Related papers: Large coordinate kernel attention network for ligh…

Dynamic convolution enhances model capacity by adaptively combining multiple kernels, yet faces critical trade-offs: prior works either (1) incur significant parameter overhead by scaling kernel numbers linearly, (2) compromise inference…

Convolutional neural networks use regular quadrilateral convolution kernels to extract features. Since the number of parameters increases quadratically with the size of the convolution kernel, many popular models use small convolution…

Multiple Kernel Learning, or MKL, extends (kernelized) SVM by attempting to learn not only a classifier/regressor but also the best kernel for the training task, usually from a combination of existing kernel functions. Most MKL methods seek…

Single-Image Super-Resolution (SISR) aims to reconstruct a High-Resolution (HR) image from a Low-Resolution (LR) observation, a fundamentally ill-posed problem where high-frequency details are severely degraded at large upscaling factors.…

Recently, some large kernel convnets strike back with appealing performance and efficiency. However, given the square complexity of convolution, scaling up kernels can bring about an enormous amount of parameters and the proliferated…

Convolutional neural network (CNN) based image enhancement methods such as super-resolution and detail enhancement have achieved remarkable performances. However, amounts of operations including convolution and parameters within the…

Visual encoding constitutes the basis of large multimodal models (LMMs) in understanding the visual world. Conventional LMMs process images in fixed sizes and limited resolutions, while recent explorations in this direction are limited in…

A unified deep neural network, denoted the multi-scale CNN (MS-CNN), is proposed for fast multi-scale object detection. The MS-CNN consists of a proposal sub-network and a detection sub-network. In the proposal sub-network, detection is…

Object detection has made substantial progress in the last decade, due to the capability of convolution in extracting local context of objects. However, the scales of objects are diverse and current convolution can only process single-scale…

Transformer-based Large Language Models (LLMs) have exhibited remarkable success in extensive tasks primarily attributed to self-attention mechanism, which requires a token to consider all preceding tokens as its context to compute…

Transformers have shown great potential in various computer vision tasks. By borrowing design concepts from transformers, many studies revolutionized CNNs and showed remarkable results. This paper falls in this line of studies.…

Despite the impressive representation capacity of vision transformer models, current light-weight vision transformer models still suffer from inconsistent and incorrect dense predictions at local regions. We suspect that the power of their…

Visual Question Answering (VQA) requires a fine-grained and simultaneous understanding of both the visual content of images and the textual content of questions. Therefore, designing an effective `co-attention' model to associate key words…

Single image super resolution is of great importance as a low-level computer vision task. Recent approaches with deep convolutional neural networks have achieved im-pressive performance. However, existing architectures have limitations due…

LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…

Convolution neural networks (CNNs) based methods have dominated the low-light image enhancement tasks due to their outstanding performance. However, the convolution operation is based on a local sliding window mechanism, which is difficult…

Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and contribute remarkable progress. However, most of the existing CNNs-based SISR methods do not adequately explore…

Despite the recent progress in light field super-resolution (LFSR) achieved by convolutional neural networks, the correlation information of light field (LF) images has not been sufficiently studied and exploited due to the complexity of 4D…

Accurate polyp segmentation is crucial for the early detection and prevention of colorectal cancer. However, the existing polyp detection methods sometimes ignore multi-directional features and drastic changes in scale. To address these…

Convolutional neural networks (CNNs) have achieved great success on grid-like data such as images, but face tremendous challenges in learning from more generic data such as graphs. In CNNs, the trainable local filters enable the automatic…