Accepted Papers
Best Paper
ID 3: Maximum Entropy Information Bottleneck for Uncertainty-aware Stochastic Embedding
Sungtae An (Georgia Institue of Technology ); Nataraj Jammalamadaka (Amazon); Eunji Chong (Amazon)
Long Oral + Poster
ID 1: Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations
Maximilian Dreyer (Fraunhofer HHI); Reduan Achtibat (Fraunhofer HHI); Thomas Wiegand (Fraunhofer-Institut für Nachrichtentechnik, Heinrich-Hertz-Institut, HHI); Wojciech Samek (Fraunhofer HHI); Sebastian Lapuschkin (Fraunhofer Heinrich Hertz Institute)
ID 2: RL-CAM: Visual Explanations for Convolutional Networks using Reinforcement Learning
Soumyendu Sarkar (Hewlett Packard Enterprise); Ashwin Ramesh Babu (Hewlett Packard Enterprise Labs); Sajad Mousavi (Hewlett Packard Enterprise); Vineet Gundecha (Hewlett Packard Enterpise); Sahand Ghorbanpour (Hewlett Packard Enterprise); Ricardo Luna Gutierrez (Hewlett Packard Enterprise); Antonio Guillen (Hewlett Packard Enterprise); Avisek Naug (Hewlett Packard Enterprise)
ID 3: Maximum Entropy Information Bottleneck for Uncertainty-aware Stochastic Embedding
Sungtae An (Georgia Institue of Technology ); Nataraj Jammalamadaka (Amazon); Eunji Chong (Amazon)
ID 4: Optimizing Explanations by Network Canonization and Hyperparameter Search
Frederik Pahde (Fraunhofer Heinrich Hertz Institute); Galip Ü. Yolcu (Fraunhofer HHI); Alexander Binder (University of Oslo); Wojciech Samek (Fraunhofer HHI); Sebastian Lapuschkin (Fraunhofer Heinrich Hertz Institute)
ID 5: Beyond AUROC & co for evaluating out-of-distribution detection performance
Galadrielle Humblot-Renaux (Aalborg University); Sergio Escalera (); Thomas B. Moeslund (Aalborg University)
Short Oral + Poster
ID 6: Uncovering the Inner Workings of STEGO for Safe Unsupervised Semantic Segmentation
Alexander Koenig (Merantix Momentum GmbH); Maximilian Schambach (Merantix Momentum); Johannes Otterbach (Merantix Momentum GmbH)
ID 7: Coherent Concept-based Explanations in Medical Image and Its Application to Skin Lesion Diagnosis
Cristiano Patrício (Universidade da Beira Interior); João Neves (Tomiworld); Luis Teixeira (INESC TEC and University of Porto)
ID 8: Investigating CLIP Performance for Meta-data Generation in AD Datasets
Sujan Gannamaneni (Fraunhofer IAIS); Arwin Sadaghiani (Fraunhofer IAIS); Rohil Prakash Rao (Uni Bonn); Michael Mock (Fraunhofer IAIS); Maram Akila (Fraunhofer IAIS)
ID 9: A Novel Benchmark for Refinement of Noisy Localization Labels in Autolabeled Datasets for Object Detection
Andreas Bär (Technische Universität Braunschweig)*; Jonas Uhrig (Mercedes-Benz); Jeethesh Pai Umesh (TU Braunschweig); Marius Cordts (Mercedes-Benz AG); Tim Fingscheidt ( Technische Universität Braunschweig)
ID 10: Category Differences Matter: A Broad Analysis of Inter-Category Error in Semantic Segmentation
Jingxing Zhou (Porsche Engineering Services GmbH); Jürgen Beyerer (Fraunhofer IOSB)
ID 11: Interpretable Model-Agnostic Plausibility Verification for 2D Object Detectors Using Domain-Invariant Concept Bottleneck Models
Mert Keser (TUM); Gesina Schwalbe (Continental Automotive GmbH); Azarm Nowzad (Continental); Alois Knoll (Technical University of Munich)
Poster Size
84” x 42” = 213 cm x 107cm (WxH, aspect ratio 2:1, landscape format)
Poster template https://docs.google.com/presentation/d/1Bj5-kxm6dFHkrq23Ux_9ytk5DUwx1tHW/edit#slide=id.p1
Poster Printing Service:
https://cvpr2023.thecvf.com/Conferences/2023/PosterPrintingInformation