论文标题
保守的发电机，渐进式歧视者：以少量增量图像合成的对手的协调
Conservative Generator, Progressive Discriminator: Coordination of Adversaries in Few-shot Incremental Image Synthesis
论文作者
论文摘要
从在线数据流逐步学习的能力是人类学习者的羡慕特征，因为深层神经网络通常会遭受灾难性的遗忘和稳定性 - 塑性困境的困扰。以前有几项作品探索了数量增量学习，这是由于数据限制而面临更大挑战的任务，主要是在分类设置和轻微成功的情况下。在这项工作中，我们研究了代表性不足的生成增量少量学习的任务。为了有效地应对增量学习的固有挑战和很少的学习学习，我们提出了一个名为Conpro的新颖框架，该框架利用了GAN的两人性质。具体而言，我们设计了一个保守的生成器，该生成器可以保留以参数和计算有效方式的过去知识，以及一个学会的渐进歧视器，该歧视器学会推理过去和现在的任务样本之间的语义距离，从而最大程度地减少了很少的数据点并追求良好的远期传输。我们提出了验证Conpro有效性的实验。
The capacity to learn incrementally from an online stream of data is an envied trait of human learners, as deep neural networks typically suffer from catastrophic forgetting and stability-plasticity dilemma. Several works have previously explored incremental few-shot learning, a task with greater challenges due to data constraint, mostly in classification setting with mild success. In this work, we study the underrepresented task of generative incremental few-shot learning. To effectively handle the inherent challenges of incremental learning and few-shot learning, we propose a novel framework named ConPro that leverages the two-player nature of GANs. Specifically, we design a conservative generator that preserves past knowledge in parameter and compute efficient manner, and a progressive discriminator that learns to reason semantic distances between past and present task samples, minimizing overfitting with few data points and pursuing good forward transfer. We present experiments to validate the effectiveness of ConPro.
