Recognition-Aware Learned Image Compression
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).
Code (0)
등록된 구현이 없습니다.
Tasks
Image Compressionobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Transferable Learned Image Compression-Resistant Adversarial Perturbations
Adversarial attacks can readily disrupt the image classification system, revealing the vulnerability of DNN-based recognition tasks. While existing adversarial perturbations are primarily applied to uncompressed images o…
Adversarial AttackAutonomous DrivingClassificationFace Recognition+3Saliency-aware End-to-end Learned Variable-Bitrate 360-degree Image Compression
Effective compression of 360$^\circ$ images, also referred to as omnidirectional images (ODIs), is of high interest for various virtual reality (VR) and related applications. 2D image compression methods ignore the equat…
Image CompressionOptimized Learned Image Compression for Facial Expression Recognition
Efficient data compression is crucial for the storage and transmission of visual data. However, in facial expression recognition (FER) tasks, lossy compression often leads to feature degradation and reduced accuracy. To …
Facial Expression RecognitionImage CompressionImage Coding for Machines with Edge Information Learning Using Segment Anything
Image Coding for Machines (ICM) is an image compression technique for image recognition. This technique is essential due to the growing demand for image recognition AI. In this paper, we propose a method for ICM that foc…
Image CompressionVideo CompressionIdentity Preserving Loss for Learned Image Compression
Deep learning model inference on embedded devices is challenging due to the limited availability of computation resources. A popular alternative is to perform model inference on the cloud, which requires transmitting ima…
Image Compression