Generative Modeling for Multitask Visual Learning

Zhipeng Bao, Yu-Xiong Wang, Martial Hebert

Abstract: Generative modeling has recently shown great promise in computer vision, but it has mostly focused on synthesizing visually realistic images. In this paper, motivated by multi-task learning of shareable feature representations, we consider a novel problem of learning a shared generative model that is useful across various visual perception tasks. Correspondingly, we propose a general multi-task oriented generative modeling (MGM) framework, by coupling a discriminative multi-task network with a generative network. While it is challenging to synthesize both RGB images and pixel-level annotations in multi-task scenarios, our framework enables us to use synthesized images paired with only weak annotations (i.e., image-level scene labels) to facilitate multiple visual tasks. Experimental evaluation on challenging multi-task benchmarks, including NYUv2 and Taskonomy, demonstrates that our MGM framework improves the performance of all the tasks by large margins, especially in the low-data regimes, and our model consistently outperforms state-of-the-art multi-task approaches.

One-sentence Summary: We propose a general multi-task oriented generative modeling (MGM) framework that introduces generative models to facilitate multi-task learning and it consistently outperforms state-of-the-art multi-task approaches.