Zobrazeno 1 - 10
of 3 733
pro vyhledávání: '"Yang, ZhiYong"'
Real-world datasets often exhibit a long-tailed distribution, where vast majority of classes known as tail classes have only few samples. Traditional methods tend to overfit on these tail classes. Recently, a new approach called Imbalanced SAM (ImbSA
Externí odkaz:
http://arxiv.org/abs/2412.13715
This paper addresses the challenge of Granularity Competition in fine-grained classification tasks, which arises due to the semantic gap between multi-granularity labels. Existing approaches typically develop independent hierarchy-aware models based
Externí odkaz:
http://arxiv.org/abs/2412.12782
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 this end, Jo
Externí odkaz:
http://arxiv.org/abs/2412.07499
Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover
Externí odkaz:
http://arxiv.org/abs/2410.06719
Autor:
Han, Boyu, Xu, Qianqian, Yang, Zhiyong, Bao, Shilong, Wen, Peisong, Jiang, Yangbangyan, Huang, Qingming
The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions.
Externí odkaz:
http://arxiv.org/abs/2409.20398
Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and collaborative filtering. Following the convention of RS, existing practices exploit unique user r
Externí odkaz:
http://arxiv.org/abs/2409.01012
Top-K Pairwise Ranking: Bridging the Gap Among Ranking-Based Measures for Multi-Label Classification
Autor:
Wang, Zitai, Xu, Qianqian, Yang, Zhiyong, Wen, Peisong, He, Yuan, Cao, Xiaochun, Huang, Qingming
Multi-label ranking, which returns multiple top-ranked labels for each instance, has a wide range of applications for visual tasks. Due to its complicated setting, prior arts have proposed various measures to evaluate model performances. However, bot
Externí odkaz:
http://arxiv.org/abs/2407.06709
Autor:
Li, Feiran, Xu, Qianqian, Bao, Shilong, Yang, Zhiyong, Cong, Runmin, Cao, Xiaochun, Huang, Qingming
This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects ar
Externí odkaz:
http://arxiv.org/abs/2405.09782
This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of mu
Externí odkaz:
http://arxiv.org/abs/2405.09321
Autor:
Yang, Zhiyong, Xu, Qianqian, Wang, Zitai, Li, Sicong, Han, Boyu, Bao, Shilong, Cao, Xiaochun, Huang, Qingming
This paper explores test-agnostic long-tail recognition, a challenging long-tail task where the test label distributions are unknown and arbitrarily imbalanced. We argue that the variation in these distributions can be broken down hierarchically into
Externí odkaz:
http://arxiv.org/abs/2405.07780