Related papers: FreConv: Frequency Branch-and-Integration Convolut…

Reconstructing natural images from functional magnetic resonance imaging (fMRI) data remains a core challenge in natural decoding due to the mismatch between the richness of visual stimuli and the noisy, low resolution nature of fMRI…

In recent years, crowd counting, a technique for predicting the number of people in an image, becomes a challenging task in computer vision. In this paper, we propose a cross-column feature fusion network to solve the problem of information…

By optimizing the rate-distortion-realism trade-off, generative image compression approaches produce detailed, realistic images instead of the only sharp-looking reconstructions produced by rate-distortion-optimized models. In this paper,…

Deep 3-dimensional (3D) Convolutional Network (ConvNet) has shown promising performance on video recognition tasks because of its powerful spatio-temporal information fusion ability. However, the extremely intensive requirements on memory…

Conventional neural architectures for sequential data present important limitations. Recurrent networks suffer from exploding and vanishing gradients, small effective memory horizons, and must be trained sequentially. Convolutional networks…

Image fusion aims to integrate complementary information across modalities to generate high-quality fused images, thereby enhancing the performance of high-level vision tasks. While global spatial modeling mechanisms show promising results,…

Convolutional neural networks (CNNs) are inherently suffering from massively redundant computation (FLOPs) due to the dense connection pattern between feature maps and convolution kernels. Recent research has investigated the sparse…

Binary neural networks (BNNs) have 1-bit weights and activations. Such networks are well suited for FPGAs, as their dominant computations are bitwise arithmetic and the memory requirement is also significantly reduced. However, compared to…

The popular VQ-VAE models reconstruct images through learning a discrete codebook but suffer from a significant issue in the rapid quality degradation of image reconstruction as the compression rate rises. One major reason is that a higher…

Transceivers used for telecommunications transmit and receive specific modulation patterns that are represented as sequences of complex numbers. Classifying modulation patterns is challenging because noise and channel impairments affect the…

Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications. However, the large model sizes of DNNs yield high demands on computation…

The interference of fluorescence signals and noise remains a significant challenge in Raman spectrum analysis, often obscuring subtle spectral features that are critical for accurate analysis. Inspired by variational methods similar to…

Cross-Domain Few-Shot Learning has witnessed great stride with the development of meta-learning. However, most existing methods pay more attention to learning domain-adaptive inductive bias (meta-knowledge) through feature-wise manipulation…

Convolutional neural networks (CNNs) have a large number of variables and hence suffer from a complexity problem for their implementation. Different methods and techniques have developed to alleviate the problem of CNN's complexity, such as…

Early exiting has become a promising approach to improving the inference efficiency of deep networks. By structuring models with multiple classifiers (exits), predictions for ``easy'' samples can be generated at earlier exits, negating the…

The increasing concerns of knowledge transfer and data privacy challenge the traditional gather-and-analyse paradigm in networks. Specifically, the intelligent orchestration of Virtual Network Functions (VNFs) requires understanding and…

Quantization for Convolutional Neural Network (CNN) has shown significant progress with the intention of reducing the cost of computation and storage with low-bitwidth data inputs. There are, however, no systematic studies on how an…

We propose neural network layers that explicitly combine frequency and image feature representations and show that they can be used as a versatile building block for reconstruction from frequency space data. Our work is motivated by the…

Graph convolution (GConv) is a widely used technique that has been demonstrated to be extremely effective for graph learning applications, most notably node categorization. On the other hand, many GConv-based models do not quantify the…

Quantization for CNN has shown significant progress with the intention of reducing the cost of computation and storage with low-bitwidth data representations. There are, however, no systematic studies on how an existing full-bitwidth…