Papers › NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANs

NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANs

12 Apr 2023CVPR 2023 1arXiv:2304.05866archive 2025-07-28

Harsh Rangwani, Lavish Bansal, Kartik Sharma, Tejan Karmali, Varun Jampani, R. Venkatesh Babu

StyleGANs are at the forefront of controllable image generation as they produce a latent space that is semantically disentangled, making it suitable for image editing and manipulation. However, the performance of StyleGANs severely degrades when trained via class-conditioning on large-scale long-tailed datasets. We find that one reason for degradation is the collapse of latents for each class in the 𝒲 latent space. With NoisyTwins, we first introduce an effective and inexpensive augmentation strategy for class embeddings, which then decorrelates the latents based on self-supervision in the 𝒲 space. This decorrelation mitigates collapse, ensuring that our method preserves intra-class diversity with class-consistency in image generation. We show the effectiveness of our approach on large-scale real-world long-tailed datasets of ImageNet-LT and iNaturalist 2019, where our method outperforms other methods by ∼19% on FID, establishing a new state-of-the-art.

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Results from the paper archive 2025-07-28

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections