相关论文: Adaptive Class Suppression Loss for Long-Tail Obje…

Real-world data is extremely imbalanced and presents a long-tailed distribution, resulting in models that are biased towards classes with sufficient samples and perform poorly on rare classes. Recent methods propose to rebalance classes but…

Benchmark datasets for visual recognition assume that data is uniformly distributed, while real-world datasets obey long-tailed distribution. Current approaches handle the long-tailed problem to transform the long-tailed dataset to uniform…

Recent object detection and instance segmentation tasks mainly focus on datasets with a relatively small set of categories, e.g. Pascal VOC with 20 classes and COCO with 80 classes. The new large vocabulary dataset LVIS brings new…

Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases. Given the promising performance contrastive learning has shown recently in…

Long-tailed data is prevalent in real-world classification tasks and heavily relies on supervised information, which makes the annotation process exceptionally labor-intensive and time-consuming. Unfortunately, despite being a common…

One crucial challenge of real-world multilingual speech recognition is the long-tailed distribution problem, where some resource-rich languages like English have abundant training data, but a long tail of low-resource languages have varying…

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,…

The visual world naturally exhibits a long-tailed distribution of open classes, which poses great challenges to modern visual systems. Existing approaches either perform class re-balancing strategies or directly improve network modules to…

In the real world, data tends to follow long-tailed distributions w.r.t. class or attribution, motivating the challenging Long-Tailed Recognition (LTR) problem. In this paper, we revisit recent LTR methods with promising Vision Transformers…

Addressing Out-Of-Distribution (OOD) Segmentation and Zero-Shot Semantic Segmentation (ZS3) is challenging, necessitating segmenting unseen classes. Existing strategies adapt the class-agnostic Mask2Former (CA-M2F) tailored to specific…

We propose adversarial constrained-CNN loss, a new paradigm of constrained-CNN loss methods, for weakly supervised medical image segmentation. In the new paradigm, prior knowledge is encoded and depicted by reference masks, and is further…

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…

While stochastic gradient descent (SGD) is still the \emph{de facto} algorithm in deep learning, adaptive methods like Clipped SGD/Adam have been observed to outperform SGD across important tasks, such as attention models. The settings…

Long-tailed data is a special type of multi-class imbalanced data with a very large amount of minority/tail classes that have a very significant combined influence. Long-tailed learning aims to build high-performance models on datasets with…

For object detection detectors, enhancing model performance hinges on the ability to simultaneously consider inconsistencies across tasks and focus on difficult-to-train samples. Achieving this necessitates incorporating information from…

Real-world data often have a long-tailed distribution, where the number of samples per class is not equal over training classes. The imbalanced data form a biased feature space, which deteriorates the performance of the recognition model.…

The continual appearance of new objects in the visual world poses considerable challenges for current deep learning methods in real-world deployments. The challenge of new task learning is often exacerbated by the scarcity of data for the…

Long-tailed semi-supervised learning (LTSSL) presents a formidable challenge where models must overcome the scarcity of tail samples while mitigating the noise from unreliable pseudo-labels. Most prior LTSSL methods are designed to train…

Long-tailed multi-label visual recognition poses a significant challenge, as images typically contain multiple labels with highly imbalanced class distributions, leading to biased models that favor head classes while underperforming on tail…

Real-world data consistently exhibits a long-tailed distribution, often spanning multiple categories. This complexity underscores the challenge of content comprehension, particularly in scenarios requiring Long-Tailed Multi-Label image…