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 14 pages, and the submission deadline is August 10th, 2024 (AoE). Short papers are limited to 4 pages, and the submission deadline is August 25th, 2024 (AoE). Long papers should use the ECCV template. Short papers can use the CVPR template. Only accepted long papers will be included in the ECCV 2024 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/OODCV2024/Submission/Index.

Important Dates

Description Date
Long paper submission deadline August 10th, 2024 (AoE)
Long paper notification to authors August 15th, 2024 (AoE)
Long paper camera-ready deadline August 31st, 2024 (AoE) Please wait for further instructions from Springer
Short paper submission deadline August 25th, 2024 (AoE)
Short paper notification to authors September 4th7th, 2024 (AoE)

Accepted Papers

  • Open-set object detection: towards unified problem formulation and benchmarking

    Authors: Hejer AMMAR (CEA)*; Nikita Kiselov (-); Guillaume Lapouge (CEA LIST); Romaric Audigier (CEA LIST)

  • Open-Vocabulary Object Detectors: Robustness Challenges under Distribution Shifts

    Authors: Prakash Chandra Chandra Chhipa (Luleå University of Technology)*; Kanjar De (Fraunhofer HHI); Meenakshi Subhash Chippa (Lulea University of Technology); Rajkumar Saini (Luleå tekniska universitet, Luleå, Sweden); Marcus Liwicki (Luleå University of Technology)

  • SOOD-ImageNet: a Large-Scale Dataset for Semantic Out-Of-Distribution Image Classification and Semantic Segmentation

    Authors: Alberto Bacchin (University of Padova)*; Davide Allegro (University of Padova); Stefano Ghidoni (University of Padua); Emanuele Menegatti (Univ of Padova)

  • Online Stochastic Optimization for Time Dependent Data

    Authors: Shivang A Patel (West Virginia University); Ram J Zaveri (West Virginia University)*; Samuel D Chambers (WVU Vision and Learning Group); Zaigham A Randhawa (West Virginia University); Gianfranco Doretto (West Virginia University)

  • A Lost Opportunity for Vision-Language Models: A Comparative Study of Online Test-time Adaptation for Vision-Language Models

    Authors: Mario Döbler (Institute of Signal Processing and System Theory)*; Robert Marsden (Institute of Signal Processing and System Theory); Tobias Raichle (University of Stuttgart); Bin Yang (University of Stuttgart)

  • OSSA: Unsupervised One-Shot Style Adaptation

    Authors: Robin Gerster (TU Delft)*; Michael Teutsch (Hensoldt Optronics); Alexander Wolpert (Hensoldt Optronics GmbH); Matthias Rapp (Hensoldt Optronics GmbH)

  • ZoDi: Zero-Shot Domain Adaptation with Diffusion-Based Image Transfer

    Authors: Hiroki Azuma (The University of Tokyo)*; Yusuke Matsui (The University of Tokyo); Atsuto Maki (KTH Royal Institute of Technology)

  • Open-set Plankton Recognition

    Authors: Joona Kareinen (LUT University)*; Annaliina Skyttä ( Finnish Environment Institute); Tuomas Eerola (LUT University); Kaisa Kraft (Finnish Environment Institute); Lasse Lensu (Lappeenranta-Lahti University of Technology LUT); Sanna Suikkanen (Finnish Environment Institute); Maiju Lehtiniemi (Finnish Environment Institute); Heikki Kälviäinen (Lappeenranta-Lahti University of Technology LUT)

  • Do Vision Foundation Models Enhance Domain Generalization in Medical Image Segmentation?

    Authors: Kerem Cekmeceli (ETH Zurich); Meva Himmetoglu (ETH Zurich); Güney I Tombak (ETH Zürich); Anna Klimovskaia Susmelj (ETH AI Center, CVL ETH Zurich)*; Ertunc Erdil (ETH Zurich); Ender Konukoglu (ETH Zurich)

  • On the Potential of Open-Vocabulary Models for Object Detection in Unusual Street Scenes

    Authors: Sadia Ilyas (Aptiv Gmbh)*; Ido Freeman (Aptiv); Matthias Rottmann (University of Wuppertal)

  • Source-Free Domain Adaptation for YOLO Object Detection

    Authors: Simon Varailhon (École de technologie supérieure)*; Masih Aminbeidokhti (École de technologie supérieure); Marco Pedersoli (École de technologie supérieure); Eric Granger (ETS Montreal )

  • Task-Specific Adaptation of Segmentation Foundation Model via Prompt Learning

    Authors: Hyung-Il Kim (ETRI)*; Kimin Yun (ETRI); Jun-Seok Yun (Korea Institute of Industrial Technology); Yuseok Bae (ETRI)

  • Utilizing Class-Agnostic Point-to-Box Regressors as Object Proposal Generators

    Authors: Gülin Tüfekci Doğan (Aselsan)*; Ramazan Gokberk Cinbis (METU); İlkay Ulusoy (METU)

  • Introducing a Class-Aware Metric for Monocular Depth Estimation: An Automotive Perspective

    Authors: Leon Eisemann (Porsche Engineering Group GmbH)*; Adrian Pogorzelski (Dr. Ing. h.c. F. Porsche AG); Attila-Balazs Kis (Porsche Engineering Services GmbH); Tim Bader (Dr. Ing. h.c. F. Porsche AG); Namrata Jangid (Porsche Engineering Services GmbH)

  • Improving Generalization in Visual Reasoning via Self-Ensemble

    Authors: Huy Tien Nguyen (UIT - University of Information Technology - Ho Chi Minh City - Vietnam)*; Quang-Khai Tran (AI VIETNAM RESEARCH); Tuan Quang (LPL Financial)

  • BelHouse3D: A Benchmark Dataset for Assessing Occlusion Robustness in 3D Point Cloud Semantic Segmentation

    Authors: Umamaheswaran Raman Kumar (KU Leuven)*; Abdur Razzaq Fayjie (KU Leuven); Jurgen Hannaert (3Frog); Patrick Vandewalle (KU Leuven)

  • Image Translation with Kernel Prediction Networks for Semantic Segmentation

    Authors: Cristina Mata (Stony Brook University)*; Michael S Ryoo (Stony Brook/Google); Henrik Turbell (Microsoft)

  • Robust fine-tuning and adaptation of zero-shot models via adaptive weight-space ensembling

    Authors: Mario Döbler (Institute of Signal Processing and System Theory)*; Michael Feil (Universität Stuttgart); Robert Marsden (Institute of Signal Processing and System Theory); Bin Yang (University of Stuttgart)

  • Robustness to Spurious Correlation: A Comprehensive Review [PDF]

    Authors: Mohammadjavad Maheronnaghsh (Sharif University of Technology)*; Taha Akbari Alvanagh (Sharif University of Technology)

  • Feasibility with Language Models for Open-World Compositional Zero-Shot Learning

    Authors: Jae Myung Kim (University of Tuebingen)*; Stephan Alaniz (Helmholtz Munich); Cordelia Schmid (Inria/Google); Zeynep Akata (Technical University of Munich)

  • Harnessing Large-Scale Pre-Trained Models for 3D Semantic Novelty Detection

    Authors: Paolo Rabino (Politecnico di Torino)*; Antonio Alliegro (Politecnico di Torino); Tatiana Tommasi (Politecnico di Torino)

  • Align and Distill: Unifying and Improving Domain Adaptive Object Detection

    Authors: Justin Kay (MIT)*; Timm Haucke (Massachusetts Institute of Technology); Suzanne C Stathatos (Caltech); Siqi Deng (Amazon); Erik Young (Skagit Fisheries Enhancement Group); Pietro Perona (California Institute of Technology); Sara M Beery (MIT); Grant Van Horn (UMass Amherst)

  • Can We Learn to Select the Right Algorithm for OOD Generalization?

    Authors: Liangze Jiang (EPFL/Idiap Research Institute)*; Damien Teney (Idiap Research Institute)

  • VIDA: Unsupervised Visible-to-Infrared Domain Adaptation for Text-Guided Object Detection

    Authors: Chanyeong Park (Chung-ang University); Junbo Jang (Chung-ang University); Joonki Paik (Chungang University)*

  • F-LGAM: Enhancing Single Domain Generalized Object Detection Through Fourier-based Local and Global Amplitude MixUp

    Authors: Chanyeong Park (Chung-ang University); Junbo Jang (Chung-ang University); Joonki Paik (Chungang University)*

  • Revealing Inherent and Counterintuitive Sensitivities of Out-Of-Distribution Detection Methods

    Authors: Christian Huber (Silicon Austria Labs)*; Bernhard Lehner (Silicon Austria Labs); Claus Hofmann (Institute for Machine Learning, Johannes Kepler University Linz); Wei Lin (Johannes Kepler University); Reinhard Feger (Johannes Kepler University Linz); Bernhard A. Moser (Software Competence Center Hagenberg GmbH); Sepp Hochreiter (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University, NXAI GmbH, Linz, Austria)

  • Build To Last: Intransigent Teachers Guide Better Test-Time Adaptation Students

    Authors: Damian Sójka (Poznań University of Technology;IDEAS-NCBR)*; Marc Masana (Graz University of Technology); Bartlomiej Twardowski (Computer Vision Center, UAB); Sebastian Cygert (Gdansk University of Technology;IDEAS-NCBR)

  • Minimizing Embedding Distortion for Robust Out-of-Distribution Performance

    Authors: Oran Shayer (AppsFlyer)*; Yuval Goldman (AppsFlyer); Tom Shaked (AppsFlyer)

  • Analysis of Spatial augmentation in Self-supervised models in the purview of training and test distributions

    Authors: Abhishek Jha (K.U. Leuven)*; Tinne Tuytelaars (KU Leuven)

  • Unified Framework For Confidence Calibration and OOD Detection From Learning Feature Spaces

    Authors: Jinhee Park (Chung-Ang Univ., Korea); Junseok Kwon (Chung-Ang Univ., Korea)*

  • Simultaneously Achieving Robustness to Spurious Correlations and Compressibility in Gradient-based Training

    Authors: Melih Barsbey (Imperial College London)*; Lucas Prieto (Imperial College London); Tolga Birdal (Imperial College London)

  • Benchmarking Generalization of Foundation Models for Remote Sensing

    Authors: Ani Vanyan (YerevaNN, Yerevan State University); Hakob Tamazyan (YerevaNN); Tigran Galstyan (YerevaNN); Alvard Barseghyan (YerevaNN); Vahan Huroyan (Yerevan State University, YerevaNN); Hrant Khachatrian (YerevaNN)*