Expanded Adaptive Scaling Normalization for End to End Image Compression
Recently, learning-based image compression methods that utilize convolutional neural layers have been developed rapidly. Rescaling modules such as batch normalization which are often used in convolutional neural networks do not operate adaptively for the various inputs. Therefore, Generalized Divisible Normalization(GDN) has been widely used in image compression to rescale the input features adaptively across both spatial and channel axes. However, the representation power or degree of freedom of GDN is severely limited. Additionally, GDN cannot consider the spatial correlation of an image. To handle the limitations of GDN, we construct an expanded form of the adaptive scaling module, named Expanded Adaptive Scaling Normalization(EASN). First, we exploit the swish function to increase the representation ability. Then, we increase the receptive field to make the adaptive rescaling module consider the spatial correlation. Furthermore, we introduce an input mapping function to give the module a higher degree of freedom. We demonstrate how our EASN works in an image compression network using the visualization results of the feature map, and we conduct extensive experiments to show that our EASN increases the rate-distortion performance remarkably, and even outperforms the VVC intra at a high bit rate.
Code (1)
Tasks
Image CompressionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Joint Degradation-Aware Arbitrary-Scale Super-Resolution for Variable-Rate Extreme Image Compression
Recent diffusion-based extreme image compression methods have demonstrated remarkable performance at ultra-low bitrates. However, most approaches require training separate diffusion models for each target bitrate, result…
Image CompressionNormalization of Non-Standard Words in Croatian Texts
This paper presents text normalization which is an integral part of any text-to-speech synthesis system. Text normalization is a set of methods with a task to write non-standard words, like numbers, dates, times, abbrevi…
FormGeneral ClassificationSpeech SynthesisText Normalization+3Weight Rescaling: Effective and Robust Regularization for Deep Neural Networks with Batch Normalization
Weight decay is often used to ensure good generalization in the training practice of deep neural networks with batch normalization (BN-DNNs), where some convolution layers are invariant to weight rescaling due to the nor…
Crowd Countingimage-classificationImage Classificationobject-detection+2Adversarially Adaptive Normalization for Single Domain Generalization
Single domain generalization aims to learn a model that performs well on many unseen domains with only one domain data for training. Existing works focus on studying the adversarial domain augmentation (ADA) to improve t…
Domain GeneralizationCompact Neural Networks based on the Multiscale Entanglement Renormalization Ansatz
This paper demonstrates a method for tensorizing neural networks based upon an efficient way of approximating scale invariant quantum states, the Multi-scale Entanglement Renormalization Ansatz (MERA). We employ MERA as …