English
Related papers

Related papers: Mean Box Pooling: A Rich Image Representation and …

200 papers

This paper proposes a novel deep subspace clustering approach which uses convolutional autoencoders to transform input images into new representations lying on a union of linear subspaces. The first contribution of our work is to insert…

Computer Vision and Pattern Recognition · Computer Science 2020-01-24 Mohsen Kheirandishfard , Fariba Zohrizadeh , Farhad Kamangar

Recently, many researches employ middle-layer output of convolutional neural network models (CNN) as features for different visual recognition tasks. Although promising results have been achieved in some empirical studies, such type of…

Computer Vision and Pattern Recognition · Computer Science 2015-09-09 Jianwei Luo , Jianguo Li , Jun Wang , Zhiguo Jiang , Yurong Chen

Pooling is essentially an operation from the field of Mathematical Morphology, with max pooling as a limited special case. The more general setting of MorphPooling greatly extends the tool set for building neural networks. In addition to…

Computer Vision and Pattern Recognition · Computer Science 2022-11-28 Rick Groenendijk , Leo Dorst , Theo Gevers

Encouraged by the success of Convolutional Neural Networks (CNNs) in image classification, recently much effort is spent on applying CNNs to video based action recognition problems. One challenge is that video contains a varying number of…

Computer Vision and Pattern Recognition · Computer Science 2015-04-17 Peng Wang , Yuanzhouhan Cao , Chunhua Shen , Lingqiao Liu , Heng Tao Shen

For convolutional neural network models that optimize an image embedding, we propose a method to highlight the regions of images that contribute most to pairwise similarity. This work is a corollary to the visualization tools developed for…

Computer Vision and Pattern Recognition · Computer Science 2019-01-04 Abby Stylianou , Richard Souvenir , Robert Pless

Mean-pooled cosine similarity is the default metric for comparing neural representations across languages, modalities, and tasks. We establish that this metric is not length-invariant: under the anisotropy that characterizes modern…

Computation and Language · Computer Science 2026-05-11 Sibayan Mitra , Dhruv Kumar

In Multimodal Neural Machine Translation (MNMT), a neural model generates a translated sentence that describes an image, given the image itself and one source descriptions in English. This is considered as the multimodal image caption…

Computation and Language · Computer Science 2018-06-01 Jean-Benoit Delbrouck , Stéphane Dupont , Omar Seddati

A major factor contributing to the success of modern representation learning is the ease of performing various vector operations. Recently, objects with geometric structures (eg. distributions, complex or hyperbolic vectors, or regions such…

Computation and Language · Computer Science 2021-09-13 Tejas Chheda , Purujit Goyal , Trang Tran , Dhruvesh Patel , Michael Boratko , Shib Sankar Dasgupta , Andrew McCallum

Visual question answering (VQA) is challenging because it requires a simultaneous understanding of both the visual content of images and the textual content of questions. The approaches used to represent the images and questions in a…

Computer Vision and Pattern Recognition · Computer Science 2017-08-07 Zhou Yu , Jun Yu , Jianping Fan , Dacheng Tao

In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network to have remarkable localization ability despite being trained on image-level labels.…

Computer Vision and Pattern Recognition · Computer Science 2015-12-15 Bolei Zhou , Aditya Khosla , Agata Lapedriza , Aude Oliva , Antonio Torralba

This work proposes a novel pose estimation model for object categories that can be effectively transferred to previously unseen environments. The deep convolutional network models (CNN) for pose estimation are typically trained and…

Computer Vision and Pattern Recognition · Computer Science 2022-03-04 Negar Nejatishahidin , Pooya Fayyazsanavi , Jana Kosecka

This paper reviews recent studies in understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations. Although deep neural networks have exhibited superior performance…

Computer Vision and Pattern Recognition · Computer Science 2018-02-08 Quanshi Zhang , Song-Chun Zhu

Unsupervised disentangled representation learning is a long-standing problem in computer vision. This work proposes a novel framework for performing image clustering from deep embeddings by combining instance-level contrastive learning with…

Machine Learning · Computer Science 2021-10-05 Ramakrishnan Sundareswaran , Jansel Herrera-Gerena , John Just , Ali Jannesari

Deep convolutional neural networks (CNNs) have achieved breakthrough performance in many pattern recognition tasks such as image classification. However, the development of high-quality deep models typically relies on a substantial amount…

Computer Vision and Pattern Recognition · Computer Science 2016-05-05 Mengchen Liu , Jiaxin Shi , Zhen Li , Chongxuan Li , Jun Zhu , Shixia Liu

Deep learning models for natural language processing (NLP) are inherently complex and often viewed as black box in nature. This paper develops an approach for interpreting convolutional neural networks for text classification problems by…

Computation and Language · Computer Science 2021-07-12 Wei Zhao , Rahul Singh , Tarun Joshi , Agus Sudjianto , Vijayan N. Nair

Convolutional neural networks (CNNs) have achieved remarkable performance in many applications, especially in image recognition tasks. As a crucial component of CNNs, sub-sampling plays an important role for efficient training or invariance…

Machine Learning · Computer Science 2020-03-17 Hayoung Eom , Heeyoul Choi

With the introduction of anti-aliased convolutional neural networks (CNN), there has been some resurgence in relooking the way pooling is done in CNNs. The fundamental building block of the anti-aliased CNN has been the application of…

Computer Vision and Pattern Recognition · Computer Science 2021-10-19 Adithya Sineesh , Mahesh Raveendranatha Panicker

Combining data from different sources can improve data analysis tasks such as clustering. However, most of the current multi-view clustering methods are limited to specific domains or rely on a suboptimal and computationally intensive…

Machine Learning · Computer Science 2025-05-21 Ran Eisenberg , Jonathan Svirsky , Ofir Lindenbaum

In computer vision, convolutional networks (CNNs) often adopts pooling to enlarge receptive field which has the advantage of low computational complexity. However, pooling can cause information loss and thus is detrimental to further…

Computer Vision and Pattern Recognition · Computer Science 2019-07-09 Pengju Liu , Hongzhi Zhang , Wei Lian , Wangmeng Zuo

We address the key question of how object part representations can be found from the internal states of CNNs that are trained for high-level tasks, such as object classification. This work provides a new unsupervised method to learn…

Machine Learning · Computer Science 2016-11-15 Jianyu Wang , Zhishuai Zhang , Cihang Xie , Vittal Premachandran , Alan Yuille