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
Semantic Drift Compensation for Class-Incremental Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
In addition, we propose a new method to estimate the drift, called semantic drift, of features and compensate for it without the need of any exemplars. ...
Class-incremental learning of deep networks sequentially increases the number of classes to be classified. ...
Semantic Drift Compensation Embeddings suffer from drift when learned in a sequential manner. ...
arXiv:2004.00440v1
fatcat:fw3e7rh5njgfddkvdtxsyzihse
Incremental Prototype Prompt-tuning with Pre-trained Representation for Class Incremental Learning
[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.
Other Versions
In detail, we incrementally prompt-tune category prototypes for classification and example prototypes to compensate for semantic drift, the problem caused by learning bias at different phases. ...
Class incremental learning has attracted much attention, but most existing works still continually fine-tune the entire representation model, inevitably resulting in much catastrophic forgetting. ...
Figure 1 : T-SNE [19] of CIFAR-10 [13] to show semantic drift and its compensation. Note that the black arrows reflect the semantic drift. ...
arXiv:2204.03410v3
fatcat:uzx27s3vfnbqtpjhhtinzyvuom
Co-Transport for Class-Incremental Learning
[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 a result, we propose CO-transport for class Incremental Learning (COIL), which learns to relate across incremental tasks with the class-wise semantic relationship. ...
However, new classes often emerge in real-world applications and should be learned incrementally. ...
Recent works focus on compensating for the drift of the incremental model. [46] utilizes the exemplars to build an extra validation set, with which an extra bias correction layer is trained. ...
arXiv:2107.12654v1
fatcat:65cocgr6zfhanc2cv3e4l5afwi
SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning
[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
This paper introduces a solid state-of-the-art baseline for a class-incremental semantic segmentation (CISS) problem. ...
drift of the background class and the multi-label prediction issue. ...
One of the key additional difficulties of the class-incremental semantic segmentation (CISS) problem lies in the semantic drift of the background class present in the incrementally arriving training data ...
arXiv:2106.11562v3
fatcat:rco3ggvsnvhy3jlyurhuqiapvu
Cognitively Inspired Learning of Incremental Drifting Concepts
[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.
Inspired by the nervous system learning mechanisms, we develop a computational model that enables a deep neural network to learn new concepts and expand its learned knowledge to new domains incrementally ...
Our model can generate pseudo-data points for experience replay and accumulate new experiences to past learned experiences without causing cross-task interference. ...
RELATED WORK The problem of continual learning of incremental drifting concepts lies in the intersection of lifelong learning to encode drifting concept classes and incremental learning to incorporate ...
arXiv:2110.04662v1
fatcat:55sswxlm3bgjrm5a5n2nipmyhy
Continual Attentive Fusion for Incremental Learning in Semantic Segmentation
[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.
However, the first incremental learning methods for semantic segmentation appeared only recently. ...
Finally, we also introduce a novel strategy to account for the background class in the distillation loss, thus preventing biased predictions. ...
ACKNOWLEDGMENT The authors would like to thank Nvidia Corporation for GPU donations to support our research. ...
arXiv:2202.00432v1
fatcat:2woq3xbvazah5e337ge2g4lzru
Class-incremental learning: survey and performance evaluation on image classification
[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 2020; 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:
2020 pre-print arXiv:2010.15277v1 fatcat:eh6wdslly5exdeuz3z4hpjj4lu
In this paper, we provide a complete survey of existing class-incremental learning methods for image classification, and in particular we perform an extensive experimental evaluation on thirteen class-incremental ...
For future learning systems incremental learning is desirable, because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory ...
1 We do not refer to the scenario where each task only contains a single class, but consider adding a group of classes for each task. ...
arXiv:2010.15277v2
fatcat:wacloedzxrea3dgcuwm7xknyxe
Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning
[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
The amount of added capacity is determined dynamically from the learned binary mask. We evaluate DGM in the continual class-incremental setup on visual classification tasks. ...
In order to tackle these challenges, we introduce Dynamic Generative Memory (DGM) - a synaptic plasticity driven framework for continual learning. ...
training time and sensitivity to semantic drift. ...
arXiv:1904.03137v4
fatcat:kd3bvn263vcz5krnxzstkjwbiq
Essentials for Class Incremental Learning
[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.
Moreover, we identify poor quality of the learned representation as another reason for catastrophic forgetting in class-IL. ...
With these lessons learned, class-incremental learning results on CIFAR-100 and ImageNet improve over the state-of-the-art by a large margin, while keeping the approach simple. ...
Semantic drift compensation for
hilbert space. arXiv:12002.05715, 2020. 6 class-incremental learning. ...
arXiv:2102.09517v1
fatcat:li3tvwjwanfbnn52dx6lhi42im
SegMap: Segment-based mapping and localization using data-driven descriptors
2019
The international journal of robotics research
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.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2019 pre-print arXiv:1909.12837v1 fatcat:dozbtsv2ynfydhelf5ztj75bbm
SegMap exploits a single compact data-driven descriptor for performing multiple tasks: global localization, 3D dense map reconstruction, and semantic information extraction. ...
We show that the learned SegMap descriptor has superior segment retrieval capabilities, compared with state-of-the-art handcrafted descriptors. ...
Note that these classes are solely used for training the descriptor and are not related to the semantics presented in Section 4.4. ...
doi:10.1177/0278364919863090
fatcat:qllqpzsy7fbllccrt4u5nz2cgm
Table of Contents
2018
2018 IEEE/ACM 5th International Conference on Big Data Computing Applications and Technologies (BDCAT)
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.
with Active Sampling for MOX Drift Compensation 61 Tamara Matthews (Dublin Institute of Technology), Muhammad Iqbal (National College of Ireland), and Horacio Gonzalez-Velez (National College of Ireland ...
Dog Breed Detection and Recognition Based on Deep Learning 87 Richard O. ...
doi:10.1109/bdcat.2018.00004
fatcat:ykdhdzmqerarpook3yfqlzxfxi
A Survey on Multi-label Data Stream Classification
2019
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.
Contrary to traditional data mining using static datasets, there are several challenges for data stream mining, for instance, finite memory, one-pass and timely reaction. ...
Secondly, we identify mining constraints on classification for multi-label streaming data, and present a comprehensive study in algorithms for multi-label data stream classification. ...
Detailed descriptions are listed as follows: • MediaMill 15 : The MediaMill data set is used for video semantic annotation task, where there are 43907 data instances (video frames) with 101 class labels ...
doi:10.1109/access.2019.2962059
fatcat:wqws3xkpmzeenatuzftjfshb2a
A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks
[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
and analyze them according to these properties, (2) introduce a unified formalization of the class-incremental learning problem, (3) propose a common evaluation framework which is more thorough than existing ...
Here, we focus on the latter, place them in a common conceptual and experimental framework and propose the following contributions: (1) define six desirable properties of incremental learning algorithms ...
In embedding systems, Semantic Drift Compensation ( ) [80] was proposed to estimate the semantic drift of past knowledge while learning new knowledge to compensate for it, to further improve performance ...
arXiv:2011.01844v4
fatcat:kw43joxgwzgsfmmi3su2pjfwv4
Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning
[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.
Few-shot class-incremental learning is to recognize the new classes given few samples and not forget the old classes. ...
To address this problem, we propose a novel incremental prototype learning scheme. ...
SDC [32] proposes a new method called semantic drift compensation to deal with the drift of the data in incremental learning. ...
arXiv:2107.08918v1
fatcat:xflgrzwl3bbwhaditcadipag4u
Deep-SLAM++: Object-level RGBD SLAM based on class-specific deep shape priors
[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
The result is an effective object-level RGBD SLAM system that produces compact, high-fidelity, and dense 3D maps with semantic annotations. ...
Our work extends this idea to environments with unknown objects and imposes object priors by employing modern class-specific neural networks to generate complete model geometry proposals. ...
It furthermore contains a loop closure module that effectively compensates for eventual drift accumulations. We conclude our exposition with our experimental results in Section 4. ...
arXiv:1907.09691v2
fatcat:4p6apklvrnc6hm3yin7mxwmska
« Previous
Showing results 1 — 15 out of 1,856 results