Related papers: Nonlinear Transform Coding
Artificial intelligence (AI) has revolutionized software engineering (SE) by enhancing software development efficiency. The advent of pre-trained models (PTMs) leveraging transfer learning has significantly advanced AI for SE. However,…
In this paper, we introduce a new nonlinear optical channel equalizer based on Transformers. By leveraging parallel computation and attending directly to the memory across a sequence of symbols, we show that Transformers can be used…
In image compression, classical block-based separable transforms tend to be inefficient when image blocks contain arbitrarily shaped discontinuities. For this reason, transforms incorporating directional information are an appealing…
Recent advancements in deep learning-based image compression are notable. However, prevalent schemes that employ a serial context-adaptive entropy model to enhance rate-distortion (R-D) performance are markedly slow. Furthermore, the…
Multiple Description Coding (MDC) is an error-resilient source coding method designed for transmission over noisy channels. We present a novel MDC scheme employing a neural network based on implicit neural representation. This involves…
This paper focuses on a newly developed transparent nADPCMB MLT speech coding algorithm. Our coder first decomposes the narrowband speech signal in subbands, a non linear ADPCM scheme is then performed in each subband. The signal subband…
Contrastive Language-Image Pretraining (CLIP) excels at learning generalizable image representations but often falls short in zero-shot inference on certain downstream datasets. Test-time adaptation (TTA) mitigates this issue by adjusting…
We discuss several applications of the recently proposed combined nonlinear-condensation transformation (CNCT) for the evaluation of slowly convergent, nonalternating series. These include certain statistical distributions which are of…
Visual Transformers (VTs) are emerging as an architectural paradigm alternative to Convolutional networks (CNNs). Differently from CNNs, VTs can capture global relations between image elements and they potentially have a larger…
In this paper, we propose a new graph-based transform and illustrate its potential application to signal compression. Our approach relies on the careful design of a graph that optimizes the overall rate-distortion performance through an…
We propose a new positional encoding method for a neural network architecture called the Transformer. Unlike the standard sinusoidal positional encoding, our approach is based on solid mathematical grounds and has a guarantee of not losing…
Efficient compression of language model weights is increasingly critical as model scale and deployment grow. Yet, most existing methods rely on handcrafted transforms and heuristics, reflecting the limited understanding of weights as a data…
The ever-growing size of neural networks poses serious challenges on resource-constrained devices, such as embedded sensors. Compression algorithms that reduce their size can mitigate these problems, provided that model performance stays…
All Lossy compression algorithms employ similar compression schemes -- frequency domain transform followed by quantization and lossless encoding schemes. They target tradeoffs by quantizating high frequency data to increase compression…
Inspired by the recent advances of image super-resolution using convolutional neural network (CNN), we propose a CNN-based block up-sampling scheme for intra frame coding. A block can be down-sampled before being compressed by normal intra…
The upcoming video coding standard, Versatile Video Coding (VVC), has shown great improvement compared to its predecessor, High Efficiency Video Coding (HEVC), in terms of bitrate saving. Despite its substantial performance, compressed…
Consistency Training (CT) has recently emerged as a strong alternative to diffusion models for image generation. However, non-distillation CT often suffers from high variance and instability, motivating ongoing research into its training…
This paper studies fixed-rate randomized vector quantization under the constraint that the quantizer's output has a given fixed probability distribution. A general representation of randomized quantizers that includes the common models in…
Neural-based image and video codecs are significantly more power-efficient when weights and activations are quantized to low-precision integers. While there are general-purpose techniques for reducing quantization effects, large losses can…
Learned image compression codecs have recently achieved impressive compression performances surpassing the most efficient image coding architectures. However, most approaches are trained to minimize rate and distortion which often leads to…