- 博客(22)
- 收藏
- 关注
RSS订阅原创 神经网络不确定性综述(Part V)——Uncertainty measures and quality
(Survey Part V) Uncertainty measures and quality
2024-05-22 13:24:13
835
原创 神经网络不确定性综述(Part IV)——Uncertainty estimation_Ensemble methods&Test-time augmentation
(Survey Part IV) Uncertainty estimation-Ensemble&Test-time augmentation
2024-05-22 13:02:57
719
原创 神经网络不确定性综述(Part III)——Uncertainty estimation_Bayesian neural networks
(Survey Part III) Uncertainty estimation-BNN
2024-05-22 12:54:01
960
原创 神经网络不确定性综述(Part II)——Uncertainty estimation_Single deterministic methods
(Survey Part II) Uncertainty estimation-Deterministic methods
2024-05-22 12:33:05
1330
原创 神经网络不确定性综述(Part I)——A survey of uncertainty in deep neural networks
随着神经网络技术在现实世界中的应用不断广泛，神经网络预测置信度变得越来越重要，尤其是在医学图像分析与自动驾驶等高风险领域。然而，最基本的神经网络并不包含置信度估计的过程，并且通常面临着over-confidence或者under-confidence的问题。针对此问题，研究人员开始关注于量化神经网络预测中存在的uncertainty，由此定义了不同类型、不同来源的uncertainty以及量化uncertainty的技术。
2024-05-22 11:08:50
1547
原创 神经网络机制解释 [NeurIPS 2023 oral]
NeurIPS 2023 oral文章，主题为mechanism explanation of neural networks.
2024-04-25 21:51:38
877
原创 Less is More: Fewer Interpretable Region via Submodular Subset Selection (ICLR 2024, oral)
[ICLR 2024 oral] submodular set selection, attribution methods.
2024-02-19 00:07:59
1475
2
原创 Faithful Vision-Language Interpretation via Concept Bottleneck Models (FVLC)
[可解释深度学习] Faithful Vision-Language Interpretation via Concept Bottleneck Models (FVLC)
2024-02-18 00:59:26
1083
原创 Evidential Deep Learning to Quantify Classification Uncertainty
Evidetial Deep Learning经典论文
2023-12-29 15:09:08
1174
原创 Probabilistic Concept Bottleneck Models (ProbCBM)
[可解释深度学习] Concept-based models-ProbCBM
2023-12-26 17:37:35
824
原创 Label-Free Concept Bottleneck Models (Label-free CBM)
[可解释深度学习] Concept-based models-Label free CBM
2023-12-26 17:33:28
1007
2
原创 Post-hoc Concept Bottleneck Models (PCBM)
[可解释深度学习] Concept-based models-PCBM
2023-12-26 17:29:22
988
原创 Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off (CEM)
[可解释深度学习] Concept-based models-CEM
2023-12-26 17:26:28
808
原创 Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors
[可解释深度学习] Concept-based models-TCAV
2023-12-26 17:14:50
1028
原创 Towards Robust Interpretability with Self-Explaining Neural Networks (SENN)
[可解释深度学习] Concept-based models-SENN
2023-12-26 17:10:26
935
原创 Uncertainty-guided dual-views for semi-supervised volumetric medical image segmentation
基于adversarial learning、multi-view learning以及uncertainty estimation实现semi-supervised volumetric medical image segmentation，文章发表于Nature Machine Intelligence 2023。
2023-12-26 16:59:21
1655
1
原创 Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
[可解释深度学习] 事后可解释模型介绍-Saliency Map
2023-12-23 15:09:29
919
原创 Visualizing and Understanding Convolutional Networks
[可解释深度学习] 事后可解释模型介绍-DeconvNet
2023-12-23 04:29:08
995
原创 [Towards Interpretable Deep Learning] Concept-based Models
[可解释深度学习] Concept-based models论文阅读笔记
2023-12-18 20:49:48
953
原创 MIT 6.S191: Evidential Deep Learning学习笔记
MIT公开课——Evidential Deep Learning
2023-12-15 01:47:50
1922
5
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人