相关论文: IQ-LUT: interpolated and quantized LUT for efficie…

We present an effective and efficient approach for low-light image enhancement, named Lookup Table Global Curve Estimation (LUT-GCE). In contrast to existing curve-based methods with pixel-wise adjustment, we propose to estimate a global…

Retrieval augmented models are becoming increasingly popular for computer vision tasks after their recent success in NLP problems. The goal is to enhance the recognition capabilities of the model by retrieving similar examples for the…

Large Language Models (LLMs) with multimodal capabilities have revolutionized vision-language tasks, but their deployment often requires huge memory and computational resources. While post-training quantization (PTQ) has successfully…

Vision Transformers have been tremendously successful in computer vision tasks. However, their large computational, memory, and energy demands are a challenge for edge inference on FPGAs -- a field that has seen a recent surge in demand. We…

We propose a novel framework for uncertainty quantification via information bottleneck (IB-UQ) for scientific machine learning tasks, including deep neural network (DNN) regression and neural operator learning (DeepONet). Specifically, we…

Neural networks have been widely used, and most networks achieve excellent performance by stacking certain types of basic units. Compared to increasing the depth and width of the network, designing more effective basic units has become an…

Recently, learned image compression methods have been actively studied. Among them, entropy-minimization based approaches have achieved superior results compared to conventional image codecs such as BPG and JPEG2000. However, the quality…

Contemporary Low-Light Image Enhancement (LLIE) techniques have made notable advancements in preserving image details and enhancing contrast, achieving commendable results on specific datasets. Nevertheless, these approaches encounter…

Large-scale image datasets are fundamental to deep learning, but their high storage demands pose challenges for deployment in resource-constrained environments. While existing approaches reduce dataset size by discarding samples, they often…

In this paper, we present Q# implementations for arbitrary single-variabled fixed-point arithmetic operations for a gate-based quantum computer based on lookup tables (LUTs). In general, this is an inefficent way of implementing a function…

Deep neural networks (DNNs) are state-of-the-art algorithms for multiple applications, spanning from image classification to speech recognition. While providing excellent accuracy, they often have enormous compute and memory requirements.…

Recently, deep convolutional neural networks (CNNs) have been demonstrated remarkable progress on single image super-resolution. However, as the depth and width of the networks increase, CNN-based super-resolution methods have been faced…

Convolutional Neural Networks (CNNs) have advanced significantly in visual representation learning and recognition. However, they face notable challenges in performance and computational efficiency when dealing with real-world, multi-scale…

Deploying deep models on embedded devices has been a challenging problem since the great success of deep learning based networks. Fixed-point networks, which represent their data with low bits fixed-point and thus give remarkable savings on…

Image prefiltering with just noticeable distortion (JND) improves coding efficiency in a visual lossless way by filtering the perceptually redundant information prior to compression. However, real JND cannot be well modeled with inaccurate…

Large language models (LLMs) have significantly advanced the natural language processing paradigm but impose substantial demands on memory and computational resources. Quantization is one of the most effective ways to reduce memory…

Dataset Condensation (DC) distills knowledge from large datasets into smaller ones, accelerating training and reducing storage requirements. However, despite notable progress, prior methods have largely overlooked the potential of…

The integral image, an intermediate image representation, has found extensive use in multi-scale local feature detection algorithms, such as Speeded-Up Robust Features (SURF), allowing fast computation of rectangular features at constant…

Standard deep neural network inference involves the computation of interleaved linear maps and nonlinear activation functions. Prior work for ultra-low latency implementations has hardcoded these operations inside FPGA lookup tables (LUTs).…

CNNs have been widely applied for medical image analysis. However, limited memory capacity is one of the most common drawbacks of processing high-resolution 3D volumetric data. 3D volumes are usually cropped or downsized first before…