Related papers: LDA-AQU: Adaptive Query-guided Upsampling via Loca…

Unsupervised domain adaptation (UDA) methods have been broadly utilized to improve the models' adaptation ability in general computer vision. However, different from the natural images, there exist huge semantic gaps for the nuclei from…

Photoacoustic imaging (PAI) is a non-invasive imaging modality that detects the ultrasound signal generated from tissue with light excitation. Photoacoustic computed tomography (PACT) uses unfocused large-area light to illuminate the target…

Pruning is a promising approach to compress deep learning models in order to deploy them on resource-constrained edge devices. However, many existing pruning solutions are based on unstructured pruning, which yields models that cannot…

2D convolutional neural networks (CNNs) have attracted significant attention for hyperspectral image super-resolution tasks. However, a key limitation is their reliance on local neighborhoods, which leads to a lack of global contextual…

In deep learning tasks, the learning rate determines the update step size in each iteration, which plays a critical role in gradient-based optimization. However, the determination of the appropriate learning rate in practice typically…

Visual Question Answering (VQA) models employ attention mechanisms to discover image locations that are most relevant for answering a specific question. For this purpose, several multimodal fusion strategies have been proposed, ranging from…

We propose a new attention mechanism for neural based question answering, which depends on varying granularities of the input. Previous work focused on augmenting recurrent neural networks with simple attention mechanisms which are a…

Prior Unsupervised Domain Adaptation (UDA) methods often aim to train a domain-invariant feature extractor, which may hinder the model from learning sufficiently discriminative features. To tackle this, a line of works based on prompt…

Convolutional neural networks (CNNs) have been not only widespread but also achieved noticeable results on numerous applications including image classification, restoration, and generation. Although the weight-sharing property of…

The quadratic complexity of self attention in Transformer based LLMs renders long context inference prohibitively expensive. While Sliding Window Attention (SWA), the simplest sparse attention pattern, offers a linear complexity…

In this paper, we propose a residual non-local attention network for high-quality image restoration. Without considering the uneven distribution of information in the corrupted images, previous methods are restricted by local convolutional…

The self-attention mechanism, while foundational to modern Transformer architectures, suffers from a critical inefficiency: it frequently allocates substantial attention to redundant or noisy context. Differential Attention addressed this…

Quantitative susceptibility mapping (QSM) is a post-processing technique for deriving tissue magnetic susceptibility distribution from MRI phase measurements. Deep learning (DL) algorithms hold great potential for solving the ill-posed QSM…

Distantly supervised relation extraction intrinsically suffers from noisy labels due to the strong assumption of distant supervision. Most prior works adopt a selective attention mechanism over sentences in a bag to denoise from wrongly…

Deep features extracted from certain layers of a pre-trained deep model show superior performance over the conventional hand-crafted features. Compared with fine-tuning or linear probing that can explore diverse augmentations, \eg, random…

The Large Vision-Language Model (LVLM) integrates computer vision and natural language processing techniques, offering substantial application potential. However, these models demand extensive resources during inference. Adaptive attention…

Recent work has made clear that the residual pathway is not mere optimization plumbing; it is part of the model's representational machinery. We agree, but argue that the cleanest way to organize this design space is through a two-axis view…

Deep Convolutional features extracted from a comprehensive labeled dataset, contain substantial representations which could be effectively used in a new domain. Despite the fact that generic features achieved good results in many visual…

Seeing clearly with high resolution is a foundation of Large Multimodal Models (LMMs), which has been proven to be vital for visual perception and reasoning. Existing works usually employ a straightforward resolution upscaling method, where…

We present a deep neural network-based approach to image quality assessment (IQA). The network is trained end-to-end and comprises ten convolutional layers and five pooling layers for feature extraction, and two fully connected layers for…