`

Timezone: »

 
Poster
CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks
Sakshi Varshney · Vinay Kumar Verma · P. K. Srijith · Lawrence Carin · Piyush Rai

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @ None #None

We present a continual learning approach for generative adversarial networks (GANs), by designing and leveraging parameter-efficient feature map transformations. Our approach is based on learning a set of global and task-specific parameters. The global parameters are fixed across tasks whereas the task-specific parameters act as local adapters for each task, and help in efficiently obtaining task-specific feature maps. Moreover, we propose an element-wise addition of residual bias in the transformed feature space, which further helps stabilize GAN training in such settings. Our approach also leverages task similarities based on the Fisher information matrix. Leveraging this knowledge from previous tasks significantly improves the model performance. In addition, the similarity measure also helps reduce the parameter growth in continual adaptation and helps to learn a compact model. In contrast to the recent approaches for continually-learned GANs, the proposed approach provides a memory-efficient way to perform effective continual data generation. Through extensive experiments on challenging and diverse datasets, we show that the feature-map-transformation approach outperforms state-of-the-art methods for continually-learned GANs, with substantially fewer parameters. The proposed method generates high-quality samples that can also improve the generative-replay-based continual learning for discriminative tasks.

Author Information

Sakshi Varshney (IIT Hyderabad)
Vinay Kumar Verma (Indian Institute of Technology Kanpur)
P. K. Srijith (Indian Institute of Technology Hyderabad)
Lawrence Carin (KAUST)
Piyush Rai (IIT Kanpur)

More from the Same Authors