Alibaba Cloud Developer

Apr 10, 2019 · Artificial Intelligence

Bilinear Residual Layers: Boosting Text‑Guided Image Editing

This article explores multimodal representation learning by introducing a Bilinear Residual Layer that automatically fuses image and text features, demonstrates its superiority over traditional concatenation and FiLM methods on text‑guided image editing and fashion synthesis tasks, and reports state‑of‑the‑art results on several benchmark datasets.