Related papers: Image Compression with Product Quantized Masked Im…
The increasing size of generative Pre-trained Language Models (PLMs) has greatly increased the demand for model compression. Despite various methods to compress BERT or its variants, there are few attempts to compress generative PLMs, and…
Video matting is crucial for applications such as film production and virtual reality, yet deploying its computationally intensive models on resource-constrained devices presents challenges. Quantization is a key technique for model…
Vision Language Models (VLMs) are central to Visual Question Answering (VQA) systems and are typically deployed in the cloud due to their high computational demands. However, this cloud-only approach underutilizes edge computational…
We propose DiffQ a differentiable method for model compression for quantizing model parameters without gradient approximations (e.g., Straight Through Estimator). We suggest adding independent pseudo quantization noise to model parameters…
Perceptual image compression has shown strong potential for producing visually appealing results at low bitrates, surpassing classical standards and pixel-wise distortion-oriented neural methods. However, existing methods typically improve…
Model quantization enables the deployment of deep neural networks under resource-constrained devices. Vector quantization aims at reducing the model size by indexing model weights with full-precision embeddings, i.e., codewords, while the…
Cutting-edge research in facial expression recognition (FER) currently favors the utilization of convolutional neural networks (CNNs) backbone which is supervisedly pre-trained on face recognition datasets for feature extraction. However,…
The exponential growth of visual data in digital communications has intensified the need for efficient compression techniques that balance rate-distortion performance with computational feasibility. While recent neural compression…
Recently, vision transformers (ViTs) have superseded convolutional neural networks in numerous applications, including classification, detection, and segmentation. However, the high computational requirements of ViTs hinder their widespread…
Masked Image Modeling (MIM) has emerged as a promising method for deriving visual representations from unlabeled image data by predicting missing pixels from masked portions of images. It excels in region-aware learning and provides strong…
Diffusion models excel in image generation but are computational and resource-intensive due to their reliance on iterative Markov chain processes, leading to error accumulation and limiting the effectiveness of naive compression techniques.…
Image compression aims to reduce the information redundancy in images. Most existing neural image compression methods rely on side information from hyperprior or context models to eliminate spatial redundancy, but rarely address the channel…
This paper presents variable bitrate lossy image compression using a VAE-based neural network. An adaptable image quality adjustment strategy is proposed. The key innovation involves adeptly adjusting the input scale exclusively during the…
Diffusion models have achieved great success in image synthesis through iterative noise estimation using deep neural networks. However, the slow inference, high memory consumption, and computation intensity of the noise estimation model…
In this paper, we present our image compression framework designed for CLIC 2020 competition. Our method is based on Variational AutoEncoder (VAE) architecture which is strengthened with residual structures. In short, we make three…
Multi-frame video enhancement tasks aim to improve the spatial and temporal resolution and quality of video sequences by leveraging temporal information from multiple frames, which are widely used in streaming video processing,…
As neural networks gain widespread adoption in embedded devices, there is a need for model compression techniques to facilitate deployment in resource-constrained environments. Quantization is one of the go-to methods yielding…
Post-training Neural Network (NN) model compression is an attractive approach for deploying large, memory-consuming models on devices with limited memory resources. In this study, we investigate the rate-distortion tradeoff for NN model…
For neural video codec, it is critical, yet challenging, to design an efficient entropy model which can accurately predict the probability distribution of the quantized latent representation. However, most existing video codecs directly use…
Quantum image representation (QIR) is a key challenge in quantum image processing (QIP) due to the large number of pixels in images, which increases the need for quantum gates and qubits. However, current quantum systems face limitations in…