Evolutionary Generative Adversarial Networks with Crossover Based Knowledge Distillation

Abstract

Generative Adversarial Networks (GAN) is an adversarial model, and it has been demonstrated to be effective for various generative tasks. However, GAN and its variants also suffer from many training problems, such as mode collapse and gradient vanish. In this paper, we firstly propose a general crossover operator, which can be widely applied to GANs using evolutionary strategies. Then we design an evolutionary GAN framework C-GAN based on it. And we combine the crossover operator with evolutionary generative adversarial networks (E-GAN) to implement the evolutionary generative adversarial networks with crossover (CE-GAN). Under the premise that a variety of loss functions are used as mutation operators to generate mutation individuals, we evaluate the generated samples and allow the mutation individuals to learn experiences from the output in a knowledge distillation manner, imitating the best output outcome, resulting in better offspring. Then, we greedily selected the best offspring as parents for subsequent training using discriminator as evaluator. Experiments on real datasets demonstrate the effectiveness of CE-GAN and show that our method is competitive in terms of generated images quality and time efficiency.

The application of evolutionary computation in generative adversarial networks (GANs): a systematic literature survey

“…E-GAN only uses different objective functions for the mutation part. Li et al (2021) improved the E-GAN algorithm. The improvement is that the crossover part is added to it, and the C-GAN framework including the crossover operator is proposed.…”

“…It can construct a guided vector (GV) with Fig. 20 Architecture of GAO good direction and adaptive length, and then add the guided vector to the corresponding fireworks position to generate an elite solution called guided spark (GS) (Li et al 2019). In GAO, different from other EAs using random sampling to generate elite solutions or guide vectors, the introduction of GANs increases the variability of the algorithm.…”

DGL-GAN: Discriminator Guided Learning for GAN Compression

“…Besides KD, several works [14], [16], [19] exploit network pruning. In addition, there exist several works [24], [25] developing evolutionary compression with inferior results compared with KD-based approaches.…”

“…We train the student StyleGAN2 on FFHQ with channel multiplier 1/2 via the objective function Eq. (24) or Eq. ( 25) with the similar training techniques for DGL-GAN and report the results in Table 7.…”

“…To make GANs easy to be deployed on computational resource limited devices, extensive works have been proposed to obtain lightweight GANs. The mainstreaming approach is to inherit the model compression techniques developed for image-classification task to compress GANs, such as weight pruning [14], weight quantization [15], channel pruning [16], [17], [18], [19], lightweight GAN architecture search/design [20], [21], [22], [23], evolutionary compression [24], [25], and knowledge distillation (KD) [26], [27], [28], [29], [30], [31], [32], [33]. However, most of the above works focus on compressing conditional (cycle) GANs for image-to-image generation tasks, scarce works have been proposed for compressing vanilla GANs except recent works [8], [17], [18], [27], [34].…”