Related papers: On Multi-Domain Long-Tailed Recognition, Imbalance…
Existing long-tailed classification (LT) methods only focus on tackling the class-wise imbalance that head classes have more samples than tail classes, but overlook the attribute-wise imbalance. In fact, even if the class is balanced,…
Class imbalance problems frequently occur in real-world tasks, and conventional deep learning algorithms are well known for performance degradation on imbalanced training datasets. To mitigate this problem, many approaches have aimed to…
Generalized Category Discovery (GCD) utilizes labeled samples of known classes to discover novel classes in unlabeled samples. Existing methods show effective performance on artificial datasets with balanced distributions. However,…
Domain generalization (DG) aims at learning a model on source domains to well generalize on the unseen target domain. Although it has achieved great success, most of existing methods require the label information for all training samples in…
We present a new loss function called Distribution-Balanced Loss for the multi-label recognition problems that exhibit long-tailed class distributions. Compared to conventional single-label classification problem, multi-label recognition…
The long-tail distribution of the visual world poses great challenges for deep learning based classification models on how to handle the class imbalance problem. Existing solutions usually involve class-balancing strategies, e.g., by loss…
As the data scale grows, deep recognition models often suffer from long-tailed data distributions due to the heavy imbalanced sample number across categories. Indeed, real-world data usually exhibit some similarity relation among different…
Real-world data often exhibits long-tailed distributions with heavy class imbalance, posing great challenges for deep recognition models. We identify a persisting dilemma on the value of labels in the context of imbalanced learning: on the…
Domain generalization is proposed to address distribution shift, arising from statistical disparities between training source and unseen target domains. The widely used first-order meta-learning algorithms demonstrate strong performance for…
Unsupervised domain adaptation is a promising way to generalize deep models to novel domains. However, the current literature assumes that the label distribution is domain-invariant and only aligns the feature distributions or vice versa.…
Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a \emph{target domain} whose distribution differs from the training data distribution, referred as the \emph{source…
Detecting and rejecting unknown out-of-distribution (OOD) samples is critical for deployed neural networks to void unreliable predictions. In real-world scenarios, however, the efficacy of existing OOD detection methods is often impeded by…
Deep neural networks may perform poorly when training datasets are heavily class-imbalanced. Recently, two-stage methods decouple representation learning and classifier learning to improve performance. But there is still the vital issue of…
As the volume of data continues to expand, it becomes increasingly common for data to be aggregated from multiple sources. Leveraging multiple sources for model training typically achieves better predictive performance on test datasets.…
We consider the problem of active domain adaptation (ADA) to unlabeled target data, of which subset is actively selected and labeled given a budget constraint. Inspired by recent analysis on a critical issue from label distribution mismatch…
Recently, long-tailed image classification harvests lots of research attention, since the data distribution is long-tailed in many real-world situations. Piles of algorithms are devised to address the data imbalance problem by biasing the…
Classical machine learning assumes that the training and test sets come from the same distributions. Therefore, a model learned from the labeled training data is expected to perform well on the test data. However, This assumption may not…
In this paper, we propose to tackle the problem of reducing discrepancies between multiple domains referred to as multi-source domain adaptation and consider it under the target shift assumption: in all domains we aim to solve a…
We propose Regularized Learning under Label shifts (RLLS), a principled and a practical domain-adaptation algorithm to correct for shifts in the label distribution between a source and a target domain. We first estimate importance weights…
Deep long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing deep models from a large number of images that follow a long-tailed class distribution. In the last decade, deep learning…