CVAILGApr 4, 2023

EGC: Image Generation and Classification via a Diffusion Energy-Based Model

arXiv:2304.02012v316 citationsh-index: 71
Originality Highly original
AI Analysis

This work addresses the problem of unifying discriminative and generative learning for researchers and practitioners in computer vision, representing a novel approach rather than an incremental improvement.

The paper tackles the challenge of performing both image generation and classification with a single neural network, introducing EGC, which achieves competitive generation results on datasets like ImageNet-1k and superior classification accuracy and robustness on CIFAR-10.

Learning image classification and image generation using the same set of network parameters is a challenging problem. Recent advanced approaches perform well in one task often exhibit poor performance in the other. This work introduces an energy-based classifier and generator, namely EGC, which can achieve superior performance in both tasks using a single neural network. Unlike a conventional classifier that outputs a label given an image (i.e., a conditional distribution $p(y|\mathbf{x})$), the forward pass in EGC is a classifier that outputs a joint distribution $p(\mathbf{x},y)$, enabling an image generator in its backward pass by marginalizing out the label $y$. This is done by estimating the energy and classification probability given a noisy image in the forward pass, while denoising it using the score function estimated in the backward pass. EGC achieves competitive generation results compared with state-of-the-art approaches on ImageNet-1k, CelebA-HQ and LSUN Church, while achieving superior classification accuracy and robustness against adversarial attacks on CIFAR-10. This work represents the first successful attempt to simultaneously excel in both tasks using a single set of network parameters. We believe that EGC bridges the gap between discriminative and generative learning.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes