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.
Filters
Progressive Representation Adaptation for Weakly Supervised Object Localization
[article]
2017
arXiv
pre-print
Preserved Fulltext
We address the problem of weakly supervised object localization where only image-level annotations are available for training object detectors. ...
In this paper, we propose to overcome these drawbacks by progressive representation adaptation with two main steps: 1) classification adaptation and 2) detection adaptation. ...
In this paper, we present a progressive representation adaptation approach to tackle the weakly supervised object localization problem. ...
arXiv:1710.04647v1
fatcat:brn2iupd7re5hb3fhjq2q3i5pq
Weakly Supervised Object Localization with Progressive Domain Adaptation
2016
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
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 2016; you can also visit the original URL.
The file type is application/pdf.
We address the problem of weakly supervised object localization where only image-level annotations are available for training. ...
In this paper, we address this problem by progressive domain adaptation with two main steps: classification adaptation and detection adaptation. ...
We find that progressive adaptation is particularly important for the weakly supervised object localization problem. ...
doi:10.1109/cvpr.2016.382
dblp:conf/cvpr/LiHLW016
fatcat:i7ttpgaipvdwreco7kdbefj5zm
Weakly Supervised Object Localization and Detection: A Survey
[article]
2021
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 2021; you can also visit the original URL.
The file type is application/pdf.
As an emerging and challenging problem in the computer vision community, weakly supervised object localization and detection plays an important role for developing new generation computer vision systems ...
supervised object localization and detection methods, and potential future directions to further promote the development of this research field. ...
In this survey, we mainly focus on reviewing the research progress in weakly supervised object localization and detection, i.e., the red dot in the top block. ...
arXiv:2104.07918v1
fatcat:dwl6sjfzibdilnvjnrbifp4uke
WALLACE: Weakly Supervised Learning of Deep Convolutional Neural Networks with Multiscale Evidence
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 2020; you can also visit the original URL.
The file type is application/pdf.
INDEX TERMS Weakly supervised learning, convolutional neural networks, object localization, object classification, multiscale features. ...
Extensive experiments on object classification and weakly supervised pointwise object localization show that WALLACE achieves state-of-the-art results on the VOC 2007 and VOC 2012 benchmark without bells ...
For weakly supervised pointwise object detection, in order to perform VOLUME 8, 2020 localization, we need to generate some largest connected segment in the image and its associated object category, ...
doi:10.1109/access.2020.2968545
fatcat:gfyc47ou6ragfg336xb2niqqdi
Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization
[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
In this paper, we address the problem of weakly supervised object localization (WSL), which trains a detection network on the dataset with only image-level annotations. ...
Several strategies are taken to adaptively eliminate the noisy proposals and generate pseudo object-level annotations for the weakly labeled dataset. ...
As a follow-up study, it is desire to adapt a new feature extraction method for the weakly supervised localization task. ...
arXiv:1910.02101v2
fatcat:yeaqlgzpavhvlet5iqby33bmtu
Reinforcement Learning for Weakly Supervised Temporal Grounding of Natural Language in Untrimmed Videos
[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.
To the best of our knowledge, we offer the first attempt to extend RL to temporal localization task with weak supervision. ...
In this paper, we propose a Boundary Adaptive Refinement (BAR) framework that resorts to reinforcement learning (RL) to guide the process of progressively refining the temporal boundary. ...
This work can be regarded as the first attempt to extend RL to weakly supervised temporal localization tasks. ...
arXiv:2009.08614v1
fatcat:kbb5c5y2bjbhhjvfrgrnotkkla
A Survey of Visual Sensory Anomaly Detection
[article]
2022
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 2022; you can also visit the original URL.
The file type is application/pdf.
Furthermore, we classify each kind of anomaly according to the level of supervision. Finally, we summarize the challenges and provide open directions for this community. ...
However, no thorough review has been provided to summarize this area for the computer vision community. ...
Weakly supervised method is more realistic for its more inclusive data setting, while domain adaptation is another interesting research in AD. ...
arXiv:2202.07006v1
fatcat:2bqzmmrnjzggti5tcewa3mh3sa
Large Scale Semi-Supervised Object Detection Using Visual and Semantic Knowledge Transfer
2016
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
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.
a semi-supervised setting. ...
Deep CNN-based object detection systems have achieved remarkable success on several large-scale object detection benchmarks. ...
semantic domains to adapt image classifiers into object detectors in a semi-supervised manner. ...
doi:10.1109/cvpr.2016.233
dblp:conf/cvpr/TangWGDGC16
fatcat:bbz6v5uyw5d6zbssua5ki6lbwi
Deep Domain Adaptive Object Detection: a Survey
[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.
Other Versions
Deep learning (DL) based object detection has achieved great progress. ...
This paper aims to review the state-of-the-art progress on deep domain adaptive object detection approaches. Firstly, we introduce briefly the basic concepts of deep domain adaptation. ...
adaptive representation learning paradigm for object detection. ...
arXiv:2002.06797v3
fatcat:mozths3lk5djndue6dzefxuq3q
2021 Index IEEE Transactions on Image Processing Vol. 30
2021
IEEE Transactions on Image Processing
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 2022; you can also visit the original URL.
The file type is application/pdf.
The Author Index contains the primary entry for each item, listed under the first author's name. ...
., +, TIP 2021 5154-5167 Multi-Hierarchical Category Supervision for Weakly-Supervised Temporal Action Localization. ...
., +, TIP 2021 5920-5932 Modeling Sub-Actions for Weakly Supervised Temporal Action Localization. ...
doi:10.1109/tip.2022.3142569
fatcat:z26yhwuecbgrnb2czhwjlf73qu
Towards Single Stage Weakly Supervised Semantic Segmentation
[article]
2021
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 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The costly process of obtaining semantic segmentation labels has driven research towards weakly supervised semantic segmentation (WSSS) methods, using only image-level, point, or box labels. ...
supervision. ...
Very deep convo-
Is object localization for free? - weakly-supervised learning lutional networks for large-scale image recognition. arXiv
with convolutional neural networks. ...
arXiv:2106.10309v2
fatcat:l3oafc7rz5frbiynru2vn6ogfa
Semi-Supervised Domain Adaptation for Weakly Labeled Semantic Video Object Segmentation
[article]
2016
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, for video semantic object segmentation, a domain where labels are scarce, effectively exploiting the representation power of CNN with limited training data remains a challenge. ...
We propose a semi-supervised approach to adapting CNN image recognition model trained from labeled image data to the target domain exploiting both semantic evidence learned from CNN, and the intrinsic ...
This data-driven object representation underpins a robust object segmentation method for weakly labelled natural videos. ...
arXiv:1606.02280v1
fatcat:c4ynsqjrkjc37pmknd2zp7dztu
W2F: A Weakly-Supervised to Fully-Supervised Framework for Object Detection
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 2019; you can also visit the original URL.
The file type is application/pdf.
Weakly-supervised object detection has attracted much attention lately, since it does not require bounding box annotations for training. ...
Although significant progress has also been made, there is still a large gap in performance between weakly-supervised and fully-supervised object detection. ...
[23] propose classification adaptation to fine-tune the network, so that it can collect class specific object proposals, and detection adaptation is used to optimize the representations for the target ...
doi:10.1109/cvpr.2018.00103
dblp:conf/cvpr/ZhangBDLG18
fatcat:hy262v5bgfh2fhpwqlzzizgw24
Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization
[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.
In this paper, we propose a novel weakly-supervised framework by adversarial learning of two modules for eliminating such demerits. ...
Since the frame-level or segment-level annotations of untrimmed videos require amounts of labor expenditure, studies on the weakly-supervised action detection have been springing up. ...
Weakly-Supervised Object Localization. Weakly supervised object localization methods locate target objects using convolutional classification networks. ...
arXiv:1908.02422v1
fatcat:stwylcwezngnrisxpulvlagnou
Cross-Domain Weakly-Supervised Object Detection Through Progressive Domain Adaptation
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 2019; you can also visit the original URL.
The file type is application/pdf.
In this paper, we present a framework for a novel task, cross-domain weakly supervised object detection, which addresses this question. ...
Starting from a fully supervised object detector, which is pre-trained on the source domain, we propose a two-step progressive domain adaptation technique by fine-tuning the detector on two types of artificially ...
Furuta is supported by the Grants-in-Aid for Scientific Research (16J07267) from JSPS. ...
doi:10.1109/cvpr.2018.00525
dblp:conf/cvpr/InoueFYA18
fatcat:g66l47zivbgl7li3p373pe5jxa
« Previous
Showing results 1 — 15 out of 9,276 results