BiLingUNet: Image Segmentation by Modulating Top-Down and Bottom-Up Visual Processing with Referring Expressions

We present BiLingUNet, a state-of-the-art model for image segmentation using referring expressions. BiLingUNet uses language to customize visual filters and outperforms approaches that concatenate a linguistic representation to the visual input. We find that using language to modulate both bottom-up and top-down visual processing works better than just making the top-down processing language-conditional. We argue that common 1x1 language-conditional filters cannot represent relational concepts and experimentally demonstrate that wider filters work better. Our model achieves state-of-the-art performance on four referring expression datasets.