Related papers: Multiscale Feature Importance-based Bit Allocation…
Image Coding for Machines (ICM) focuses on optimizing image compression for AI-driven analysis rather than human perception. Existing ICM frameworks often rely on separate codecs for specific tasks, leading to significant storage…
Learning-based lossy image compression usually involves the joint optimization of rate-distortion performance. Most existing methods adopt spatially invariant bit length allocation and incorporate discrete entropy approximation to constrain…
Mamba-based vision models have gained extensive attention as a result of being computationally more efficient than attention-based models. However, spatial redundancy still exists in these models, represented by token and block redundancy.…
Ground-based cloud image segmentation is a critical research domain for photovoltaic power forecasting. Current deep learning approaches primarily focus on encoder-decoder architectural refinements. However, existing methodologies exhibit…
Compressing neural networks by quantizing model parameters offers useful trade-off between performance and efficiency. Methods like quantization-aware training and post-training quantization strive to maintain the downstream performance of…
Machine learning is a powerful tool for extracting valuable information and making various predictions from diverse datasets. Traditional machine learning algorithms rely on well-defined input and output variables; however, there are…
Bag-based Multiple Instance Learning (MIL) approaches have emerged as the mainstream methodology for Whole Slide Image (WSI) classification. However, most existing methods adopt a segmented training strategy, which first extracts features…
Content-based image retrieval (CBIR) of medical images is a crucial task that can contribute to a more reliable diagnosis if applied to big data. Recent advances in feature extraction and classification have enormously improved CBIR results…
Existing RGB-Event detection methods process the low-information regions of both modalities (background in images and non-event regions in event data) uniformly during feature extraction and fusion, resulting in high computational costs and…
Vision Transformers have achieved impressive performance in video classification, while suffering from the quadratic complexity caused by the Softmax attention mechanism. Some studies alleviate the computational costs by reducing the number…
Image Coding for Machines (ICM) has become increasingly important with the rapid integration of computer vision technology into real-world applications. However, most neural network-based ICM frameworks operate at a fixed rate, thus…
Motion estimation is the most critical process in video coding systems. First of all, it has a definitive impact on the rate-distortion performance given by the video encoder. Secondly, it is the most computationally intensive process…
Large language models (LLMs) have demonstrated remarkable performance across various language tasks, but their widespread deployment is impeded by their large size and high computational costs. Structural pruning is a prevailing technique…
Variable-rate mechanism has improved the flexibility and efficiency of learning-based image compression that trains multiple models for different rate-distortion tradeoffs. One of the most common approaches for variable-rate is to…
State space models (SSMs) like Mamba have recently attracted much attention. Compared to Transformer-based large language models (LLMs), Mamba achieves linear computation complexity with the sequence length and demonstrates superior…
Machine unlearning, driven by privacy regulations and the "right to be forgotten", is increasingly needed at the edge, yet server-centric or retraining-heavy methods are impractical under tight computation and energy budgets. We present…
Vision Mamba has emerged as a strong competitor to Vision Transformers (ViTs) due to its ability to efficiently capture long-range dependencies with linear computational complexity. While token reduction, an effective compression technique…
Efficient model inference is an important and practical issue in the deployment of deep neural network on resource constraint platforms. Network quantization addresses this problem effectively by leveraging low-bit representation and…
Cross-view geo-localization aims to determine the geographical location of a query image by matching it against a gallery of images. This task is challenging due to the significant appearance variations of objects observed from variable…
We present the Finite Element Method (FEM) for the numerical solution of the multidimensional coefficient inverse problem (MCIP) in two dimensions. This method is used for explicit reconstruction of the coefficient in the hyperbolic…