Related papers: MSE Loss with Outlying Label for Imbalanced Classi…
One common loss function in neural network classification tasks is Categorical Cross Entropy (CCE), which punishes all misclassifications equally. However, classes often have an inherent structure. For instance, classifying an image of a…
Training of large-scale models is both computationally intensive and often constrained by the availability of labeled data. Model merging offers a compelling alternative by directly integrating the weights of multiple source models without…
Target imbalance affects the performance of recent deep learning methods in many medical image segmentation tasks. It is a twofold problem: class imbalance - positive class (lesion) size compared to negative class (non-lesion) size; lesion…
Unsupervised Deep Distance Metric Learning (UDML) aims to learn sample similarities in the embedding space from an unlabeled dataset. Traditional UDML methods usually use the triplet loss or pairwise loss which requires the mining of…
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…
Multi-label Out-Of-Distribution (OOD) detection aims to discriminate the OOD samples from the multi-label In-Distribution (ID) ones. Compared with its multiclass counterpart, it is crucial to model the joint information among classes. To…
Semi-supervised learning is the problem of training an accurate predictive model by combining a small labeled dataset with a presumably much larger unlabeled dataset. Many methods for semi-supervised deep learning have been developed,…
Cross-entropy (CE) is the default training loss for supervised classification, but its sample efficiency is limited when labels are scarce. Existing remedies primarily act on the data side, via augmentation, synthesis, or transfer from…
Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes.…
Contrastive learning approaches have achieved great success in learning visual representations with few labels of the target classes. That implies a tantalizing possibility of scaling them up beyond a curated "seed" benchmark, to…
This paper proposes a deep representation learning using an information-theoretic loss with an aim to increase the inter-class distances as well as within-class similarity in the embedded space. Tasks such as anomaly and out-of-distribution…
In this study, we systematically investigate the impact of class imbalance on classification performance of convolutional neural networks (CNNs) and compare frequently used methods to address the issue. Class imbalance is a common problem…
Imbalanced learning (IL), i.e., learning unbiased models from class-imbalanced data, is a challenging problem. Typical IL methods including resampling and reweighting were designed based on some heuristic assumptions. They often suffer from…
Class labels used for machine learning are relatable to each other, with certain class labels being more similar to each other than others (e.g. images of cats and dogs are more similar to each other than those of cats and cars). Such…
In this paper, we propose a Dual Focal Loss (DFL) function, as a replacement for the standard cross entropy (CE) function to achieve a better treatment of the unbalanced classes in a dataset. Our DFL method is an improvement on the recently…
Modern deep neural networks for classification usually jointly learn a backbone for representation and a linear classifier to output the logit of each class. A recent study has shown a phenomenon called neural collapse that the within-class…
Supervised contrastive learning (SupCon) has proven to be a powerful alternative to the standard cross-entropy loss for classification of multi-class balanced datasets. However, it struggles to learn well-conditioned representations of…
Instance-sensitive losses for semantic segmentation such as blob loss and CC loss were designed to address instance imbalance, ensuring small lesions generate the same gradient as large ones, but operate only on single-class segmentation.…
In recent years Deep Neural Network-based systems are not only increasing in popularity but also receive growing user trust. However, due to the closed-world assumption of such systems, they cannot recognize samples from unknown classes and…
Overparameterized models fail to generalize well in the presence of data imbalance even when combined with traditional techniques for mitigating imbalances. This paper focuses on imbalanced classification datasets, in which a small subset…