FORB: A Flat Object Retrieval Benchmark For Universal Image Embedding

Abstract

Image retrieval is a fundamental task in computer vision. Despite recent advances in this field, many techniques have been evaluated on a limited number of domains, with a small number of instance categories. Notably, most existing works only consider domains like 3D landmarks, making it difficult to generalize the conclusions made by these works to other domains, e.g., logo and other 2D flat objects. To bridge this gap, we introduce a new dataset for benchmarking visual search methods on flat images with diverse patterns. Our flat object retrieval benchmark (FORB) supplements the commonly adopted 3D object domain, and more importantly, it serves as a testbed for assessing the image embedding quality on out-of-distribution domains. In this benchmark we investigate the retrieval accuracy of representative methods in terms of candidate ranks, as well as matching score margin, a viewpoint which is largely ignored by many works. Our experiments not only highlight the challenges and rich he

Stats

• citations0
• S2 citations—
• github stars12
• HF likes0
• heat score2.23
• arxiv keywu2023forb

Related papers

• Benchmarking Image Retrieval For Visual Localization (2020)17.78
• Efficient And Discriminative Image Feature Extraction For Universal Image Retrieval (2024)4.94
• FOR: Finetuning For Object Level Open Vocabulary Image Retrieval (2024)0.00
• Visual Product Search Benchmark (2026)0.00
• Investigating The Role Of Image Retrieval For Visual Localization -- An Exhaustive Benchmark (2022)16.58
• Revisiting Oxford And Paris: Large-scale Image Retrieval Benchmarking (2018)17.97
• Object-centric Open-vocabulary Image-retrieval With Aggregated Features (2023)0.00
• General Image Descriptors For Open World Image Retrieval Using Vit CLIP (2022)0.00