Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-tailed Learning

2022-08-22 · Hualiang Wang, Siming Fu, Xiaoxuan He, Hangxiang Fang, Zuozhu Liu, Haoji Hu

Long-tailed learning aims to tackle the crucial challenge that head classes dominate the training procedure under severe class imbalance in real-world scenarios. However, little attention has been given to how to quantify the dominance severity of head classes in the representation space. Motivated by this, we generalize the cosine-based classifiers to a von Mises-Fisher (vMF) mixture model, denoted as vMF classifier, which enables to quantitatively measure representation quality upon the hyper-sphere space via calculating distribution overlap coefficient. To our knowledge, this is the first work to measure representation quality of classifiers and features from the perspective of distribution overlap coefficient. On top of it, we formulate the inter-class discrepancy and class-feature consistency loss terms to alleviate the interference among the classifier weights and align features with classifier weights. Furthermore, a novel post-training calibration algorithm is devised to zero-costly boost the performance via inter-class overlap coefficients. Our method outperforms previous work with a large margin and achieves state-of-the-art performance on long-tailed image classification, semantic segmentation, and instance segmentation tasks (e.g., we achieve 55.0\% overall accuracy with ResNetXt-50 in ImageNet-LT). Our code is available at https://github.com/VipaiLab/vMF\_OP.

📄 PDF Abstract BibTeX arXiv:2208.10043

Code (1)

vipailab/vmf_op 공식 구현

Tasks

image-classification Image Classification Instance Segmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

SphereFed: Hyperspherical Federated Learning

2022-07-19 · Xin Dong, Sai Qian Zhang, Ang Li, H. T. Kung

Federated Learning aims at training a global model from multiple decentralized devices (i.e. clients) without exchanging their private local data. A key challenge is the handling of non-i.i.d. (independent identically di…

Federated Learning

SphUnc: Hyperspherical Uncertainty Decomposition and Causal Identification via Information Geometry

2026-03-01 · Rong Fu, Chunlei Meng, Jinshuo Liu, Dianyu Zhao 외 arxiv

Reliable decision-making in complex multi-agent systems requires calibrated predictions and interpretable uncertainty. We introduce SphUnc, a unified framework combining hyperspherical representation learning with struct…

Representation Learning

Few-shot Classification with Hypersphere Modeling of Prototypes

2022-11-10 · Ning Ding, Yulin Chen, Ganqu Cui, Xiaobin Wang 외

Metric-based meta-learning is one of the de facto standards in few-shot learning. It composes of representation learning and metrics calculation designs. Previous works construct class representations in different ways, …

Classification Few-Shot Learning Meta-Learning Representation Learning

Deep Orthogonal Hypersphere Compression for Anomaly Detection

2023-02-13 · Yunhe Zhang, Yan Sun, Jinyu Cai, Jicong Fan

Many well-known and effective anomaly detection methods assume that a reasonable decision boundary has a hypersphere shape, which however is difficult to obtain in practice and is not sufficiently compact, especially whe…

Anomaly Detection

Deep Hyperspherical Learning

2017-11-08 · NeurIPS 2017 12 · Weiyang Liu, Yan-Ming Zhang, Xingguo Li, Zhiding Yu 외

Convolution as inner product has been the founding basis of convolutional neural networks (CNNs) and the key to end-to-end visual representation learning. Benefiting from deeper architectures, recent CNNs have demonstrat…