Semantic-assisted image compression
Conventional image compression methods typically aim at pixel-level consistency while ignoring the performance of downstream AI tasks.To solve this problem, this paper proposes a Semantic-Assisted Image Compression method (SAIC), which can maintain semantic-level consistency to enable high performance of downstream AI tasks.To this end, we train the compression network using semantic-level loss function. In particular, semantic-level loss is measured using gradient-based semantic weights mechanism (GSW). GSW directly consider downstream AI tasks' perceptual results. Then, this paper proposes a semantic-level distortion evaluation metric to quantify the amount of semantic information retained during the compression process. Experimental results show that the proposed SAIC method can retain more semantic-level information and achieve better performance of downstream AI tasks compared to the traditional deep learning-based method and the advanced perceptual method at the same compression ratio.
Code (0)
등록된 구현이 없습니다.
Tasks
Image CompressionSimilar Papers 제목 키워드 기반
SEEC: Segmentation-Assisted Multi-Entropy Models for Learned Lossless Image Compression
Recently, learned image compression has attracted considerable attention due to its superior performance over traditional methods. However, most existing approaches employ a single entropy model to estimate the probabili…
Semantic SegmentationImage CompressionMap-Assisted Remote-Sensing Image Compression at Extremely Low Bitrates
Remote-sensing (RS) image compression at extremely low bitrates has always been a challenging task in practical scenarios like edge device storage and narrow bandwidth transmission. Generative models including VAEs and G…
Image CompressionDNN-Driven Compressive Offloading for Edge-Assisted Semantic Video Segmentation
Deep learning has shown impressive performance in semantic segmentation, but it is still unaffordable for resource-constrained mobile devices. While offloading computation tasks is promising, the high traffic demands ove…
Optical Flow EstimationSegmentationSemantic SegmentationSensitivity+2Large Generative Model Assisted 3D Semantic Communication
Semantic Communication (SC) is a novel paradigm for data transmission in 6G. However, there are several challenges posed when performing SC in 3D scenarios: 1) 3D semantic extraction; 2) Latent semantic redundancy; and 3…
Generative Adversarial NetworkmodelNeRFSemantic Communication+1Point Cloud-Assisted Neural Image Compression
High-efficient image compression is a critical requirement. In several scenarios where multiple modalities of data are captured by different sensors, the auxiliary information from other modalities are not fully leverage…
Autonomous DrivingImage Compression