LARGE: Latent-Based Regression through GAN Semantics

By Yotam Nitzan, Rinon Gal, Ofir Brenner, Daniel Cohen-Or. 2021

27 citations recorded by the source corpus.

We propose a novel method for solving regression tasks using few-shot or weak supervision. At the core of our method is the fundamental observation that GANs are incredibly successful at encoding semantic information within their latent space, even in a completely unsupervised setting. For modern generative frameworks, this semantic encoding manifests as smooth, linear directions which affect image attributes in a disentangled manner. These directions have been widely used in GAN-based image editing. In this work, we leverage them for few-shot regression. Specifically, we make the simple observation that distances traversed along such directions are good features for downstream tasks - reliably gauging the magnitude of a property in an image. In the absence of explicit supervision, we use these distances to solve tasks such as sorting a collection of images, and ordinal regression. With a few labels - as little as two - we calibrate these distances to real-world values and convert a pre-trained GAN into a state-of-the-art few-shot regression model. This enables solving regression tasks on datasets and attributes which are difficult to produce quality supervision for. Extensive experimental evaluations demonstrate that our method can be applied across a wide range of domains, leverage multiple latent direction discovery frame-works, and achieve state-of-the-art results in few-shot and low-supervision settings, even when compared to methods designed to tackle a single task. Code is available on our project website.

Subfields: Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

StyleGAN-NADA (2021, background): “These range from image enhancement [18,50], editing [13,36] and recently even discriminative tasks such as classification and regression [27, 48].”
StyleAlign: Analysis and Applications of Aligned StyleGAN Models (2021, methodology): “To leverage aligned models for regression tasks, we use LARGE (Nitzan et al., 2021), which demonstrated that the distance in W + space to the decision hyperplane associated with a semantic property, gauges the degree of that attribute in image space.”