UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes

We introduce UViM, a unified approach capable of modeling a wide range of computer vision tasks. In contrast to previous models, UViM has the same functional form for all tasks; it requires no task-specific modifications which require extensive human expertise. The approach involves two components: (I) a base model (feedforward) which is trained to directly predict raw vision outputs, guided by a learned discrete code and (II) a language model (autoregressive) that is trained to generate the guiding code. These components complement each other: the language model is well-suited to modeling structured interdependent data, while the base model is efficient at dealing with high-dimensional outputs. We demonstrate the effectiveness of UViM on three diverse and challenging vision tasks: panoptic segmentation, depth prediction and image colorization, where we achieve competitive and near state-of-the-art results. Our experimental results suggest that UViM is a promising candidate for a unified modeling approach in computer vision. Recently, there have been significant advances in the modeling of complex structured outputs in the context of language generation and (conditional) image generation: autoregressive models [49, 41, 25] , GANs [13], VAE [22], VQVAE [51], diffusion models [45, 18] . However, using such techniques to tackle discriminative problems in a unified way remains under-explored. In this work, we propose a new approach, UViM, capable of modeling many vision tasks, leveraging recent advances in discrete representation learning [51] and language modeling [52] . We show competitive results in three diverse tasks: panoptic segmentation [23], depth prediction [43] and colorization [57] . Crucially, there are no task-specific components required for each task. All of the tasks use the same model and are amenable to transfer learning from standard pre-trained models.