English
Related papers

Related papers: Top-down Neural Attention by Excitation Backprop

200 papers

Spatial attention has been introduced to convolutional neural networks (CNNs) for improving both their performance and interpretability in visual tasks including image classification. The essence of the spatial attention is to learn a…

Image and Video Processing · Electrical Eng. & Systems 2020-08-03 Linchuan Xu , Jun Huang , Atsushi Nitanda , Ryo Asaoka , Kenji Yamanishi

We propose an inference procedure for deep convolutional neural networks (CNNs) when partial evidence is available. Our method consists of a general feedback-based propagation approach (feedback-prop) that boosts the prediction accuracy for…

Computer Vision and Pattern Recognition · Computer Science 2018-04-02 Tianlu Wang , Kota Yamaguchi , Vicente Ordonez

Many real-world applications involve data from multiple modalities and thus exhibit the view heterogeneity. For example, user modeling on social media might leverage both the topology of the underlying social network and the content of the…

Machine Learning · Computer Science 2021-02-16 Lecheng Zheng , Yu Cheng , Hongxia Yang , Nan Cao , Jingrui He

We provide a probabilistic interpretation of attention and show that the standard dot-product attention in transformers is a special case of Maximum A Posteriori (MAP) inference. The proposed approach suggests the use of Expectation…

Computer Vision and Pattern Recognition · Computer Science 2021-07-06 Prasad Gabbur , Manjot Bilkhu , Javier Movellan

Convolutional Neural Networks (CNNs) were recently shown to provide state-of-the-art results for object category viewpoint estimation. However different ways of formulating this problem have been proposed and the competing approaches have…

Computer Vision and Pattern Recognition · Computer Science 2016-09-14 Francisco Massa , Renaud Marlet , Mathieu Aubry

Despite the widespread adoption of Backpropagation algorithm-based Deep Neural Networks, the biological infeasibility of the BP algorithm could potentially limit the evolution of new DNN models. To find a biologically plausible algorithm to…

Neural and Evolutionary Computing · Computer Science 2024-02-29 Jian-Hui Chen , Cheng-Lin Liu , Zuoren Wang

Image search can be tackled using deep features from pre-trained Convolutional Neural Networks (CNN). The feature map from the last convolutional layer of a CNN encodes descriptive information from which a discriminative global descriptor…

Computer Vision and Pattern Recognition · Computer Science 2021-06-11 J. I. Forcen , Miguel Pagola , Edurne Barrenechea , Humberto Bustince

Conditional image modeling based on textual descriptions is a relatively new domain in unsupervised learning. Previous approaches use a latent variable model and generative adversarial networks. While the formers are approximated by using…

Computer Vision and Pattern Recognition · Computer Science 2020-01-22 Tehseen Zia , Shahan Arif , Shakeeb Murtaza , Mirza Ahsan Ullah

Top-down information plays a central role in human perception, but plays relatively little role in many current state-of-the-art deep networks, such as Convolutional Neural Networks (CNNs). This work seeks to explore a path by which…

Neural and Evolutionary Computing · Computer Science 2015-11-24 Patrick W. Gallagher , Shuai Tang , Zhuowen Tu

While the use of bottom-up local operators in convolutional neural networks (CNNs) matches well some of the statistics of natural images, it may also prevent such models from capturing contextual long-range feature interactions. In this…

Computer Vision and Pattern Recognition · Computer Science 2019-01-15 Jie Hu , Li Shen , Samuel Albanie , Gang Sun , Andrea Vedaldi

Convolutional Neural Networks (CNNs) excel in local spatial pattern recognition. For many vision tasks, such as object recognition and segmentation, salient information is also present outside CNN's kernel boundaries. However, CNNs struggle…

Computer Vision and Pattern Recognition · Computer Science 2023-11-22 Farzad Salajegheh , Nader Asadi , Soroush Saryazdi , Sudhir Mudur

Attention mechanisms have recently been introduced in deep learning for various tasks in natural language processing and computer vision. But despite their popularity, the "correctness" of the implicitly-learned attention maps has only been…

Computer Vision and Pattern Recognition · Computer Science 2016-11-24 Chenxi Liu , Junhua Mao , Fei Sha , Alan Yuille

Transformers have achieved significant success across various domains, relying on self-attention to capture dependencies. However, the standard first-order attention mechanism is often limited by a low-rank bottleneck, struggling to capture…

Computation and Language · Computer Science 2025-12-05 Hanting Chen , Chong Zhu , Kai Han , Yuchuan Tian , Yuchen Liang , Tianyu Guo , Xinghao Chen , Dacheng Tao , Yunhe Wang

While convolutional neural networks have gained impressive success recently in solving structured prediction problems such as semantic segmentation, it remains a challenge to differentiate individual object instances in the scene. Instance…

Machine Learning · Computer Science 2017-07-14 Mengye Ren , Richard S. Zemel

Deep models are state-of-the-art for many vision tasks including video action recognition and video captioning. Models are trained to caption or classify activity in videos, but little is known about the evidence used to make such…

Computer Vision and Pattern Recognition · Computer Science 2018-03-09 Sarah Adel Bargal , Andrea Zunino , Donghyun Kim , Jianming Zhang , Vittorio Murino , Stan Sclaroff

High-level visual brain regions contain subareas in which neurons appear to respond more strongly to examples of a particular semantic category, like faces or bodies, rather than objects. However, recent work has shown that while this…

Computer Vision and Pattern Recognition · Computer Science 2024-10-29 Alexander Lappe , Anna Bognár , Ghazaleh Ghamkhari Nejad , Albert Mukovskiy , Lucas Martini , Martin A. Giese , Rufin Vogels

This paper proposes a weakly- and self-supervised deep convolutional neural network (WSSDCNN) for content-aware image retargeting. Our network takes a source image and a target aspect ratio, and then directly outputs a retargeted image.…

Computer Vision and Pattern Recognition · Computer Science 2019-02-18 Donghyeon Cho , Jinsun Park , Tae-Hyun Oh , Yu-Wing Tai , In So Kweon

The use of attention models for automated image captioning has enabled many systems to produce accurate and meaningful descriptions for images. Over the years, many novel approaches have been proposed to enhance the attention process using…

Computer Vision and Pattern Recognition · Computer Science 2022-04-18 Murad Popattia , Muhammad Rafi , Rizwan Qureshi , Shah Nawaz

This paper proposes a new method, that we call VisualBackProp, for visualizing which sets of pixels of the input image contribute most to the predictions made by the convolutional neural network (CNN). The method heavily hinges on exploring…

Computer Vision and Pattern Recognition · Computer Science 2017-05-23 Mariusz Bojarski , Anna Choromanska , Krzysztof Choromanski , Bernhard Firner , Larry Jackel , Urs Muller , Karol Zieba

Typically, objects with the same semantics are not always prominent in images containing different backgrounds. Motivated by this observation that accurately salient object detection is related to both foreground and background, we proposed…

Computer Vision and Pattern Recognition · Computer Science 2019-09-19 Changqun Xia , Jia Li , Jinming Su , Yonghong Tian