Learning Deep Representation for Imbalanced Classification

By Chen Huang, Yining Li, Chen Change Loy, Xiaoou Tang. 2016

1,085 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Radiology, Nuclear Medicine and Imaging, Representation & Self-Supervised Learning

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 Radiology, Nuclear Medicine and Imaging

In Representation & Self-Supervised Learning

Citations in the corpus

Using Pre-Training Can Improve Model Robustness and Uncertainty (2019, background): “To this end, He & Garcia (2008) propose to remove samples from the majority classes, while Huang et al. (2016) replicate samples from the minority classes.”
Imbalanced Continual Learning with Partitioning Reservoir Sampling (2020, methodology): “Data processing methods such as oversampling or undersampling [5,8,65] explicitly simulate the input balance, while cost-sensitive approaches [38,85,18] adjust the update via regularizing the objective.”
Maintaining Discrimination and Fairness in Class Incremental Learning (2019, background): “Though class imbalance is an old topic and has attracted a lot of attention [4, 15, 17], multi-class imbalance learning is still an open problem [35].”
Large-Scale Long-Tailed Recognition in an Open World (2019, methodology): “Some recent methods include metric learning [22, 33], hard negative mining [10, 27], and meta learning [15, 55].”
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.”
Class-Balanced Loss Based on Effective Number of Samples (2019, methodology): “This simple heuristic method has been widely adopted [17, 43].”
Learning to Reweight Examples for Robust Deep Learning (2018, background): “, 2015), and structured margin based objectives (Huang et al., 2016).”
Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation (2020, methodology): “One prominent method for long-tailed visual recognition is data re-balancing, which is usually divided into two groups: resampling [2, 15, 18, 33, 46] and re-weighting [8, 9, 19].”
Learning a Unified Classifier Incrementally via Rebalancing (2019, background): “Previous efforts to tackle the class imbalance can be roughly divided into two groups: data resampling [13, 6, 12] and cost-sensitive learning [32, 17, 38, 16, 9].”
Differential Attention for Visual Question Answering (2018, background): “Objective function for Quintuplet loss[3] is defined as :”
Balanced Meta-Softmax for Long-Tailed Visual Recognition (2020, background): “, cost-sensitive learning [31, 11, 12, 24], assigns a cost weight to the loss of each class.”
Asymmetric Loss For Multi-Label Classification (2020, methodology): “It should be noted that methods which address class imbalance via static weighting factors were proposed in previous works [17, 9].”
Image Aesthetic Assessment: An experimental survey (2016, background): “uating testing partition with imbalanced distribution [54], [55].”
Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets (2020, background): “Typically, researchers apply class-level re-weighting by the proportional inverse of class frequency [13,34], or the square root for smoothing.”
BBN: Bilateral-Branch Network With Cumulative Learning for Long-Tailed Visual Recognition (2019, methodology): “, resampling [25, 1, 14, 1, 11, 2, 7, 21, 4] and cost-sensitive re-weighting [13, 28, 5, 23].”
Decomposing fit semantics for product size recommendation in metric spaces (2018, methodology): “To that end, our prototyping technique first alters the training data distribution by re-sampling from different classes, which is shown to be effective in handling label imbalance issues [4].”
Multi-label Contrastive Predictive Coding (2020, background): “When the dataset has extremely imbalanced classes, higher weights are given to classes with less frequency [21, 22, 52] or classes with less effective samples [11].”