Search

A fundamental bottleneck in text-to-image synthesis is that there are rarely subjective quality evaluation metrics for a single generated image. To address this issue, this paper proposed a procedure to evaluate the single generated image, which includes a specific dataset named multiple metrics quality assessment for birds(MMQA Birds) and a learning model named blind generated image evaluator(BGIE). The motivation of our proposal is twofold. On the one hand, subjective image quality evaluation is a human perceptual task; Therefore, it tends to be a process of supervised learning. To the best of our knowledge, there are not any datasets for this study. Thus, we handle this problem via designing a specific dataset. On the other hand, we observed that the spatial content of generated image attracts more attention when humans judge its quality; According to this finding, an efficient machine-learning model that combines both pixel-level features and spatial features is proposed. Extensive experiments manifest our method can solve this problem to some extent. In the generated image dataset, BGIE surpasses the state-of-art NSS-based method by 6.3% in PLCC and SRCC. In practice, we further discuss the rationality of the MMQA Birds dataset and the application of BGIE. It proves that both in subjective and objective aspects, our method achieves convincing results.

A fundamental problem of text-to-image synthesis is the lack of quality assessment for a single generated image. Quantitative indicators of this work (such as Inception Score and Frechet Inception Distance) only affect plenty of images' feature distribution. It causes monotonous evaluation and plenty of poor-quality image results. This paper proposes a new evaluation criterion for text-to-image synthesis by the blind image quality assessment(BIQA) method. To train the model, a Multi-Metrics Quality Assessment Dataset for generated birds' images(MMQA) is proposed. Besides, the Multi-hyper model is proposed to fit our dataset better. Experiments show that our method evaluates text- to-image tasks more comprehensively and optimize their results.

Advanced sensors are increasingly used in aeronautical facility. Broader acquisition of images improves the quality and quantity of remote sensing images and makes a large number of fine remote sensing images available. Although semantic segmentation models based on deep learning has been a great success in computer vision, there are still a lot of difficulties compared to regular visual senses. In this paper, we propose a novel end-to-end model for remote sensing image segmentation of building footprints and a loss function based on IoU to improve the performance. Semantic labels for building structures are being accurately allocated by our method. We make control experiments on Map Challenge dataset with other semantic segmentation model based on recent deep learning advances. Our proposed method generates 94.73% of IoU on the Map Challenge Dataset's validation set, which outperforms all previous models in literature.