Moritz Böhle
9 papers · 2021–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🧭 Keyword Pioneer 🗺️ Taxonomy Completionist (14) 🌍 Conference Polyglot (5) 🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (13)
🔥
Unstoppable
(5)
📈
Trend Setter
Conferences
CVPR (3)
ECCV (2)
ICLR (2)
ICCV (1)
NIPS (1)
Top co-authors
Keywords
attribution method
(3)
neural network
(3)
feature attribution
(2)
convolutional neural network
(2)
model architecture
(2)
neural network interpretability
(1)
visual explanation
(1)
model interpretability
(1)
distribution shift
(1)
interpretable classification
(1)
convolutional network
(1)
interpretable model
(1)
feature visualization
(1)
clip model
(1)
dynamic weight
(1)
post-hoc explanation
(1)
model decision
(1)
model guidance
(1)
weight alignment
(1)
neural network explanation
(1)
Papers
How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations
ICLR 2025
Good Teachers Explain: Explanation-Enhanced Knowledge Distillation
ECCV 2024
B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable
NIPS 2024
Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery
ECCV 2024
Temperature Schedules for self-supervised contrastive methods on long-tail data
ICLR 2023
Studying How to Efficiently and Effectively Guide Models with Explanations
ICCV 2023
B-Cos Networks: Alignment Is All We Need for Interpretability
CVPR 2022
Towards Better Understanding Attribution Methods
CVPR 2022
Convolutional Dynamic Alignment Networks for Interpretable Classifications
CVPR 2021