中文
相关论文

相关论文: Learning to ignore: rethinking attention in CNNs

200 篇论文

Convolutional neural networks (CNNs) define the current state-of-the-art for image recognition. With their emerging popularity, especially for critical applications like medical image analysis or self-driving cars, confirmability is…

计算机视觉与模式识别 · 计算机科学 2018-01-08 Keyang Zhou , Bernhard Kainz

Supervised learning of convolutional neural networks (CNNs) can require very large amounts of labeled data. Labeling thousands or millions of training examples can be extremely time consuming and costly. One direction towards addressing…

计算机视觉与模式识别 · 计算机科学 2017-07-27 Amir Ghaderi , Vassilis Athitsos

Convolutional Neural Networks (CNNs) provide excellent performance when used for image classification. The classical method of training CNNs is by labeling images in a supervised manner as in "input image belongs to this label" (Positive…

机器学习 · 计算机科学 2019-08-21 Youngdong Kim , Junho Yim , Juseung Yun , Junmo Kim

The splendid success of convolutional neural networks (CNNs) in computer vision is largely attributable to the availability of massive annotated datasets, such as ImageNet and Places. However, in medical imaging, it is challenging to create…

机器学习 · 计算机科学 2021-04-13 Zongwei Zhou , Jae Y. Shin , Suryakanth R. Gurudu , Michael B. Gotway , Jianming Liang

We address the problem of anomaly detection, that is, detecting anomalous events in a video sequence. Anomaly detection methods based on convolutional neural networks (CNNs) typically leverage proxy tasks, such as reconstructing input video…

计算机视觉与模式识别 · 计算机科学 2020-03-31 Hyunjong Park , Jongyoun Noh , Bumsub Ham

Scene parsing is an important and challenging prob- lem in computer vision. It requires labeling each pixel in an image with the category it belongs to. Tradition- ally, it has been approached with hand-engineered features from color…

机器学习 · 统计学 2014-11-18 Rahul Mohan

Event recognition from still images is of great importance for image understanding. However, compared with event recognition in videos, there are much fewer research works on event recognition in images. This paper addresses the issue of…

计算机视觉与模式识别 · 计算机科学 2015-05-05 Limin Wang , Zhe Wang , Wenbin Du , Yu Qiao

Aiming at the problems that the convolutional neural networks neglect to capture the inherent attributes of natural images and extract features only in a single scale in the field of image super-resolution reconstruction, a network…

图像与视频处理 · 电气工程与系统科学 2020-04-09 Jiawen Lyn , Sen Yan

Humans rely heavily on shape information to recognize objects. Conversely, convolutional neural networks (CNNs) are biased more towards texture. This is perhaps the main reason why CNNs are vulnerable to adversarial examples. Here, we…

计算机视觉与模式识别 · 计算机科学 2021-12-08 Ali Borji

The human visual system employs a selective attention mechanism to understand the visual world in an eficient manner. In this paper, we show how computational models of this mechanism can be exploited for the computer vision application of…

计算机视觉与模式识别 · 计算机科学 2013-07-23 Samuel F. Dodge , Lina J. Karam

For image inpainting, the convolutional neural networks (CNN) in previous methods often adopt standard convolutional operator, which treats valid pixels and holes indistinguishably. As a result, they are limited in handling irregular holes…

计算机视觉与模式识别 · 计算机科学 2021-04-27 Dongsheng Wang , Chaohao Xie , Shaohui Liu , Zhenxing Niu , Wangmeng Zuo

An important goal in visual recognition is to devise image representations that are invariant to particular transformations. In this paper, we address this goal with a new type of convolutional neural network (CNN) whose invariance is…

计算机视觉与模式识别 · 计算机科学 2015-01-08 Julien Mairal , Piotr Koniusz , Zaid Harchaoui , Cordelia Schmid

In this paper, we present an approach based on convolutional neural networks (CNNs) for facial expression recognition in a difficult setting with severe occlusions. More specifically, our task is to recognize the facial expression of a…

计算机视觉与模式识别 · 计算机科学 2019-11-13 Mariana-Iuliana Georgescu , Radu Tudor Ionescu

When humans describe a visual scene, they do not process the entire image uniformly; instead, they selectively fixate on regions relevant to their intended description. In contrast, current multimodal large language models (MLLMs) attend to…

计算机视觉与模式识别 · 计算机科学 2026-05-14 Junha Song , Byeongho Heo , Geonmo Gu , Jaegul Choo , Dongyoon Han , Sangdoo Yun

In recent years, learned image compression methods have demonstrated superior rate-distortion performance compared to traditional image compression methods. Recent methods utilize convolutional neural networks (CNN), variational…

计算机视觉与模式识别 · 计算机科学 2025-02-14 Priyanka Mudgal , Feng Liu

In recent years, deep learning has achieved remarkable success in the field of image restoration. However, most convolutional neural network-based methods typically focus on a single scale, neglecting the incorporation of multi-scale…

图像与视频处理 · 电气工程与系统科学 2025-02-27 Jiatao Jiang , Zhen Cui , Chunyan Xu , Jian Yang

Despite the initial belief that Convolutional Neural Networks (CNNs) are driven by shapes to perform visual recognition tasks, recent evidence suggests that texture bias in CNNs provides higher performing models when learning on large…

计算机视觉与模式识别 · 计算机科学 2020-12-25 Reza Azad , Abdur R Fayjie , Claude Kauffman , Ismail Ben Ayed , Marco Pedersoli , Jose Dolz

This paper proposes a method to modify traditional convolutional neural networks (CNNs) into interpretable CNNs, in order to clarify knowledge representations in high conv-layers of CNNs. In an interpretable CNN, each filter in a high…

计算机视觉与模式识别 · 计算机科学 2018-02-15 Quanshi Zhang , Ying Nian Wu , Song-Chun Zhu

Attention models have recently emerged as a powerful approach, demonstrating significant progress in various fields. Visualization techniques, such as class activation mapping, provide visual insights into the reasoning of convolutional…

计算机视觉与模式识别 · 计算机科学 2025-10-31 Ali Caglayan , Nevrez Imamoglu , Oguzhan Guclu , Ali Osman Serhatoglu , Ahmet Burak Can , Ryosuke Nakamura

Attention modules for Convolutional Neural Networks (CNNs) are an effective method to enhance performance on multiple computer-vision tasks. While existing methods appropriately model channel-, spatial- and self-attention, they primarily…

计算机视觉与模式识别 · 计算机科学 2022-10-24 Shantanu Jaiswal , Basura Fernando , Cheston Tan