Continuous Manifold Based Adaptation for Evolving Visual Domains
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
We pose the following question: what happens when test data not only differs from training data, but differs from it in a continually evolving way? The classic domain adaptation paradigm considers the world to be separated into stationary domains with clear boundaries between them. However, in many real-world applications, examples cannot be naturally separated into discrete domains, but arise from a continuously evolving underlying process. Examples include video with gradually changing lighting and spam email with evolving spammer tactics. We formulate a novel problem of adapting to such continuous domains, and present a solution based on smoothly varying embeddings. Recent work has shown the utility of considering discrete visual domains as fixed points embedded in a manifold of lower-dimensional subspaces. Adaptation can be achieved via transforms or kernels learned between such stationary source and target subspaces. We propose a method to consider non-stationary domains, which we refer to as Continuous Manifold Adaptation (CMA). We treat each target sample as potentially being drawn from a different subspace on the domain manifold, and present a novel technique for continuous transform-based adaptation. Our approach can learn to distinguish categories using training data collected at some point in the past, and continue to update its model of the categories for some time into the future, without receiving any additional labels. Experiments on two visual datasets demonstrate the value of our approach for several popular feature representations.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Object Detection with Discriminatively Trained Part-Based Models
Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.167 · Cited by 9,853
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
Lazebnik, S., Schmid, C., & Ponce, J. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.68 · Cited by 7,916
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2013) · arXiv · doi:10.48550/arxiv.1310.1531 · Cited by 4,019 · cited 7×
“Our 4http://www.cardatabase.net 5For our experiments we use the vectorized output of layer 6 of the network. algorithm, CMA, provides a significant accuracy improvement over the non-adaptive baselines for the GIST and DeCAF features.”
MethodInfluentialSelf-citationAdapting visual category models to new domains
Saenko, K., Kulis, B., Fritz, M., & Darrell, T. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15561-1_16 · Cited by 2,847 · cited 2×
“Our approach is inspired by recent methods that learn a transformation in feature space to minimize domain-induced dissimilarity [24, 17, 5, 12].”
BackgroundMethodInfluentialSelf-citationTorralba, A., & Efros, A. A. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995347 · Cited by 2,440 · cited 1×
“It has become increasingly clear that there is a significant bias between available labeled visual training data and the data encountered in the real world [28, 16].”
BackgroundLearning with Augmented Features for Heterogeneous Domain Adaptation
Duan, L., Xu, D., & Tsang, I. (2012) · arXiv · doi:10.48550/arxiv.1206.4660 · Cited by 320
Online domain adaptation of a pre-trained cascade of classifiers
Jain, V., & Learned-Miller, E. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995317 · Cited by 161
Cited by
Taskonomy: Disentangling Task Transfer Learning
Zamir, A. R., Sax, A., Shen, W., Guibas, L., Malik, J., & Savarese, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00391 · Cited by 1,128
A Review of Domain Adaptation without Target Labels
Kouw, W. M., & Loog, M. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2945942 · Cited by 613
Seeing Through Fog Without Seeing Fog: Deep Multimodal Sensor Fusion in Unseen Adverse Weather
Bijelic, M., Gruber, T., Mannan, F., Kraus, F., Ritter, W., Dietmayer, K., & Heide, F. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01170 · Cited by 609
Continual Test-Time Domain Adaptation
Wang, Q., Fink, O., Van Gool, L., & Dai, D. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00706 · Cited by 502
Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization
Ghifary, M., Balduzzi, D., Kleijn, W. B., & Zhang, M. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2599532 · Cited by 471
Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
Sun, Y., Wang, X., Liu, Z., Miller, J., Efros, A. A., & Hardt, M. (2019) · arXiv · doi:10.48550/arxiv.1909.13231 · Cited by 393
Transfer adaptation learning: A decade survey
Zhang, L., & Gao, X. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3183326 · Cited by 314
Unsupervised Domain Adaptation of Object Detectors: A Survey
Oza, P., Sindagi, V. A., VS, V., & Patel, V. M. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3217046 · Cited by 313
“Note that these strategies should consider additional constraints such as computationally inexpensive adaptation, restricted access to source domain data, and the issue of catastrophic forgetting, which is a prominent issue that results from continuous learning [171], [201], [202], [203], [204].”
BackgroundSakaridis, C., Dai, D., & Van Gool, L. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00747 · Cited by 281
Towards Recognizing Unseen Categories in Unseen Domains
Mancini, M., Akata, Z., Ricci, E., & Caputo, B. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58592-1_28 · Cited by 9
Metadata
- Authors
- Hoffman, J., Darrell, T., & Saenko, K.
- Venue
- 2014 IEEE Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2014-06
- Pages
- 867-874
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2005295545
- Cited by
- 130
- References
- 7
- FWCI
- 6.92
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.