Research map / Detection and segmentation / Open-set and few-shot detection
Does Progress On Object Recognition Benchmarks Improve Generalization on Crowdsourced, Global Data?
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Examines whether gains on object recognition benchmarks (ImageNet and its generalization variants) transfer to crowdsourced, globally diverse data, using the abstract's framing of brittle foundation models.
Problem
Object recognition benchmarks such as ImageNet, ImageNet-A, -C, and -R are nearly saturated by foundation models, yet models remain brittle in practice; it is unclear whether benchmark progress improves generalization on crowdsourced, global data.
Approach
Evaluates progress on object recognition against crowdsourced, globally collected image data to test whether benchmark gains translate to real-world generalization (details beyond the abstract not available).
Experimental setup
Datasets: ImageNet ImageNet-A ImageNet-C ImageNet-R
Benchmarks: ImageNet ImageNet-A ImageNet-C ImageNet-R
Closest papers by meaning
- Object Detection Benchmarks are Incomplete: The Role of Label Errors and Annotation Uncertainty (NeurIPS 2026 · similarity 0.88)
- COUNTS: Benchmarking Object Detectors and Multimodal Large Language Models under Distribution Shifts (CVPR 2025 · similarity 0.87)
- How to Evaluate the Generalization of Detection? A Benchmark for Comprehensive Open-Vocabulary Detection (AAAI 2024 · similarity 0.87)
- Benchmarking Object Detectors under Real-World Distribution Shifts in Satellite Imagery (CVPR 2025 · similarity 0.87)
- SELECT: A Large-Scale Benchmark of Data Curation Strategies for Image Classification (NeurIPS 2024 · similarity 0.87)
- Doomed to Re-Annotate, Forever: The ImageNet Story (NeurIPS 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.