Unbiased Metric Learning: On the Utilization of Multiple Datasets and Web Images for Softening Bias

By Chen Fang, Ye Xu, D. Rockmore. 2013

497 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

In Safety, Robustness & Interpretability

Citations in the corpus

Break-It-Fix-It: Unsupervised Learning for Program Repair (2021, background): “Such domain shifts typically occur across related but different datasets (Torralba & Efros, 2011; Fang et al., 2013; Venkateswara et al., 2017; Yu et al., 2018b; 2019; Peng et al., 2019; Kamath et al., 2020), as well as from synthetic data to real data (including sim2real) (Wang et al., 2015; Ganin…”
In Search of Lost Domain Generalization (2020, neutral): “…loaders for seven multi-domain image classiﬁcation tasks: Colored MNIST [Arjovsky et al., 2019], Rotated MNIST [Ghifary et al., 2015], PACS [Li et al., 2017], VLCS [Fang et al., 2013], Ofﬁce-Home [Venkateswara et al., 2017], Terra Incognita [Beery et al., 2018], and DomainNet [Peng et al., 2019].”
Deeper, Broader and Artier Domain Generalization (2017, neutral): “Unseen domain Image 7→ Deep Feature 7→ Classifier Image 7→ E2E SVM 1HNN Undo-Bias[12] uDICA[19] UML[7] LRE-SVM[30] MTAE+1HNN[10] D-MTAE+1HNN[10] Ours-MLP Deep-All Ours-Full Caltech 77.”
Domain Generalization for Object Recognition with Multi-task Autoencoders (2015, background): “UML [16]: a structural metric learning-based algo-rithm that aims to learn a less biased distance metric for classiﬁcation tasks.”
Unified Deep Supervised Domain Adaptation and Generalization (2017, methodology): “1NN SVM LB UML [17] LRE-SVM [65] SCA [23] CCSA”
WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020, neutral): “Other similar benchmarks that have been proposed for domain generalization include VLCS (Fang et al., 2013), which tests generalization across similar visual object recognition datasets; PACS (Li et al., 2017), which (like DomainNet) tests generalization across datasets with different renditions; an”
Gradient Matching for Domain Generalization (2021, unknown): “It contains 7 popular domain generalization datasets, including Colored MNIST (Arjovsky et al., 2019), Rotated MNIST (Ghifary et al., 2015), VLCS (Fang et al., 2013), PACS (Li et al., 2017), OfﬁceHome (Venkateswara et al., 2017), Terra Incognita (Beery et al., 2018) and DomainNet (Peng et al.,…”
Domain Generalization via Gradient Surgery (2021, methodology): “datasets: PACS [15], VLCS [6] and Office-Home [29].”
Domain Generalization with Adversarial Feature Learning (2018, methodology): “For object recognition, we use the VLCS dataset [7], which contains 5 shared object categories (bird, car, chair, dog and person) from PASCAL VOC2007 (V) [6], LabelMe (L) [29], Caltech-101 (C) [8] and SUN09 (S) [2].”
Generalizing to Unseen Domains: A Survey on Domain Generalization (2021, background): “Among them, PACS [2], VLCS [231], and Ofﬁce-Home [232] are three most popular datasets.”
Deep Domain Generalization With Structured Low-Rank Constraint (2018, background): “However, current domain generalization [16], [18]–[21] works all adopted shallow structures to extract domain-invariant features, which actually cannot uncover enough effective features to facilitate the target learning.”
Domain Generalization via Model-Agnostic Learning of Semantic Features (2019, background): “VLCS [8] is a classic benchmark for domain generalization, which includes images from four datasets: PASCAL VOC2007 (V) [7], LabelMe (L) [41], Caltech (C) [9], and SUN09 (S) [4].”
Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning (2021, unknown): “We use 3 benchmark datasets, i.e., PACS [33], VLCS [14] and Ofﬁce-Home [53].”
Adversarial target-invariant representation learning for domain generalization (2019, background): “, 2017) and VLCS (Fang et al., 2013) domain generalization benchmarks which consist of object recognition tasks.”
Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization (2021, methodology): “We evaluate our method on multiple standard domain generalization benchmarks, namely VLCS [12], PACS [27], OfﬁceHome [50], and TerraIncognita [5].”
Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization (2020, methodology): “ic relationship supervision, and intrinsic selfsupervision, respectively. 4 Experiments 4.1 Datasets We evaluate our method on two public domain generalization benchmark datasets: VLCS and PACS. VLCS [10] is a classic domain generalization benchmark for image classication, which includes ve object c”
SelfReg: Self-supervised Contrastive Regularization for Domain Generalization (2021, background): “This testbed currently provides seven multi-domain datasets (i.e. ColoredMNIST [1], RotatedMNIST [16], VLCS [13], PACS [26], Ofﬁce-Home [42], and TerraIncognita [2], DomainNet [34]) and provides benchmarks results of 14 baseline approaches (i.e. ERM [41], IRM [1], GroupDRO [36], Mixup [45], MLDG [27”