DeepAI AI Chat
Log In Sign Up

Each Attribute Matters: Contrastive Attention for Sentence-based Image Editing

10/21/2021
by   Liuqing Zhao, et al.
0

Sentence-based Image Editing (SIE) aims to deploy natural language to edit an image. Offering potentials to reduce expensive manual editing, SIE has attracted much interest recently. However, existing methods can hardly produce accurate editing and even lead to failures in attribute editing when the query sentence is with multiple editable attributes. To cope with this problem, by focusing on enhancing the difference between attributes, this paper proposes a novel model called Contrastive Attention Generative Adversarial Network (CA-GAN), which is inspired from contrastive training. Specifically, we first design a novel contrastive attention module to enlarge the editing difference between random combinations of attributes which are formed during training. We then construct an attribute discriminator to ensure effective editing on each attribute. A series of experiments show that our method can generate very encouraging results in sentence-based image editing with multiple attributes on CUB and COCO dataset. Our code is available at https://github.com/Zlq2021/CA-GAN

READ FULL TEXT

page 2

page 4

page 8

page 10

page 18

page 19

page 20

07/12/2020

PA-GAN: Progressive Attention Generative Adversarial Network for Facial Attribute Editing

Facial attribute editing aims to manipulate attributes on the human face...
07/18/2022

Label2Label: A Language Modeling Framework for Multi-Attribute Learning

Objects are usually associated with multiple attributes, and these attri...
07/21/2020

Garment Design with Generative Adversarial Networks

The designers' tendency to adhere to a specific mental set and heavy emo...
06/24/2021

Learning by Planning: Language-Guided Global Image Editing

Recently, language-guided global image editing draws increasing attentio...
10/02/2022

ManiCLIP: Multi-Attribute Face Manipulation from Text

In this paper we present a novel multi-attribute face manipulation metho...
12/09/2021

HairCLIP: Design Your Hair by Text and Reference Image

Hair editing is an interesting and challenging problem in computer visio...
08/22/2022

TaCo: Textual Attribute Recognition via Contrastive Learning

As textual attributes like font are core design elements of document for...