Related papers: A Multi-Stage Optimization Framework for Deploying…
Learnable Image Compression (LIC) has shown the potential to outperform standardized video codecs in RD efficiency, prompting the research for hardware-friendly implementations. Most existing LIC hardware implementations prioritize latency…
Prevailing quantization techniques in Learned Image Compression (LIC) typically employ a static, uniform bit-width across all layers, failing to adapt to the highly diverse data distributions and sensitivity characteristics inherent in LIC…
Quantizing a floating-point neural network to its fixed-point representation is crucial for Learned Image Compression (LIC) because it improves decoding consistency for interoperability and reduces space-time complexity for implementation.…
Despite its improvements in coding performance compared to traditional codecs, Learned Image Compression (LIC) suffers from large computational costs for storage and deployment. Model quantization offers an effective solution to reduce the…
Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency,…
Quantization-Aware Training (QAT), combined with Knowledge Distillation (KD), holds immense promise for compressing models for edge deployment. However, joint optimization for precision-sensitive image restoration (IR) to recover visual…
Deep Neural Networks (DNNs) have shown significant advantages in a wide variety of domains. However, DNNs are becoming computationally intensive and energy hungry at an exponential pace, while at the same time, there is a vast demand for…
Learned image compression (LIC) has gained traction as an effective solution for image storage and transmission in recent years. However, existing LIC methods are redundant in latent representation due to limitations in capturing…
With the tremendous success of deep learning, there exists imminent need to deploy deep learning models onto edge devices. To tackle the limited computing and storage resources in edge devices, model compression techniques have been widely…
In recent years, learned image compression (LIC) methods have achieved significant performance improvements. However, obtaining a more compact latent representation and reducing the impact of quantization errors remain key challenges in the…
The compression of deep learning models is of fundamental importance in deploying such models to edge devices. The selection of compression parameters can be automated to meet changes in the hardware platform and application using…
Deploying transformer-based neural networks on resource-constrained edge devices presents a significant challenge. This challenge is often addressed through various techniques, such as low-rank approximation and mixed-precision…
Retrieval-Augmented Generation enhances language models by retrieving relevant information from external knowledge bases, relying on high-dimensional vector embeddings typically stored in float32 precision. However, storing these embeddings…
Image compression under ultra-low bitrates remains challenging for both conventional learned image compression (LIC) and generative vector-quantized (VQ) modeling. Conventional LIC suffers from severe artifacts due to heavy quantization,…
Learned image compression (LIC) using deep learning architectures has seen significant advancements, yet standard rate-distortion (R-D) optimization often encounters imbalanced updates due to diverse gradients of the rate and distortion…
Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency,…
Learned image compression methods generally optimize a rate-distortion loss, trading off improvements in visual distortion for added bitrate. Increasingly, however, compressed imagery is used as an input to deep learning networks for…
Post-training quantization (PTQ) is essential for deploying large diffusion transformers on resource-constrained hardware, but aggressive 4-bit quantization significantly degrades generative performance. Low-rank approximation methods have…
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…
Recent advancements in learned image compression (LIC) methods have demonstrated superior performance over traditional hand-crafted codecs. These learning-based methods often employ convolutional neural networks (CNNs) or Transformer-based…