Related papers: CUE: Concept-Aware Multi-Label Expansion to Mitiga…
Label noise and long-tailed distributions are two major challenges in distantly supervised relation extraction. Recent studies have shown great progress on denoising, but paid little attention to the problem of long-tailed relations. In…
The long-tailed image classification task remains important in the development of deep neural networks as it explicitly deals with large imbalances in the class frequencies of the training data. While uncommon in engineered datasets, this…
In this work, we address the challenging task of long-tailed image recognition. Previous long-tailed recognition methods commonly focus on the data augmentation or re-balancing strategy of the tail classes to give more attention to tail…
Long-tailed data is still a big challenge for deep neural networks, even though they have achieved great success on balanced data. We observe that vanilla training on long-tailed data with cross-entropy loss makes the instance-rich head…
For semi-supervised learning with imbalance classes, the long-tailed distribution of data will increase the model prediction bias toward dominant classes, undermining performance on less frequent classes. Existing methods also face…
Learning an effective representation in multi-label text classification (MLTC) is a significant challenge in NLP. This challenge arises from the inherent complexity of the task, which is shaped by two key factors: the intricate connections…
We tackle the long-tailed visual recognition problem from the knowledge distillation perspective by proposing a Distill the Virtual Examples (DiVE) method. Specifically, by treating the predictions of a teacher model as virtual examples, we…
Multi-label classification is a type of supervised machine learning that can simultaneously assign multiple labels to an instance. To solve this task, some methods divide the original problem into several sub-problems (local approach),…
Class incremental learning (CIL) aims to enable models to continuously learn new classes without catastrophically forgetting old ones. A promising direction is to learn and use prototypes of classes during incremental updates. Despite…
Long-tailed data bias decision boundaries toward head classes and degrade tail class accuracy. Diffusion-based generative augmentation address this problem by generating additional data, while head-to-tail transfer further mitigate the…
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…
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…
Unified Speech Recognition (USR) has emerged as a semi-supervised framework for training a single model for audio, visual, and audiovisual speech recognition, achieving state-of-the-art results on in-distribution benchmarks. However, its…
Long-tail learning is the problem of learning under skewed label distributions, which pose a challenge for standard learners. Several recent approaches for the problem have proposed enforcing a suitable margin in logit space. Such…
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,…
Wearable sensor systems have demonstrated a great potential for real-time, objective monitoring of physiological health to support behavioral interventions. However, obtaining accurate labels in free-living environments remains difficult…
Real-world imagery is often characterized by a significant imbalance of the number of images per class, leading to long-tailed distributions. An effective and simple approach to long-tailed visual recognition is to learn feature…
Being able to model correlations between labels is considered crucial in multi-label classification. Rule-based models enable to expose such dependencies, e.g., implications, subsumptions, or exclusions, in an interpretable and…
Long-tailed distribution of semantic categories, which has been often ignored in conventional methods, causes unsatisfactory performance in semantic segmentation on tail categories. In this paper, we focus on the problem of long-tailed…
Despite impressive accuracy, deep neural networks are often miscalibrated and tend to overly confident predictions. Recent techniques like temperature scaling (TS) and label smoothing (LS) show effectiveness in obtaining a well-calibrated…