论文标题
识别意识到的学习图像压缩
Recognition-Aware Learned Image Compression
论文作者
论文摘要
学到的图像压缩方法通常优化了利率损失，从而使添加比特率的视觉失真的改善进行了改善。但是，越来越多的压缩图像被用作深度学习网络的输入，用于各种任务，例如分类，对象检测和超分辨率。我们提出了一种识别意识到的学习压缩方法，该方法可以与特定于任务的损失，共同学习压缩和识别网络一起优化利率损失。我们增强了具有高效网络识别模型的基于层次自动编码器的压缩网络，并使用两个超参数在失真，比特率和识别性能之间进行权衡。我们将提出方法的分类精度表征为比特率的函数，并发现与传统方法相比，在等效比特率的低比特率中，我们的方法的识别精度高达26％，例如更好的便携式图形（BPG）。
Learned image compression methods generally optimize a rate-distortion loss, trading off improvements in visual distortion for added bitrate. Increasingly, however, compressed imagery is used as an input to deep learning networks for various tasks such as classification, object detection, and superresolution. We propose a recognition-aware learned compression method, which optimizes a rate-distortion loss alongside a task-specific loss, jointly learning compression and recognition networks. We augment a hierarchical autoencoder-based compression network with an EfficientNet recognition model and use two hyperparameters to trade off between distortion, bitrate, and recognition performance. We characterize the classification accuracy of our proposed method as a function of bitrate and find that for low bitrates our method achieves as much as 26% higher recognition accuracy at equivalent bitrates compared to traditional methods such as Better Portable Graphics (BPG).
