A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
Filters
Task-Driven Feature Pooling for Image Classification
2015
2015 IEEE International Conference on Computer Vision (ICCV)
Preserved Fulltext
Feature pooling is an important strategy to achieve high performance in image classification. However, most pooling methods are unsupervised and heuristic. ...
In this paper, we propose a novel task-driven pooling (TDP) model to directly learn the pooled representation from data in a discriminative manner. ...
strategy named task-driven pooling (TDP) for image classification. ...
doi:10.1109/iccv.2015.140
dblp:conf/iccv/XieZSYL15
fatcat:d4clvyocuveajk3h7dc64dcg3u
Multi-scale and Discriminative Part Detectors Based Features for Multi-label Image Classification
2018
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Convolutional neural networks (CNNs) have shown their promise for image classification task. ...
maps with each feature map representing the occurrence probability of a particular part detector and learn DPD-based features by using a task-driven pooling scheme. ...
By integrating feature learning into classification, we can use more information from i O X to get a task-driven feature representation which is more suitable for classification than traditional pooling ...
doi:10.24963/ijcai.2018/90
dblp:conf/ijcai/ChengGLH18
fatcat:wqundh2u5nhrjfzaudaf476pai
Hierarchical task-driven feature learning for tumor histology
2015
2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
We explore this hierarchical and task-driven model in classifying malignant melanoma and the genetic subtype of breast tumors from histology images. ...
Through learning small and large-scale image features, we can capture the local and architectural structure of tumor tissue from histology images. ...
The patch-level classification results indicate that the task-driven method has great promise in learning subtle features that distinguish classes. ...
doi:10.1109/isbi.2015.7164039
dblp:conf/isbi/CoutureMTPN15
fatcat:hcjpjtoh2ndl3l62xhukeyye5i
Deep Convolutional Features for Image Based Retrieval and Scene Categorization
[article]
2015
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Instead of recognition, this paper focuses on the image retrieval problem and proposes a examines alternative pooling strategies derived for CNN features. ...
We examine several pooling strategies and demonstrate superior performance on the image retrieval task (INRIA Holidays) at the fraction of the computational cost, while using a relatively small memory ...
The work of [7] proposed a data driven method for computing the coarse geographical location of an image using simpler features like GIST and color histograms. ...
arXiv:1509.06033v1
fatcat:q6jj7jwbz5fotercxumrk53tsy
Indoor Scene Recognition using Task and Saliency-driven Feature Pooling
2012
Procedings of the British Machine Vision Conference 2012
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Our results prove this approach to be effective in the indoor scenario, while being also meaningful for other scene categorization tasks. ...
This is usually done by combining multiple representations of different image regions, most often using a fixed 4 × 4, or pyramidal image-partitioning scheme. ...
The classification is finally performed using SVM [3] , with C fixed to 100 for all the features and datasets. ...
doi:10.5244/c.26.98
dblp:conf/bmvc/FornoniC12
fatcat:cxuqczlng5b5toeaqokfxlqrsa
Using Deep Convolutional Neural Networks to Circumvent Morphological Feature Specification when Classifying Subvisible Protein Aggregates from Micro-Flow Images
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
of "morphological features" in a variety of tasks. ...
We demonstrate that our new classifier (in combination with a sample "image pooling" strategy) can obtain nearly perfect predictions using as few as 20 FIM images from a given protein formulation in a ...
In this work, we demonstrate a new strategy for using ConvNets for classification tasks. ...
arXiv:1709.00152v1
fatcat:g37dcyxxhvgnpbfv4mw6hqqu7y
MeshCNN: A Network with an Edge
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We demonstrate the effectiveness of our task-driven pooling on various learning tasks applied to 3D meshes. ...
MeshCNN learns which edges to collapse, thus forming a task-driven process where the network exposes and expands the important features while discarding the redundant ones. ...
In particular, we use the edge-collapse technique [Hoppe 1997 ] for our task-driven pooling operator. ...
arXiv:1809.05910v2
fatcat:di5f53ex25hp3dgd7l7je4nlt4
Classifying Melanoma Skin Lesions Using Convolutional Spiking Neural Networks with Unsupervised STDP Learning Rule
2020
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
We further propose to use feature selection to select more diagnostic features to improve the classification performance of our networks. ...
Experimental results show that comparing to CNNs that need to be trained from scratch, our SNNs (with and without feature selection) not only achieve much better classification accuracies but also have ...
The CNNs can learn from training image set and automatically extract important features for classification. ...
doi:10.1109/access.2020.2998098
fatcat:hnuwnpsuvvh55jjfrpjvvcsnnm
Neural encoding and interpretation for high-level visual cortices based on fMRI using image caption features
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
However, previous studies almost used image features of those deep network models pre-trained on classification task to construct visual encoding models. ...
In this study, we introduced one higher-level vision task: image caption (IC) task and proposed the visual encoding model based on IC features (ICFVEM) to encode voxels of high-level visual cortices. ...
However, for high-level visual cortices, those deep network models driven by the image classification task seem to be relatively limited. ...
arXiv:2003.11797v1
fatcat:svhidctfyvf4dllmqskz3ybtlm
Knowledge-Driven Network for Object Detection
2021
Algorithms
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In this paper, we present a knowledge-driven network (KDNet)—a new architecture that can aggregate and model keypoint relations to augment object features for detection. ...
Object detection is a challenging computer vision task with numerous real-world applications. ...
These novel modules can extract interesting features in the image for further classification and regression. Corner pooling layers. ...
doi:10.3390/a14070195
fatcat:cfnhqungzbgkzkmebab2a6dyny
Active Learning for Visual Question Answering: An Empirical Study
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We present an empirical study of active learning for Visual Question Answering, where a deep VQA model selects informative question-image pairs from a pool and queries an oracle for answers to maximally ...
and effective goal-driven active learning scoring function to pick question-image pairs for deep VQA models under the Bayesian Neural Network framework. ...
Acknowledgements We thank Michael Cogswell and Qing Sun for discussions about the active learning strategies. ...
arXiv:1711.01732v1
fatcat:2mf3bfiljna67n5rv52ymbef4y
Target Driven Instance Detection
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We introduce a Target Driven Instance Detector(TDID), which modifies existing general object detectors for the instance recognition setting. ...
For many applications, such as household robotics, a system may need to recognize a few very specific instances at a time. ...
This pooled target feature vector is then both cross-correlated with, and subtracted from, every location in the scene image feature map. ...
arXiv:1803.04610v6
fatcat:6nr7yhdcpng3nfeyrhb66esnfm
Attentive Fashion Grammar Network for Fashion Landmark Detection and Clothing Category Classification
2018
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The latter is goal-driven, which directly enhances task-related features and can be learned in an implicit, top-down manner. ...
For enhancing clothing category classification, our fashion network is encoded with two novel attention mechanisms, i.e., landmark-aware attention and category-driven attention. ...
Thus the rest layers (pooling-4, conv5s, pooling-5, and fcs) of VGG-Net can be stacked for final cloth image classification. ...
doi:10.1109/cvpr.2018.00449
dblp:conf/cvpr/WangXSZ18
fatcat:6ab7jil4ffbhpik52cba5kcpae
A Comparative Analysis of Visual Encoding Models Based on Classification and Segmentation Task-Driven CNNs
2020
Computational and Mathematical Methods in Medicine
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Using functional magnetic resonance imaging (fMRI) data, the features of natural visual stimulation are extracted using a segmentation network (FCN32s) and a classification network (VGG16) with different ...
However, the prediction performances of encoding models will have differences based on different networks driven by different tasks. Here, the impact of network tasks on encoding models is studied. ...
In particular, task-driven deep networks performing different computer vision tasks can extract different features from the same image stimuli, resulting in variations in the performance of encoding models ...
doi:10.1155/2020/5408942
pmid:32802150
pmcid:PMC7416280
fatcat:l7v4hynddffwjgnvohbeh7cscu
Gradient Driven Learning for Pooling in Visual Pipeline Feature Extraction Models
[article]
2013
arXiv
pre-print
Preserved Fulltext
The Internet Archive has a preservation copy of this work in our general collections.
The file type is application/pdf.
Hyper-parameter selection remains a daunting task when building a pattern recognition architecture which performs well, particularly in recently constructed visual pipeline models for feature extraction ...
Preliminary results show moderate potential gains in classification accuracy and highlight areas of importance within the intermediate feature representation space. ...
Open issues remain, particularly in the learning rate choice (for which we have traded the pooling structure for hyper-parameter η = 5e −5 ) and the number of maps needed to cover separate areas of invariance ...
arXiv:1301.3755v1
fatcat:ehfxjynfrjeovdfrjgispdvioy
« Previous
Showing results 1 — 15 out of 53,940 results