where feature vectors and classification weights converge to a very simple geometrical arrangement (a simplex). While it has be…
A Testable Certificate for Constant Collapse in Teacher-Guided VAEs
Posterior collapse in variational autoencoders is often diagnosed by its symptoms: a small KL term, a strong decoder, or weak use of the latent code. These signals are useful, but they do not define a collapse boundary. …