A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL.
The file type is application/pdf.
Filters
Deep Transfer Learning for Intelligent Vehicle Perception: a Survey
[article]
2023
arXiv
pre-print
Preserved Fulltext
Other Versions
Nevertheless, there are currently no survey papers on the topic of deep transfer learning for intelligent vehicle perception. ...
To the best of our knowledge, this paper represents the first comprehensive survey on the topic of the deep transfer learning for intelligent vehicle perception. ...
Weakly-Supervised TL: Theories of weakly supervised learning have been applied in autonomous driving Barnes et al. (2017) , Gojcic et al. (2021) , such as object detection, semantic segmentation, and ...
arXiv:2306.15110v2
fatcat:prw7thp6cnhhdft7ifwjrukswu
Zero-Annotation Object Detection with Web Knowledge Transfer
[article]
2018
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
With our end-to-end framework that simultaneously learns a weakly supervised detector and transfers knowledge across domains, we achieved significant improvements over baseline methods on the benchmark ...
Most of the existing detection works rely on labor-intensive supervision, such as ground truth bounding boxes of objects or at least image-level annotations. ...
As weakly supervised detection is essentially a multi-instance multi-label learning problem, each image actually is a bag of instances, where each instance corresponds to a bounding box proposal. ...
arXiv:1711.05954v2
fatcat:h6t5z4ropfhmpktt3mry23vfqq
Zero-Annotation Object Detection with Web Knowledge Transfer
[chapter]
2018
Lecture Notes in Computer Science
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.
With our end-to-end framework that simultaneously learns a weakly supervised detector and transfers knowledge across domains, we achieved significant improvements over baseline methods on the benchmark ...
Most of the existing detection works rely on labor-intensive supervision, such as ground truth bounding boxes of objects or at least image-level annotations. ...
As weakly supervised detection is essentially a multi-instance multi-label learning problem, each image actually is a bag of instances, where each instance corresponds to a bounding box proposal. ...
doi:10.1007/978-3-030-01252-6_23
fatcat:eynxmqzi4fcgxe7tya5yobxb3m
Weakly-supervised Salient Instance Detection
[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.
Existing salient instance detection (SID) methods typically learn from pixel-level annotated datasets. In this paper, we present the first weakly-supervised approach to the SID problem. ...
Although weak supervision has been considered in general saliency detection, it is mainly based on using class labels for object localization. ...
It has three synergic branches: (1) a Boundary Detection Branch for detecting object boundaries using class discrepancy information; (2) a Saliency Detection Branch for detecting objects using class consistency ...
arXiv:2009.13898v1
fatcat:baighmhl5fafdbgm2b2aiasgqm
Mixed Supervised Object Detection with Robust Objectness Transfer
2018
IEEE Transactions on Pattern Analysis and Machine 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 2018; you can also visit the original URL.
The file type is application/pdf.
Under the guidance of learned objectness knowledge, we utilize multiple instance learning (MIL) to model the concepts of both objects and distractors and to further improve the ability of rejecting distractors ...
In this paper, we consider the problem of leveraging existing fully labeled categories to improve the weakly supervised detection (WSD) of new object categories, which we refer to as mixed supervised detection ...
To address this issue, we aim to further model the difference between objects and distractors based on a multiple instance learning (MIL) approach and propose the objectness-aware detection model. ...
doi:10.1109/tpami.2018.2810288
pmid:29994285
fatcat:zcud2xdfirf35hazr4h63ha6rq
Mixed Supervised Object Detection with Robust Objectness Transfer
[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
Under the guidance of learned objectness knowledge, we utilize multiple instance learning (MIL) to model the concepts of both objects and distractors and to further improve the ability of rejecting distractors ...
In this paper, we consider the problem of leveraging existing fully labeled categories to improve the weakly supervised detection (WSD) of new object categories, which we refer to as mixed supervised detection ...
APPENDIX C HARD NEGATIVE MINING IN WEAKLY/MIXED SUPER-
VISED DETECTION In early fully supervised detection works that are based on standard multiple instance learning (MIL), e.g., DPM [42] , hard negative ...
arXiv:1802.09778v3
fatcat:ompykpngtjg5pcslofcqylypby
Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence 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.
In this paper, we analyze the modality asynchrony and undifferentiated instances phenomena of the multiple instance learning (MIL) procedure, and further investigate its negative impact on weakly-supervised ...
Weakly-supervised audio-visual violence detection aims to distinguish snippets containing multimodal violence events with video-level labels. ...
The entire framework is trained jointly in a weakly supervised manner, and we adopt the multiple instance learning (MIL) strategy for optimization. ...
arXiv:2207.05500v1
fatcat:msv2qehs6raatikql2ffwdobxu
Zigzag Learning for Weakly Supervised 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.
This paper addresses weakly supervised object detection with only image-level supervision at training stage. ...
In this way, the model can be well prepared by training on easy examples for learning from more difficult ones and thus gain a stronger detection ability more efficiently. ...
Conclusion This paper proposed a zigzag learning strategy for weakly supervised object detection. ...
doi:10.1109/cvpr.2018.00448
dblp:conf/cvpr/0008FX018
fatcat:y6jn5b5o65ak5fh2yubn57ey5q
Zigzag Learning for Weakly Supervised Object Detection
[article]
2018
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.
This paper addresses weakly supervised object detection with only image-level supervision at training stage. ...
In this way, the model can be well prepared by training on easy examples for learning from more difficult ones and thus gain a stronger detection ability more efficiently. ...
Conclusion This paper proposed a zigzag learning strategy for weakly supervised object detection. ...
arXiv:1804.09466v1
fatcat:22l3yozl6rfv5mazkvute2ohjq
Uncertainty-Aware Weakly Supervised Action Detection from 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.
Our method leverages per-frame person detectors which have been trained on large image datasets within a Multiple Instance Learning framework. ...
Furthermore, we report the first weakly-supervised results on the AVA dataset and state-of-the-art results among weakly-supervised methods on UCF101-24. ...
Conclusion and Future Work We have proposed a weakly supervised spatio-temporal action detection method based on Multiple Instance Learning (MIL). ...
arXiv:2007.10703v1
fatcat:rwwbuzwxafbwbk5zpv3ybpkspq
Deep Weakly-Supervised Domain Adaptation for Pain Localization in 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.
Other Versions
Given the cost of annotating intensity levels for every video frame, we propose a weakly-supervised domain adaptation (WSDA) technique that allows for training 3D CNNs for spatio-temporal pain intensity ...
In particular, WSDA integrates multiple instance learning into an adversarial deep domain adaptation framework to train an Inflated 3D-CNN (I3D) model such that it can accurately estimate pain intensities ...
Multiple Instance Learning (MIL) is one of the widely used approaches for inexact supervision [6] . ...
arXiv:1910.08173v2
fatcat:p7huseb36ve37nk4qpmbygnazq
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. ...
Can we detect common objects in a variety of image domains without instance-level annotations? ...
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
Optical Remote Sensing Image Understanding with Weak Supervision: Concepts, Methods, and Perspectives
2022
IEEE Geoscience and Remote Sensing Magazine
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.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2022 pre-print arXiv:2204.09120v1 fatcat:ilcje7m6pjdztf545rfe3y2oga
detection, and object detection. ...
This paper summarizes the research progress of weakly supervised learning in the field of remote sensing, including three typical weakly supervised paradigms: 1) Incomplete supervision, where only a subset ...
In the third part, inexact supervision and its typical applications in RSI understanding, including multi-instance learning for RSI object localization and detection, are summarized in detail. ...
doi:10.1109/mgrs.2022.3161377
fatcat:x2lm7l43tvfm7ks2j6v5zmfcp4
Weakly Supervised Object Detection using Complementary Learning and Instance Clustering
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.
Whereas, weakly supervised object detection (WSOD) uses only image-level annotations for training which are much simpler to acquire. ...
This network learns the proposals enclosing whole object instances by complementary features which ultimately learns to predict the high probabilities for whole objects than proposals containing only object ...
Weakly supervised object detection (WSOD) refers to learning object detections with only image-level annotations [2] , [3] . ...
doi:10.1109/access.2020.2999596
fatcat:pswtjhcmqrg6zoineul2bjvk3e
MonoGRNet: A General Framework for Monocular 3D Object Detection
[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.
In addition, MonoGRNet flexibly adapts to both fully and weakly supervised learning, which improves the feasibility of our framework in diverse settings. ...
MonoGRNet decomposes the monocular 3D object detection task into four sub-tasks including 2D object detection, instance-level depth estimation, projected 3D center estimation and local corner regression ...
Weakly supervised object detection Most existing studies focus on 2D object detection, while weakly supervised 3D detection has not been extensively explored. ...
arXiv:2104.08797v1
fatcat:x27vv6c3frekxonpsn4764lqyi
« Previous
Showing results 1 — 15 out of 4,825 results