Publications

Interpretability

The Importance of Prompt Tuning for Automated Neuron Explanations

• J. Lee*, T. Oikarinen*, A. Chatha, K.C. Chang, Y.Chen, T.W. Weng
• NeurIPS 2023 ATTRIB workshop

Label-Free Concept Bottleneck Models

• T. Oikarinen, S. Das, L.M. Nguyen, T.W. Weng
• ICLR 2023, code, video presentation

CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks

• T. Oikarinen, T.W. Weng
• ICLR 2023 Spotlight, code, video presentation

Robustness

Corrupting Neuron Explanations of Deep Visual Features

• D. Srivastava, T. Oikarinen, T.W. Weng
• ICCV 2023, code

Robust Deep Reinforcement Learning through Adversial Loss

• T. Oikarinen, W. Zhang, A. Megretski, L. Daniel, T.W. Weng
• NeurIPS 2021, code, video presentation

Applied ML

GraphMDN: Leveraging Graph Structure and Deep Learning to Solve Inverse Problems

• T. Oikarinen, D. Hannah, S.Kazerounian
• IJCNN 2021, code

Landslide Geohazard Assessment with Convolutional Neural Networks using Sentinel-2 Imagery Data

• S. Ullo, M. Langenkamp, T. Oikarinen, M.P. Del Rosso, A. Sebastianelli, F. Piccirillo, S. Sica
• IEEE IGARSS 2019, code

Deep Convolutional Network for Animal Sound Classification and Source Attribution using Dual Audio Recordings

• T. Oikarinen, K. Srinivasan, O. Meisner, J. Hyman, S. Parmar, A. Fanucci-Kiss, R. Desimone, R. Landman, G. Feng
• The Journal of the Acoustical Society of America, 2019, code