相关论文: Seesaw Loss for Long-Tailed Instance Segmentation

Real-world data usually couples the label ambiguity and heavy imbalance, challenging the algorithmic robustness of partial label learning (PLL) and long-tailed learning (LT). The straightforward combination of LT and PLL, i.e., LT-PLL,…

While the novel class discovery has recently made great progress, existing methods typically focus on improving algorithms on class-balanced benchmarks. However, in real-world recognition tasks, the class distributions of their…

Real-world datasets often exhibit long-tailed distributions, where a few dominant "Head" classes have abundant samples while most "Tail" classes are severely underrepresented, leading to biased learning and poor generalization for the Tail.…

Long-tailed relation classification is a challenging problem as the head classes may dominate the training phase, thereby leading to the deterioration of the tail performance. Existing solutions usually address this issue via…

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.…

Active learning aims to reduce the labeling effort that is required to train algorithms by learning an acquisition function selecting the most relevant data for which a label should be requested from a large unlabeled data pool. Active…

Effectively handling the co-occurrence of non-IID data and long-tailed distributions remains a critical challenge in federated learning. While fine-tuning vision-language models (VLMs) like CLIP has shown to be promising in addressing…

In class incremental learning (CIL) a model must learn new classes in a sequential manner without forgetting old ones. However, conventional CIL methods consider a balanced distribution for each new task, which ignores the prevalence of…

Adam has been shown to outperform gradient descent on large language models by a larger margin than on other tasks, but it is unclear why. We show that a key factor in this performance gap is the heavy-tailed class imbalance found in…

Class imbalance is a fundamental problem in computer vision applications such as semantic segmentation. Specifically, uneven class distributions in a training dataset often result in unsatisfactory performance on under-represented classes.…

Compositional Zero-Shot Learning (CZSL) aims to transfer knowledge from seen state-object pairs to novel unseen pairs. In this process, visual bias caused by the diverse interrelationship of state-object combinations blurs their visual…

Vanilla models for object detection and instance segmentation suffer from the heavy bias toward detecting frequent objects in the long-tailed setting. Existing methods address this issue mostly during training, e.g., by re-sampling or…

Conventional de-noising methods rely on the assumption that all samples are independent and identically distributed, so the resultant classifier, though disturbed by noise, can still easily identify the noises as the outliers of training…

The long-tailed recognition (LTR) is the task of learning high-performance classifiers given extremely imbalanced training samples between categories. Most of the existing works address the problem by either enhancing the features of tail…

Neural networks trained on real-world datasets with long-tailed label distributions are biased towards frequent classes and perform poorly on infrequent classes. The imbalance in the ratio of positive and negative samples for each class…

Anomaly detection (AD) aims to identify defective images and localize their defects (if any). Ideally, AD models should be able to detect defects over many image classes; without relying on hard-coded class names that can be uninformative…

Learning from real-world data is frequently hindered by the compound challenge of long-tailed class distributions and noisy annotations. Existing methods partially address these issues but typically ignore the non-uniform impact of label…

Computer vision tasks are traditionally defined and evaluated using semantic categories. However, it is known to the field that semantic classes do not necessarily correspond to a unique visual class (e.g. inside and outside of a car).…

This paper focuses on long-tailed object detection in the semi-supervised learning setting, which poses realistic challenges, but has rarely been studied in the literature. We propose a novel pseudo-labeling-based detector called…

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,…