When Naïve Bayes Nearest Neighbors Meet Convolutional Neural Networks

Kuzborskij, Ilja; Carlucci, Fabio Maria; Caputo, Barbara

doi:10.1109/cvpr.2016.231

Cited by 24 publications

(49 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The DSLR domain contains low-noise high resolution images of object captured from different viewpoints while Webcam contains low resolution images. The Office dataset has been used in numerous publications [28,33,8,5,36,17,32,14] that address domain adaptation, to name but a few of approaches. Its recent extension includes a new Caltech 10 domain [12].…”

Section: Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and Beyond

Koniusz

Tas

Zhang

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In this paper, we approach an open problem of artwork identification and propose a new dataset dubbed Open Museum Identification Challenge (Open MIC). It contains photos of exhibits captured in 10 distinct exhibition spaces of several museums which showcase paintings, timepieces, sculptures, glassware, relics, science exhibits, natural history pieces, ceramics, pottery, tools and indigenous crafts. The goal of Open MIC is to stimulate research in domain adaptation, egocentric recognition and few-shot learning by providing a testbed complementary to the famous Office dataset which reaches ∼90% accuracy [15]. To form our dataset, we captured a number of images per art piece with a mobile phone and wearable cameras to form the source and target data splits, respectively. To achieve robust baselines, we build on a recent approach that aligns per-class scatter matrices of the source and target CNN streams [15]. Moreover, we exploit the positive definite nature of such representations by using end-to-end Bregman divergences and the Riemannian metric. We present baselines such as training/evaluation per exhibition and training/evaluation on the combined set covering 866 exhibit identities. As each exhibition poses distinct challenges e.g., quality of lighting, motion blur, occlusions, clutter, viewpoint and scale variations, rotations, glares, transparency, non-planarity, clipping, we break down results w.r.t. these factors.Recently, algorithms for supervised domain adaptation such as Simultaneous Deep Transfer Across Domains and Tasks [33] and Second-or Higher-order Transfer (So-HoT) of knowledge [15] com-

show abstract

Section: Datasetsmentioning

confidence: 99%

“…Domain adaptation algorithms. Deep learning has been used in the context of domain adaptation in numerous recent works e.g., [33,8,5,36,17,32,15]. These works establish the so-called commonality between domains.…”

Section: Datasetsmentioning

confidence: 99%

Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and Beyond

Koniusz

Tas

Zhang

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…With a similar motivation, lately several works in computer vision have attempted to bring back the notion of localities into deep networks, e.g. by designing appropriate pooling strategies [12] or by casting the problem within the Image-2-Class (I2C) recognition framework [13], with a high degree of success. All these works decouple the choice of the significant localities from the learning of deep representations, as the CNN feature extraction and the classifier learning are implemented as two separate modules.…”

Section: Introductionmentioning

confidence: 99%

Learning Deep NBNN Representations for Robust Place Categorization

Mancini

Bulò²,

Ricci

et al. 2017

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

Abstract-This paper presents an approach for semantic place categorization using data obtained from RGB cameras. Previous studies on visual place recognition and classification have shown that, by considering features derived from pretrained Convolutional Neural Networks (CNNs) in combination with part-based classification models, high recognition accuracy can be achieved, even in presence of occlusions and severe viewpoint changes. Inspired by these works, we propose to exploit local deep representations, representing images as set of regions applying a Naïve Bayes Nearest Neighbor (NBNN) model for image classification. As opposed to previous methods where CNNs are merely used as feature extractors, our approach seamlessly integrates the NBNN model into a fully-convolutional neural network. Experimental results show that the proposed algorithm outperforms previous methods based on pre-trained CNN models and that, when employed in challenging robot place recognition tasks, it is robust to occlusions, environmental and sensor changes.

show abstract

“…Note that our I2CDDE algorithm can be applied to improve the performance of any local feature descriptors [58]. By using dense sampling or dense trajectory based local features, the overall performance can be further improved to achieve state-of-the-art performance [18].…”

Section: A Experimental Settingsmentioning

confidence: 99%

“…The NBNN has been extended in [14]- [16] achieve local NBNN and NBNN kernels, which have substantially improved the performance of NBBN and achieve great success in image classification. NBNN has recently been combined with deep convolutional neural networks show great effectiveness for scene classification [17], [18].…”

mentioning

confidence: 99%

Supervised Local Descriptor Learning for Human Action Recognition

Zhen

Zheng

Shao

et al. 2017

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Abstract-Local features have been widely used in computer vision tasks, e.g., human action recognition, but it tends to be an extremely challenging task to deal with large-scale local features of high dimensionality with redundant information. In this paper, we propose a novel fully supervised local descriptor learning algorithm called discriminative embedding method based on the image-toclass distance (I2CDDE) to learn compact but highly discriminative local feature descriptors for more accurate and efficient action recognition. By leveraging the advantages of the I2C distance, the proposed I2CDDE incorporates class labels to enable fully supervised learning of local feature descriptors, which achieves highly discriminative but compact local descriptors. The objective of our I2CDDE is to minimize the I2C distances from samples to their corresponding classes while maximizing the I2C distances to the other classes in the low-dimensional space. To further improve the performance, we propose incorporating a manifold regularization based on the graph Laplacian into the objective function, which can enhance the smoothness of the embedding by extracting the local intrinsic geometrical structure. The proposed I2CDDE for the first time achieves fully supervised learning of local feature descriptors. It significantly improves the performance of I2C-based methods by increasing the discriminative ability of local features while greatly reducing the computational burden by dimensionality reduction to handle large-scale data. We apply the proposed I2CDDE algorithm to human action recognition on four widely used benchmark datasets. The results have shown that I2CDDE can significantly improve I2C-based classifiers and achieves state-of-the-art performance.

show abstract

When Naïve Bayes Nearest Neighbors Meet Convolutional Neural Networks

Cited by 24 publications

References 35 publications

Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and Beyond

Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and Beyond

Learning Deep NBNN Representations for Robust Place Categorization

Supervised Local Descriptor Learning for Human Action Recognition

Contact Info

Product

Resources

About