{"doi":"10.1109/cvpr.2014.81","title":"Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation","abstract":"Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.","journal":"2014 IEEE Conference on Computer Vision and Pattern Recognition","year":2014,"id":7058,"datarank":20.971894410994366,"base_score":10.357520577896485,"endowment":10.357520577896485,"self_citation_contribution":1.553628086684473,"citation_network_contribution":19.418266324309894,"self_endowment_contribution":1.553628086684473,"citer_contribution":19.418266324309894,"corpus_percentile":98.8,"corpus_rank":185,"citation_count":31492,"citer_count":177,"citers_with_citation_signal":177,"citers_with_endowment":177,"datacite_reuse_total":0,"is_dataset":false,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2014-06-01","authors":[{"id":63939,"name":"Jeff Donahue","orcid":null,"position":1,"is_corresponding":false},{"id":63940,"name":"Trevor Darrell","orcid":"0000-0001-5453-8533","position":2,"is_corresponding":false},{"id":17957,"name":"Jitendra Malik","orcid":"0000-0003-3695-1580","position":3,"is_corresponding":false},{"id":2013,"name":"Ross Girshick","orcid":null,"position":0,"is_corresponding":true}],"reference_count":37,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-03-01T18:20:47.508186Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}