.png){kind=icon}
返回
Exploiting classifier inter-level features for efficient out-of-distribution detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.imavis.2023.104897.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep learning approaches have achieved state-of-the-art performance in a wide range of applications. Most often, however, it is falsely assumed that samples at inference follow a similar distribution as the training data. This assumption impairs models' ability to handle Out-of-Distribution (OOD) data during deployment. While several OOD detection approaches mostly focus on outputs of the last layer, we propose a novel mechanism that exploits features extracted from intermediate layers of a deep classifier. Specifically, we train an off-the-shelf auxiliary network using features of early layers to learn distinctive representations that improve OOD detection. The proposed network can be appended to any classification model without imposing any modification to its original architecture. Additionally, the mechanism does not require access to OOD data during training. We evaluate the performance of the mechanism on a variety of backbone architectures and datasets for near-OOD and far-OOD scenarios. The results demonstrate improvements in OOD detection compared to other state-of-the-art approaches. In particular, our proposed mechanism improves AUROC by 14.2% and 8.3% in comparison to the strong OOD baseline method, and by 3.2% and 3.9% in comparison to the second-best performing approach, on CIFAR-10 and CIFAR-100 datasets respectively.
Keyword:
Out -of -distribution detection
Deep learning -based classification
Machine learning
Feature exploitation
Intermediate feature extraction
期刊
IF:
4.2
论文数:
4.1K
被引数:
6.7K
机构
引用论文
Entropic Out-of-Distribution Detection: Seamless Detection of Unknown Examples熵超出分布检测: 未知示例的无缝检测
OAAI
OAAI分享收藏Detecting out-of-distribution samples via variational auto-encoder with reliable uncertainty estimation.png)
NEURAL NETWORKS
OAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏Multi-label out-of-distribution detection via exploiting sparsity and co-occurrence of labels通过利用标签的稀疏性和共现性进行多标签分布外检测
PREAI
分享收藏Deep Learning Sensor Fusion for Autonomous Vehicle Perception and Localization: A Review用于自动驾驶车辆感知和定位的深度学习传感器融合: 综述SENSORSOAAI
SENSORSIF3.5
OAAI分享收藏
查看更多内容