Leveraging Pretrained Image Classifiers for Language-Based Segmentation
arxiv(2019)
摘要
Current semantic segmentation models cannot easily generalize to new object classes unseen during train time: they require additional annotated images and retraining. We propose a novel segmentation model that injects visual priors into semantic segmentation architectures, allowing them to segment out new target labels without retraining. As visual priors, we use the activations of pretrained image classifiers, which provide noisy indications of the spatial location of both the target object and distractor objects in the scene. We leverage language semantics to obtain these activations for a target label unseen by the classifier. Further experiments show that the visual priors obtained via language semantics for both relevant and distracting objects are key to our performance.
更多查看译文
AI 理解论文
溯源树
样例

生成溯源树,研究论文发展脉络