# Cross-scale Aligned Supervision for Training GANs

Source: [Cross-scale Aligned Supervision for Training GANs](<https://www.sota2.com/research/paper/6a167aacdbd7150506f800cd>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-29T06:00:02.568Z

Authors: Sangeek Hyun, MinKyu Lee, Jae-Pil Heo

Published: 2026-05-26T02:01:11.000Z

## Abstract

Modern GANs often introduce adversarial supervision on intermediate generator outputs and interpret the resulting multi-stage synthesis as coarse-to-fine hierarchical generation. In this work, we challenge this interpretation. We argue that standard scale-wise adversarial supervision does not construct a proper coarse-to-fine hierarchy: each intermediate image is independently pushed toward the real distribution at its own resolution, but this scale-wise realism does not ensure that outputs across stages represent the identical generated sample. Moreover, the scale-specific image produced at each stage is not used as an explicit refinement target for the subsequent stage. Therefore, its adversarial loss can improve a scale-specific output without constraining later stages to preserve the same sample trajectory, allowing them to move toward a different sample rather than refine the previous output. We refer to this problem as a cross-scale trajectory misalignment problem. To resolve it, we propose CAT, a Cross-scale Aligned Transformer for multi-scale adversarial generation. CAT keeps the discriminator scale-wise, so each intermediate output is evaluated at its own resolution, while adding a simple generator-side consistency regularization that aligns intermediate outputs with the final output. On class-conditional ImageNet-256, CAT-H/2 achieves an FID-50K of 1.56 with one-step inference after only 60 training epochs, outperforming strong one-step GAN and diffusion/flow baselines.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Class-conditional Image Generation on ImageNet 256x256](<https://www.sota2.com/research/sota/class-conditional-image-generation-on-imagenet-256x256.md>): Class-conditional Image Generation; ImageNet 256x256; Inception Score (IS): not recorded.

- [Image Generation on ImageNet 256x256](<https://www.sota2.com/research/sota/image-generation-on-imagenet-256x256.md>): Image Generation; ImageNet 256x256; IS: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.26449>)

[PDF](<https://arxiv.org/pdf/2605.26449.pdf>)
