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

Abstract

Out-of-Distribution (OOD) detection in computer vision is a crucial research area, with related benchmarks playing a vital role in assessing the generalizability of models and their applicability in real-world scenarios. However, existing OOD benchmarks in the literature suffer from two main limitations: (1) they often overlook semantic shift as a potential challenge, and (2) their scale is limited compared to the large datasets used to train modern models. To address these gaps, we introduce SOOD-ImageNet, a novel dataset comprising around 1.6M images across 56 classes, designed for common computer vision tasks such as image classification and semantic segmentation under OOD conditions, with a particular focus on the issue of semantic shift. We ensured the necessary scalability and quality by developing an innovative data engine that leverages the capabilities of modern vision-language models, complemented by accurate human checks. Through extensive training and evaluation of various models on SOOD-ImageNet, we showcase its potential to significantly advance OOD research in computer vision. The project page is available at https://github.com/bach05/SOODImageNet.git.

arXiv commentAccepeted as long paper at "The 3rd Workshop for Out-of-Distribution Generalization in Computer Vision Foundation Models", ECCV 2024

References in corpus (5)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Learning Transferable Visual Models From Natural Language Supervision
• CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification
• Learning from Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation
• VisDA 2022 Challenge: Domain Adaptation for Industrial Waste Sorting