Leveraging StyleGAN's expressivity and its disentangled latent codes,
existing methods can achieve realistic editing of different visual attributes
such as age and gender of facial images. An intriguing yet challenging problem
arises: Can generative models achieve counterfactual editing against their
learnt priors? Due to the lack of counterfactual samples in natural datasets,
we investigate this problem in a text-driven manner with
Contrastive-Language-Image-Pretraining (CLIP), which can offer rich semantic
knowledge even for various counterfactual concepts. Different from in-domain
manipulation, counterfactual manipulation requires more comprehensive
exploitation of semantic knowledge encapsulated in CLIP as well as more
delicate handling of editing directions for avoiding being stuck in local
minimum or undesired editing. To this end, we design a novel contrastive loss
that exploits predefined CLIP-space directions to guide the editing toward
desired directions from different perspectives. In addition, we design a simple
yet effective scheme that explicitly maps CLIP embeddings (of target text) to
the latent space and fuses them with latent codes for effective latent code
optimization and accurate editing. Extensive experiments show that our design
achieves accurate and realistic editing while driving by target texts with
various counterfactual concepts.

通过 Contrastive-Language-Image- Pretraining (CLIP) 进行对抗操作，利用预定义的 CLIP 空间方向指导编辑，并将文本嵌入显式地转换为潜在空间，以实现准确的编码和编辑。