J Shao, K Zhu, H Zhang, J Wu - arXiv preprint arXiv:2403.05170, 2024 - arxiv.org
This paper proposes a new pipeline for long-tail (LT) recognition. Instead of re-weighting or re-sampling, we utilize the long-tailed dataset itself to generate a balanced proxy that can be …
C Wang, Z Yang, ZS Li, D Damian, D Lo - arXiv preprint arXiv:2402.16391, 2024 - arxiv.org
Quality Assurance (QA) aims to prevent mistakes and defects in manufactured products and avoid problems when delivering products or services to customers. QA for AI systems …
E Zhang, C Geng, C Li, S Chen - IEEE Transactions on Circuits …, 2024 - ieeexplore.ieee.org
Logit adjustment is an effective long-tailed visual recognition strategy to encourage a significant margin between rare and dominant labels. Existing methods typically employ the …
Data augmentation for minority classes is an effective strategy for long-tailed recognition, thus developing a large number of methods. Although these methods all ensure the balance …
Long-tailed recognition (LTR) aims to learn balanced models from extremely unbalanced training data. Fine-tuning pretrained foundation models has recently emerged as a …
E Zhang, C Li, C Geng, S Chen - arXiv preprint arXiv:2408.07253, 2024 - arxiv.org
Neural Collapse (NC) presents an elegant geometric structure that enables individual activations (features), class means and classifier (weights) vectors to reach\textit {optimal} …
Recent advancements in computer vision enable machines to perform tasks like image classification, object detection, and instance segmentation with high performance. However …
L Li, XC Li, HJ Ye, DC Zhan - Forty-first International Conference on … - openreview.net
In class-imbalanced learning, the scarcity of information about minority classes presents challenges in obtaining generalizable features for these classes. Leveraging large-scale pre …
Conformal prediction (CP) has emerged as a rigorous means of providing deep learning models with reliable uncertainty estimates and safety guarantees. However, its performance …