A Novel Visual Representation on Text Using Diverse Conditional GAN for Visual Recognition
Abstract— Automatic image visual recognition can make full use of largely available images with text descriptions on social media platforms to build large-scale image labeled datasets. In this paper, we propose a novel visual text representation, named DG-VRT (Diverse GAN-Visual Representation on Text), which extracts visual features from synthetic images generated by a diverse conditional Generative Adversarial Network (DCGAN) on the text, for visual recognition. The DCGAN incorporates the current state-of-the-art text-to-image GANs and generates multiple synthetic images with various prior noises conditioned on a text. Then we extract deep visual features from the generated synthetic images to explore the underlying visual concepts and provide a visual transformation on text in feature space. Finally, we combine image-level visual features, text-level features and visual features based on synthetic images together to recognize the images, and we also extend the proposed work to semantic segmentation. We conduct extensive experiments on two benchmark datasets and the experimental results demonstrate the efficacy of our proposed representation on text for visual recognition. Index Terms— Visual representation, diverse conditional GAN, visual recognition.
Code (1)
Tasks
Generative Adversarial NetworkSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Text-Conditional JEPA for Learning Semantically Rich Visual Representations
Image-based Joint-Embedding Predictive Architecture (I-JEPA) offers a promising approach to visual self-supervised learning through masked feature prediction. However with the inherent visual uncertainty at masked positi…
Self-Supervised LearningNoise Conditional Flow Model for Learning the Super-Resolution Space
Fundamentally, super-resolution is ill-posed problem because a low-resolution image can be obtained from many high-resolution images. Recent studies for super-resolution cannot create diverse super-resolution images. Alt…
DiversitySuper-ResolutionFocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations
Visual understanding is inherently contextual -- what we focus on in an image depends on the task at hand. For instance, given an image of a person holding a bouquet of flowers, we may focus on either the person such as …
image-classificationImage ClassificationImage RetrievalImage-text Retrieval+2Transfer Learning via Unsupervised Task Discovery for Visual Question Answering
We study how to leverage off-the-shelf visual and linguistic data to cope with out-of-vocabulary answers in visual question answering task. Existing large-scale visual datasets with annotations such as image class labels…
Question AnsweringTransfer LearningVisual Question AnsweringVisual Question Answering (VQA)Multi-Modal Representation Learning with Text-Driven Soft Masks
We propose a visual-linguistic representation learning approach within a self-supervised learning framework by introducing a new operation, loss, and data augmentation strategy. First, we generate diverse features for th…
Contrastive LearningData AugmentationImage-text matchingRepresentation Learning+2