Deep learning models have achieved great success in many fields, yet they are vulnerable to adversarial examples. This paper follows a causal perspective to look into the adversarial …
Y Zhou, Y Qu, X Xu, H Shen - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Class imbalance is a common challenge in real-world recognition tasks, where the majority of classes have few samples, also known as tail classes. We address this challenge with the …
S Yu, J Guo, R Zhang, Y Fan… - Proceedings of the …, 2022 - openaccess.thecvf.com
Real-world data often exhibits class-imbalanced distributions, where a few classes (aka majority classes) occupy most instances and lots of classes (aka minority classes) have few …
Vision-language models (VLMs) that use contrastive language-image pre-training have shown promising zero-shot classification performance. However, their performance on …
Z Xu, R Liu, S Yang, Z Chai… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
The real-world data tends to be heavily imbalanced and severely skew the data-driven deep neural networks, which makes Long-Tailed Recognition (LTR) a massive challenging task …
Z Zhang, Q Liu, Z Wang, Z Lu… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Deep neural networks (DNNs) are recently shown to be vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by injecting a few poisoned …
Vanilla models for object detection and instance segmentation suffer from the heavy bias toward detecting frequent objects in the long-tailed setting. Existing methods address this …
Foundation models like CLIP allow zero-shot transfer on various tasks without additional training data. Yet, the zero-shot performance is less competitive than a fully supervised one …
Despite the previous success of object analysis, detecting and segmenting a large number of object categories with a long-tailed data distribution remains a challenging problem and is …