相关论文: Effective Guidance for Model Attention with Simple…

The auditory attention decoding (AAD) approach was proposed to determine the identity of the attended talker in a multi-talker scenario by analyzing electroencephalography (EEG) data. Although the linear model-based method has been widely…

Face anti-spoofing plays a critical role in safeguarding facial recognition systems against presentation attacks. While existing deep learning methods show promising results, they still suffer from the lack of fine-grained annotations,…

Learning semantic correspondence between image and text is significant as it bridges the semantic gap between vision and language. The key challenge is to accurately find and correlate shared semantics in image and text. Most existing…

Neural attention has become central to many state-of-the-art models in natural language processing and related domains. Attention networks are an easy-to-train and effective method for softly simulating alignment; however, the approach does…

Convolutional neural networks (CNNs) have been shown to be state-of-the-art models for visual cortical neurons. Cortical neurons in the primary visual cortex are sensitive to contextual information mediated by extensive horizontal and…

Attention mechanisms are ubiquitous components in neural architectures applied to natural language processing. In addition to yielding gains in predictive accuracy, attention weights are often claimed to confer interpretability, purportedly…

Deep learning has emerged as a compelling solution to many NLP tasks with remarkable performances. However, due to their opacity, such models are hard to interpret and trust. Recent work on explaining deep models has introduced approaches…

Recent studies strive to incorporate various human rationales into neural networks to improve model performance, but few pay attention to the quality of the rationales. Most existing methods distribute their models' focus to…

Deep-learning-based approaches for retinal lesion segmentation often require an abundant amount of precise pixel-wise annotated data. However, coarse annotations such as circles or ellipses for outlining the lesion area can be six times…

Recently, many plug-and-play self-attention modules are proposed to enhance the model generalization by exploiting the internal information of deep convolutional neural networks (CNNs). Previous works lay an emphasis on the design of…

The performance of deep neural networks improves with more annotated data. The problem is that the budget for annotation is limited. One solution to this is active learning, where a model asks human to annotate data that it perceived as…

Diffusion Transformers dominate video generation, but the quadratic complexity of attention computation introduces substantial latency. Attention sparsity reduces computational costs by focusing on critical tokens while ignoring…

Automatic annotation of images with descriptive words is a challenging problem with vast applications in the areas of image search and retrieval. This problem can be viewed as a label-assignment problem by a classifier dealing with a very…

Accurate ground truth estimation in medical screening programs often relies on coalitions of experts and peer second opinions. Algorithms that efficiently aggregate noisy annotations can enhance screening workflows, particularly when data…

Retrieval-augmented large language models, when optimized with outcome-level rewards, can achieve strong answer accuracy on multi-hop questions. However, under noisy retrieval, models frequently suffer from "right-answer-wrong-reason…

Deep neural networks for medical image diagnosis often achieve high predictive accuracy while relying on spurious or clinically irrelevant visual cues, limiting their trustworthiness in practice. Post-hoc explanation methods are widely used…

Large annotated datasets are vital for training segmentation models, but pixel-level labeling is time-consuming, error-prone, and often requires scarce expert annotators, especially in medical imaging. In contrast, coarse annotations are…

In this paper, we build upon the weakly-supervised generation mechanism of intermediate attention maps in any convolutional neural networks and disclose the effectiveness of attention modules more straightforwardly to fully exploit their…

Radar is an inevitable part of the perception sensor set for autonomous driving functions. It plays a gap-filling role to complement the shortcomings of other sensors in diverse scenarios and weather conditions. In this paper, we propose a…

The electronic health record (EHR) contains a large amount of multi-dimensional and unstructured clinical data of significant operational and research value. Distinguished from previous studies, our approach embraces a double-annotated…