Learning to Model the Tail

By Yu-Xiong Wang, Deva Ramanan, Martial Hebert. 2017

722 citations recorded by the source corpus.

How researchers see this paper

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

In Anomaly & Outlier Detection

Citations in the corpus

CrossTransformers: spatially-aware few-shot transfer (2020, background): “Unfamiliar objects are ubiquitous in many real-world vision applications due to the so-called ‘long tail’ [93] of objects that occur in real scenes, and therefore we expect our algorithm to improve the robustness of visual recognition systems.”
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples (2019, background): “, 2018) in a low-shot learning setting, and some learn to predict the parameters of a large-shot classifier from the parameters learned in a few-shot setting (Wang & Hebert, 2016; Wang et al., 2017).”
Greedy AutoAugment (2019, background): “Such problems can be addressed by data augmentation [5].”
Low-Shot Learning from Imaginary Data (2018, background): “An alternative is to directly predict the classifier weights that would be learned from a large dataset using few novel class examples [2] or from a small dataset classifier [37, 38].”
Long-Tailed Class Incremental Learning (2022, background): “However, data sampled from the real world often follows a long-tailed distribution [14,24,40,49] in which some classes have many more samples than others.”
Incremental Meta-Learning via Indirect Discriminant Alignment (2020, background): “The natural occurrence of classes in the world is a long tailed distribution [42, 37, 39], whereby instances for most classes are rare and instances for few classes are abundant.”
Large-Scale Long-Tailed Recognition in an Open World (2019, methodology): “Note that our approach also incurs much less computational cost since MetaModelNet [55] requires a recursive training procedure.”
Decoupling Representation and Classifier for Long-Tailed Recognition (2019, methodology): “For imbalanced datasets, instance-balanced sampling has been shown to be sub-optimal (Huang et al., 2016; Wang et al., 2017) as the model under-fits for few-shot classes leading to lower accuracy, especially for balanced test sets.”
Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learning (2019, methodology): “e 64 Head and 5 Tail categories. Setups 1-Shot 5-Shot 1-Shot 5-Shot Perf. Measures Mean Acc. " # Mean Acc. " # Harmonic Mean Acc. " IFSL [41] 54.95 0.30 11.84 63.04 0.30 10.66 - - L2ML [58] 46.25 0.04 27.49 45.81 0.03 35.53 2.98 0.06 1.12 0.04 DFSL [15] 61.00 0.11 13.28 72.84 0.09 10.”
Meta R-CNN: Towards General Solver for Instance-Level Low-Shot Learning (2019, background): “Distinct from them, meta-learning [40, 37, 12, 32, 3, 16, 43, 11] designs to learn a meta-learner to parametrize the optimization algorithm or predict the parameters of a classifier, so-called “learning-to-learn”.”
Boosting Few-Shot Visual Learning With Self-Supervision (2019, neutral): “, training images, of a few-shot task [26, 33, 53, 55, 57, 59]; methods learning to map a test example to a class label by accessing memory modules that store training examples for that task [11, 25, 35, 38, 50]; approaches that learn how to generate the weights of a classifier [12, 16, 43, 44, 13] ”
Diverse Few-Shot Text Classification with Multiple Metrics (2018, methodology): “…(Koch, 2015; Vinyals et al., 2016; Snell et al., 2017); and (2) optimization-based models, which receive the input of gradients from a FSL task and predict either model parameters or parameter updates (Ravi and Larochelle, 2017; Munkhdalai and Yu, 2017; Finn et al., 2017; Wang et al., 2017).”
Adaptive Risk Minimization: A Meta-Learning Approach for Tackling Group Shift (2020, background): “Meta-learning [57, 6, 66, 28] has been most extensively studied in the context of few shot supervised learning methods [56, 69, 52, 18, 70, 62, 20, 1].”
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss (2019, background): “The vanilla scheme re-weights classes proportionally to the inverse of their frequency [21, 22, 55].”
Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition From a Domain Adaptation Perspective (2020, background): “Yin et al. transfer intra-class variance from the head to tail [56], Liu et al. add a memory module to the neural networks to transfer semantic features [36], and Wang et al. employ a meta network to regress network weights between different classes [53].”
Rethinking the Value of Labels for Improving Class-Imbalanced Learning (2020, background): “In addition, cost-sensitive re-weighting schemes [6, 22, 23, 27, 52] are proposed to (dynamically) adjust weights during training for different classes or even different samples.”
Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning (2022, background): “The idea of weighting training samples in the loss calculation originates from the class imbalance (Wang et al., 2017) and noisy label (Hendrycks et al.”