On Multi-Domain Long-Tailed Recognition, Generalization and Beyond
- URL: http://arxiv.org/abs/2203.09513v1
- Date: Thu, 17 Mar 2022 17:59:21 GMT
- Title: On Multi-Domain Long-Tailed Recognition, Generalization and Beyond
- Authors: Yuzhe Yang, Hao Wang, Dina Katabi
- Abstract summary: Multi-Domain Long-Tailed Recognition learns from multi-domain imbalanced data.
We propose BoDA, a theoretically grounded learning strategy that tracks the upper bound of transferability statistics.
As a byproduct, BoDA establishes new state-of-the-art on Domain Generalization benchmarks, improving generalization to unseen domains.
- Score: 29.629072761463863
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Real-world data often exhibit imbalanced label distributions. Existing
studies on data imbalance focus on single-domain settings, i.e., samples are
from the same data distribution. However, natural data can originate from
distinct domains, where a minority class in one domain could have abundant
instances from other domains. We formalize the task of Multi-Domain Long-Tailed
Recognition (MDLT), which learns from multi-domain imbalanced data, addresses
label imbalance, domain shift, and divergent label distributions across
domains, and generalizes to all domain-class pairs. We first develop the
domain-class transferability graph, and show that such transferability governs
the success of learning in MDLT. We then propose BoDA, a theoretically grounded
learning strategy that tracks the upper bound of transferability statistics,
and ensures balanced alignment and calibration across imbalanced domain-class
distributions. We curate five MDLT benchmarks based on widely-used multi-domain
datasets, and compare BoDA to twenty algorithms that span different learning
strategies. Extensive and rigorous experiments verify the superior performance
of BoDA. Further, as a byproduct, BoDA establishes new state-of-the-art on
Domain Generalization benchmarks, improving generalization to unseen domains.
Code and data are available at
https://github.com/YyzHarry/multi-domain-imbalance.
Related papers
- Overcoming Data Inequality across Domains with Semi-Supervised Domain
Generalization [4.921899151930171]
We propose a novel algorithm, ProUD, which can effectively learn domain-invariant features via domain-aware prototypes.
Our experiments on three different benchmark datasets demonstrate the effectiveness of ProUD.
arXiv Detail & Related papers (2024-03-08T10:49:37Z) - Composite Active Learning: Towards Multi-Domain Active Learning with
Theoretical Guarantees [12.316113075760743]
Active learning (AL) aims to improve model performance within a fixed labeling budget by choosing the most informative data points to label.
We propose the first general method, dubbed composite active learning (CAL), for multi-domain AL.
Our theoretical analysis shows that our method achieves a better error bound compared to current AL methods.
arXiv Detail & Related papers (2024-02-03T10:22:18Z) - Multi-Domain Long-Tailed Learning by Augmenting Disentangled
Representations [80.76164484820818]
There is an inescapable long-tailed class-imbalance issue in many real-world classification problems.
We study this multi-domain long-tailed learning problem and aim to produce a model that generalizes well across all classes and domains.
Built upon a proposed selective balanced sampling strategy, TALLY achieves this by mixing the semantic representation of one example with the domain-associated nuisances of another.
arXiv Detail & Related papers (2022-10-25T21:54:26Z) - Dynamic Instance Domain Adaptation [109.53575039217094]
Most studies on unsupervised domain adaptation assume that each domain's training samples come with domain labels.
We develop a dynamic neural network with adaptive convolutional kernels to generate instance-adaptive residuals to adapt domain-agnostic deep features to each individual instance.
Our model, dubbed DIDA-Net, achieves state-of-the-art performance on several commonly used single-source and multi-source UDA datasets.
arXiv Detail & Related papers (2022-03-09T20:05:54Z) - Aligning Domain-specific Distribution and Classifier for Cross-domain
Classification from Multiple Sources [25.204055330850164]
We propose a new framework with two alignment stages for Unsupervised Domain Adaptation.
Our method can achieve remarkable results on popular benchmark datasets for image classification.
arXiv Detail & Related papers (2022-01-04T06:35:11Z) - Cross-domain Contrastive Learning for Unsupervised Domain Adaptation [108.63914324182984]
Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labeled source domain to a different unlabeled target domain.
We build upon contrastive self-supervised learning to align features so as to reduce the domain discrepancy between training and testing sets.
arXiv Detail & Related papers (2021-06-10T06:32:30Z) - Inferring Latent Domains for Unsupervised Deep Domain Adaptation [54.963823285456925]
Unsupervised Domain Adaptation (UDA) refers to the problem of learning a model in a target domain where labeled data are not available.
This paper introduces a novel deep architecture which addresses the problem of UDA by automatically discovering latent domains in visual datasets.
We evaluate our approach on publicly available benchmarks, showing that it outperforms state-of-the-art domain adaptation methods.
arXiv Detail & Related papers (2021-03-25T14:33:33Z) - Batch Normalization Embeddings for Deep Domain Generalization [50.51405390150066]
Domain generalization aims at training machine learning models to perform robustly across different and unseen domains.
We show a significant increase in classification accuracy over current state-of-the-art techniques on popular domain generalization benchmarks.
arXiv Detail & Related papers (2020-11-25T12:02:57Z) - Mind the Gap: Enlarging the Domain Gap in Open Set Domain Adaptation [65.38975706997088]
Open set domain adaptation (OSDA) assumes the presence of unknown classes in the target domain.
We show that existing state-of-the-art methods suffer a considerable performance drop in the presence of larger domain gaps.
We propose a novel framework to specifically address the larger domain gaps.
arXiv Detail & Related papers (2020-03-08T14:20:24Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.