Q-LIC: Quantizing Learned Image Compression with Channel Splitting
Learned image compression (LIC) has reached a comparable coding gain with traditional hand-crafted methods such as VVC intra. However, the large network complexity prohibits the usage of LIC on resource-limited embedded systems. Network quantization is an efficient way to reduce the network burden. This paper presents a quantized LIC (QLIC) by channel splitting. First, we explore that the influence of quantization error to the reconstruction error is different for various channels. Second, we split the channels whose quantization has larger influence to the reconstruction error. After the splitting, the dynamic range of channels is reduced so that the quantization error can be reduced. Finally, we prune several channels to keep the number of overall channels as origin. By using the proposal, in the case of 8-bit quantization for weight and activation of both main and hyper path, we can reduce the BD-rate by 0.61%-4.74% compared with the previous QLIC. Besides, we can reach better coding gain compared with the state-of-the-art network quantization method when quantizing MS-SSIM models. Moreover, our proposal can be combined with other network quantization methods to further improve the coding gain. The moderate coding loss caused by the quantization validates the feasibility of the hardware implementation for QLIC in the future.
Code (0)
등록된 구현이 없습니다.
Tasks
Image CompressionMS-SSIMQuantizationSSIMSimilar Papers 제목 키워드 기반
Variable-Rate Learned Image Compression with Multi-Objective Optimization and Quantization-Reconstruction Offsets
Achieving successful variable bitrate compression with computationally simple algorithms from a single end-to-end learned image or video compression model remains a challenge. Many approaches have been proposed, includin…
Image CompressionQuantizationVideo CompressionEnd-to-End Learned Image Compression with Quantized Weights and Activations
End-to-end Learned image compression (LIC) has reached the traditional hand-crafted methods such as BPG (HEVC intra) in terms of the coding gain. However, the large network size prohibits the usage of LIC on resource-lim…
Image CompressionMS-SSIMQuantizationSSIMImproving Neural Network Quantization without Retraining using Outlier Channel Splitting
Quantization can improve the execution latency and energy efficiency of neural networks on both commodity GPUs and specialized accelerators. The majority of existing literature focuses on training quantized DNNs, while t…
Language ModelingLanguage ModellingNeural Network CompressionQuantizationQuantized Decoder in Learned Image Compression for Deterministic Reconstruction
Learned image compression has a problem of non-bit-exact reconstruction due to different calculations of floating point arithmetic on different devices. This paper shows a method to achieve a deterministic reconstructed …
DecoderImage CompressionQuantizationBottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems
The emergence of various intelligent mobile applications demands the deployment of powerful deep learning models at resource-constrained mobile devices. The device-edge co-inference framework provides a promising solutio…
DecoderEdge-computingFeature Compression