Call for Papers

We invite submissions of both long and short papers on the topic of out-of-distribution generalization in computer vision. Long papers are limited to 8 pages, and the submission deadline is July 28th, 2023 (AoE). Short papers are limited to 4 pages, and the submission deadline is August 28th, 2023 (AoE). Both should use the ICCV template. Supplementary materials are allowed, but the reviewers will not be required to review them. Only accepted long papers will be included in the ICCV 2023 workshop proceedings. Both accepted long and short papers will be presented as either an oral or poster presentation. At least one author of each accepted submission must present the paper at the workshop. The topics include but are not limited to:
  • Discussion of OOD generalization in the context of internet scale pretrained models
  • Improving generalization of computer vision systems in OOD scenarios
  • Research at the intersection of biological and machine vision
  • Generative causal models for image analysis
  • Domain generalization
  • Novel architectures with robustness to occlusion, viewpoint and other real-world domain shifts
  • Domain adaptation techniques for robust vision system in the real world
  • Datasets for evaluating model robustness

Please submit you paper to the https://cmt3.research.microsoft.com/OODCV2023/Submission/Index. Note that we temporarily closed the system since we are processing the long paper submissions, we will reopen after that is done. Due to the high number of short paper submissions, we have postponed the notification date of the short papers to Sept. 19th AoE.

Important Dates

Description Date
Long paper submission deadline July 28th, 2023 (AoE)
Long paper notification to authors August 8th, 2023 (AoE)
Long paper camera-ready deadline August 21st, 2023 (AoE)
Short paper submission deadline August 28th, 2023 (AoE)
Short paper notification to authors September 4thSeptember 19th, 2023 (AoE)

Accepted Papers

Long Papers

  • [Oral] Confusing Large Models by Confusing Small Models [pdf]

    Authors: Vítor Albiero (Meta AI); Raghav Mehta (McGill University); Ivan Evtimov (Meta AI); Samuel Bell (Meta AI); Levent D Sagun (Facebook AI); Aram H. Markosyan (Meta AI)

  • Misalignment-Free Relation Aggregation for Multi-Source-Free Domain Adaptation [pdf]

    Authors: Hao-Wei Yeh (The University of Tokyo); Qier Meng (Research Center for Advanced Science and Technology, The University of Tokyo); Tatsuya Harada (The University of Tokyo / RIKEN)

  • Consistency Regularization for Generalizable Source-free Domain Adaptation [pdf]

    Authors: Longxiang Tang (Tsinghua University) Kai Li (NEC LABORATORIES AMERICA, INC); Chunming He (Tsinghua University); Yulun Zhang (ETH Zurich); Xiu Li (Tsinghua University)

  • Unsupervised Camouflaged Object Segmentation as Domain Adaptation [pdf]

    Authors: Yi Zhang (ETS Montreal) Chengyi Wu (Henan Polytechnic University)

  • Class-aware Memory Guided Unbiased Weighting for Universal Domain Adaptive Object Detection [pdf]

    Authors: Qinghai Lang (Chongqing University); Zhenwei He (Chongqing University of Technology); XiaoweiFu (Chongqing University); Lei Zhang (Chongqing University)

  • AD-CLIP: Adapting Domains in Prompt Space Using CLIP [pdf]

    Authors: Mainak Singha (Indian Institute of Technology Bombay); Harsh Pal (Indian Institute of Technoloy Bombay); Ankit Jha (Indian Institute of Technology Bombay); Biplab Banerjee (Indian Institute of Technology, Bombay)

  • [Oral] Raising the Bar on the Evaluation of Out-of-Distribution Detection [pdf]

    Authors: Jishnu Mukhoti (University of Oxford); Tsung-Yu Lin (Facebook AI); Bor-Chun Chen (Facebook AI); Ashish Shah (Facebook AI); Philip Torr (University of Oxford); Puneet Dokania (University of Oxford); Ser-Nam Lim (Meta AI)

  • A Re-Parameterized Vision Transformer (ReVT) for Domain-Generalized Semantic Segmentation [pdf]

    Authors: Jan-Aike Termöhlen (Technische Universität Braunschweig); Timo Bartels (Technische Universität Braunschweig); Tim Fingscheidt ( Technische Universität Braunschweig)

  • [Oral] LORD: Leveraging Open-Set Recognition with Unknown Data [pdf]

    Authors: Tobias Koch (e.solutions GmbH); Christian Riess (Friedrich-Alexander University Erlangen-Nuremberg); Thomas Koehler (e.solutions GmbH)

  • Masking Strategies for Backround Bias Removal in Computer Vision Models [pdf]

    Authors: Ananthu Aniraj (Inria); Cassio F. Dantas (TETIS, INRAE, Univ Montpellier); Dino Ienco (INRAE); Diego Marcos (Inria)

  • Assessing the Impact of Diversity on the Resilience of Deep Learning Ensembles: A Comparative Study on Model Architecture, Output, Activation, and Attribution [pdf]

    Authors: Rafael Rosales (Intel); J. Pablo Munoz (Intel); Michael Paulitsch (Intel)

  • DatasetEquity: Are All Samples Created Equal? In The Quest For Equity Within Datasets [pdf]

    Authors: Shubham Shrivastava (Ford Greenfield Labs); Xianling Zhang (Ford Motor Company); Sushruth Nagesh (Ford Motor Company); Armin Parchami (Ford Motor Copany)

  • Benchmarking Image Classifiers for Out-of-Dstribution Adversary Detection [pdf]

    Authors: Ojaswee . (Indian Institute of Science Education and Research Bhopal); Akshay Agarwal (IISER Bhopal); Nalini Ratha (SUNY Buffalo)

  • Gradient Estimation for Uneen Domain Risk Minimization with Pre-Trained Models [pdf]

    Authors: Byounggyu Lew (Hyperconnect); Donghyun Son (VisualCamp); Buru Chang (Sogang University)

  • Leveraging Visual Attention for Out-of-Distribution Detection. [pdf]

    Authors: Luca Cultrera (University of Florence); Lorenzo Seidenari (University of Florence); Alberto Del Bimbo (University of Florence)

  • Improving Shift Invariance with Translation Invariant Polyphase Sampling[pdf]

    Authors: Sourajit Saha (University of Maryland Baltimore County); Tejas Gokhale (University of Maryland Baltimore County)

  • SC2GAN: Rethinking Entanglement by Self-correcting the Correlated GAN Space [pdf]

    Authors: Zikun Chen (ModiFace Inc. ); Han Zhao (University of Illinois at Urbana-Champaign); Parham Aarabi (University of Toronto); Ruowei Jiang (ModiFace Inc.)

  • Can Self-Supervised Representation Learning Methods Withstand Distribution Shifts and Corruptions? [pdf]

    Authors: Prakash Chandra Chhipa (Luleå University of Technology); Johan Tobias Rodahl Holmgren (Luleå Uiversity of Technology); Kanjar De (Luleå University of Technology); Rajkumar Saini (Luleå tekniska universitet, Luleå, Sweden); Marcus Liwicki (Luleå University of Technology)

Short Papers

  • Domain Aware Continual Zero-Shot Learning[pdf]

    Authors: Kai Yi (King Abdullah University of Science and Technology); Paul Janson (University of Moratuwa); Mohamed Elhoseiny (KAUST)

  • Adversarial Bayesian Augmentation for Single-Source Domain Generalization [pdf]

    Authors: Sheng Cheng (Arizona State University); Tejas Gokhale (University of Maryland Baltimore County); Yezhou Yang (Arizona State University)

  • Toward Unsupervised Realistic Visual Question Answering[pdf]

    Authors: Chih-Hui Ho (University of California San Diego); Yuwei Zhang (University of California San Diego); NaYeon Kim (Department of Computer Engineering, Tech University of Korea); SungBal Seo (Department of Computer Engineering, Tech University of Korea); You Suk Bae (Technology University of Korea); Nuno Vasconcelos (University of California San Diego)

  • [Oral] Group-Balanced Mixup for Out of Distribution Generalization[pdf]

    Authors: Sangwoo Hong (Seoul National University); Youngseok Yoon (Seoul National University); Hyungjun Joo (Seoul National University); Jungwoo Lee (Seoul National University)

  • Delving into CLIP latent space for Video Anomaly Detection and Recognition [pdf]

    Authors: Luca Zanella (University of Trento); Benedetta Liberatori (University of Trento); Willi Menapace (University of Trento); Fabio Poiesi (Fondazione Bruno Kessler); Yiming Wang (Fondazione Bruno Kessler); Elisa Ricci (University of Trento)

  • Coupling Vision and Proprioception for Sample-Efficient, Object-Occlusion-Robust Robotic Manipulation[pdf]

    Authors: Samyeul Noh (ETRI); Hyun Myung (KAIST)

  • Semantic Disagreement for Embodied Active Perception [pdf]

    Authors: Gianluca Scarpellini (Istituto Italiano di Tecnologia); Stefano Rosa (Istituto Italiano di Tecnologia); Pietro Morerio (Istituto Italiano di Tecnologia); Lorenzo Natale (Italian Institute of Technology); Alessio Del Bue (Istituto Italiano di Tecnologia (IIT))

  • Familiarity-Based Open-Set Recognition Under Adversarial Attacks [pdf]

    Authors: Philip Enevoldsen (University of Copenhagen); Christian Gundersen (University of Copenhagen); Nico Lang (University of Copenhagen); Serge Belongie (University of Copenhagen); Christian Igel (University of Copenhagen)

  • Differentiable Weight Masks for Domain Transfer [pdf]

    Authors: Samar Khanna (Stanford University); Skanda Vaidyanath (Stanford University); Akash Velu (UC Berkeley)

  • HAct: Out-of-Distribution Detection with Neural Net Activation Histograms [pdf]

    Authors: Sudeepta Mondal (Raytheon Technologies Research Center); Ganesh Sundaramoorthi (RTX)

  • MINR: Implicit Neural Representations with Masked Image Modelling [pdf]

    Authors: Sua Lee (Seoul National University); Joonhun Lee (Seoul National University); Myungjoo Kang (Seoul National University)

  • MATE: Masked Autoencoders are Online 3D Test-Time Learners [pdf]

    Authors: Muhammad Jehanzeb Mirza (Technical University of Graz); Inkyu Shin (KAIST); Wei Lin (Graz University of Technology); Andreas Schriebl (Graz University of Technology); Jaesung Choe (KAIST)

  • Towards Sparse and Debiased Neural Networks: Selective Pruning to overcoming the Simplicity Bias[pdf]

    Authors: Sangwoo Hong (Seoul National University); Hyungjun Joo (Seoul National University); Youngseok Yoon (Seoul National University); Jungwoo Lee (Seoul National University)

  • [Oral] Intriguing Properties of Generative Classifiers [pdf]

    Authors: Priyank Jaini (Google); Kevin Clark (Google DeepMind); Robert Geirhos (Google DeepMind)

  • Text-to-Image Diffusion Models are Zero Shot Classifiers [pdf]

    Authors: Kevin Clark (Google); Priyank Jaini (Google)

  • HyperClass: A Hypernetwork for Few Shot One-Class Classification and Open Set Recognition [pdf]

    Authors: Boaz Lerner (OriginAI); Nir Darshan (OriginAI); Rami Ben-Ari (OriginAI)

  • Weight Averaging Improves Knowledge Distillation under Domain Shift [pdf]

    Authors: Valeriy Berezovskiy (HSE University); Nikita Morozov (HSE University)

  • Towards Class-wise Robustness Analysis [pdf]

    Authors: Tejaswini Medi (University of Siegen); Julia Grabinski (University of Siegen); Margret Keuper (University of Siegen, Max Planck Institute for Informatics)

  • Environment-biased Feature Ranking for Novelty Detection Robustness [pdf]

    Authors: Stefan D Smeu (Bitdefender, University of Bucharest); Elena Burceanu (Bitdefender); Emanuela Haller (Bitdefender); Andrei Nicolicioiu (Bitdefender and Politehnica University of Bucharest)

  • [Oral] Language Plays a Pivotal Role in the Object-Attribute Compositional Generalization of CLIP [pdf]

    Authors: Reza Abbasi (Sharif University of Technology); Mohammad-Mahdi Samiei (Sharif University of Technology); Mohammad Rohban (Sharif University of Technology); Mahdieh Soleymani Baghshah (Sharif University of Technology)

  • Data-Driven Annotation-Free Group Robustness Across Extremely Unbalanced Group Sizes [pdf]

    Authors: Mahdi Ghaznavi (Sharif University of Technology); Hesam Asadollahzadeh (Sharif University of Technology); HamidReza Yaghoubi Araghi (Sharif University of Technology); Fahimeh HosseiniNoohdani (Sharif university of technology); Mohammad Rohban (Sharif University of Technology); Mahdieh Soleymani Baghshah (Sharif University of Technology)

  • Generalized Categories Discovery for Long-tailed Recognition [pdf]

    Authors: Ziyun Li (Hasso Plattner Institute); Meinel Christoph (Hasso Plattner Institute, Potsdam Germany); Haojin Yang (Hasso-Plattner-Institut für Digital Engineering)

  • Mitigating Spurious Correlation in Images by Intervention [pdf]

    Authors: Fahimeh HosseiniNoohdani (Sharif university of technology); Mohammad-Mahdi Samiei (Sharif University of Technology); Parsa Hosseini (Sharif University of Technology); Mahdieh Soleymani Baghshah (Sharif University of Technology)

  • Statistical Guarantees for Safe 2D Object Detection Post-processing[pdf]

    Authors: Emmanouil Seferis (Fraunhofer IKS)

  • Evaluating Robustness of Pre-Trained Deep Neural Networks against Spurious Correlations [pdf]

    Authors: Alireza Hoseinpour (Sharif University of Technology); Majid Taherkhani (Sharif university of technology ); Fahimeh HosseiniNoohdani (Sharif university of technology); Hesam Asadollahzadeh (Sharif University of Technology); Mahdieh Soleymani Baghshah (Sharif University of Technology)