Related papers: Improving Calibration for Long-Tailed Recognition
The generalization gap on the long-tailed data sets is largely owing to most categories only occupying a few training samples. Decoupled training achieves better performance by training backbone and classifier separately. What causes the…
Learning with noisy labels has gained increasing attention because the inevitable imperfect labels in real-world scenarios can substantially hurt the deep model performance. Recent studies tend to regard low-loss samples as clean ones and…
Real-world datasets usually are class-imbalanced and corrupted by label noise. To solve the joint issue of long-tailed distribution and label noise, most previous works usually aim to design a noise detector to distinguish the noisy and…
Long-tailed visual recognition has received increasing attention in recent years. Due to the extremely imbalanced data distribution in long-tailed learning, the learning process shows great uncertainties. For example, the predictions of…
Supervised deep learning methods are enjoying enormous success in many practical applications of computer vision and have the potential to revolutionize robotics. However, the marked performance degradation to biases and imbalanced data…
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…
In many real-life tasks of application of supervised learning approaches, all the training data are not available at the same time. The examples are lifelong image classification or recognition of environmental objects during interaction of…
Modern machine learning suffers from catastrophic forgetting when learning new classes incrementally. The performance dramatically degrades due to the missing data of old classes. Incremental learning methods have been proposed to retain…
Continual learning from a sequential stream of data is a crucial challenge for machine learning research. Most studies have been conducted on this topic under the single-label classification setting along with an assumption of balanced…
Despite the notable success of deep neural networks (DNNs) in solving complex tasks, the training process still remains considerable challenges. A primary obstacle is the substantial time required for training, particularly as high…
Mislabeled data is a pervasive issue that undermines the performance of machine learning systems in real-world applications. An effective approach to mitigate this problem is to detect mislabeled instances and subject them to special…
In deep learning, mini-batch training is commonly used to optimize network parameters. However, the traditional mini-batch method may not learn the under-represented samples and complex patterns in the data, leading to a longer time for…
Real-world data usually suffers from severe class imbalance and long-tailed distributions, where minority classes are significantly underrepresented compared to the majority ones. Recent research prefers to utilize multi-expert…
Mixup~\cite{zhang2017mixup} is a recently proposed method for training deep neural networks where additional samples are generated during training by convexly combining random pairs of images and their associated labels. While simple to…
State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to label errors in this data, typically resulting in large efforts and costs and therefore…
Among all data augmentation techniques proposed so far, linear interpolation of training samples, also called Mixup, has found to be effective for a large panel of applications. Along with improved predictive performance, Mixup is also a…
Natural data are often long-tail distributed over semantic classes. Existing recognition methods tackle this imbalanced classification by placing more emphasis on the tail data, through class re-balancing/re-weighting or ensembling over…
Balancing performance trade-off on long-tail (LT) data distributions remains a long-standing challenge. In this paper, we posit that this dilemma stems from a phenomenon called "tail performance degradation" (the model tends to severely…
Real-world training data usually exhibits long-tailed distribution, where several majority classes have a significantly larger number of samples than the remaining minority classes. This imbalance degrades the performance of typical…
One of the most prominent problems in machine learning in the age of deep learning is the availability of sufficiently large annotated datasets. For specific domains, e.g. animal species, a long-tail distribution means that some classes are…