Search papers, labs, and topics across Lattice.
This survey examines the interplay between diffusion and flow-based models in generative modeling, highlighting how advancements in representation learning can enhance generative capabilities and vice versa. By proposing a three-tier progressive framework, the authors categorize existing works that utilize representation learning for generative tasks, extract representations for perception, and aim for unified applications. The study identifies key challenges and suggests future research directions, providing a comprehensive reference for leveraging generative models in various downstream tasks, including image classification and instance-level perception.
Generative models can significantly boost representation learning, but the reverse is equally transformative for generative quality.
Diffusion models and flow-based models have recently become the dominant paradigms in generative modeling, largely due to their ability to learn rich, multi-level visual representations through large-scale training. This creates a bidirectional relationship between generative models and representation learning: improving representation learning enhances generation quality, while the learned representations can be leveraged for broader understanding tasks. This survey systematically explores this interplay with a focus on applications. We propose a three-tier progressive framework that organizes existing works from three perspectives: using representation learning to improve generative capabilities, exploiting generative models to extract representations for perception tasks, and ultimately moving toward general-purpose unified applications. We systematically categorize representative methods across a wide range of downstream tasks, including image classification, dense visual prediction, instance-level perception, and annotation-scarce scenarios. By providing a unified taxonomy and identifying key challenges, this survey aims to clarify the underlying logic of current research and suggest promising directions for future exploration. We hope this work can serve as a valuable reference for researchers interested in harnessing the representation power of generative models for applications beyond generation.
