{"doi":"10.1109/iccv.2019.00338","title":"Attention Augmented Convolutional Networks","abstract":"Convolutional networks have been the paradigm of choice in many computer vision applications. The convolution operation however has a significant weakness in that it only operates on a local neighborhood, thus missing global information. Self-attention, on the other hand, has emerged as a recent advance to capture long range interactions, but has mostly been applied to sequence modeling and generative modeling tasks. In this paper, we consider the use of self-attention for discriminative visual tasks as an alternative to convolutions. We introduce a novel two-dimensional relative self-attention mechanism that proves competitive in replacing convolutions as a stand-alone computational primitive for image classification. We find in control experiments that the best results are obtained when combining both convolutions and self-attention. We therefore propose to augment convolutional operators with this self-attention mechanism by concatenating convolutional feature maps with a set of feature maps produced via self-attention. Extensive experiments show that Attention Augmentation leads to consistent improvements in image classification on ImageNet and object detection on COCO across many different models and scales, including ResNets and a state-of-the art mobile constrained network, while keeping the number of parameters similar. In particular, our method achieves a $1.3\\%$ top-1 accuracy improvement on ImageNet classification over a ResNet50 baseline and outperforms other attention mechanisms for images such as Squeeze-and-Excitation. It also achieves an improvement of 1.4 mAP in COCO Object Detection on top of a RetinaNet baseline.","journal":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","year":2019,"id":7154,"datarank":1.016988286120838,"base_score":6.779921907472252,"endowment":6.779921907472252,"self_citation_contribution":1.016988286120838,"citation_network_contribution":0.0,"self_endowment_contribution":1.016988286120838,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":879,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.0464,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2019-10-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":64757,"name":"Barret Zoph","orcid":null,"position":1,"is_corresponding":false},{"id":64758,"name":"Quoc Le","orcid":null,"position":2,"is_corresponding":false},{"id":64759,"name":"Ashish Vaswani","orcid":"0000-0002-7794-2085","position":3,"is_corresponding":false},{"id":64760,"name":"Jonathon Shlens","orcid":"0000-0001-9513-4244","position":4,"is_corresponding":false},{"id":64756,"name":"Irwan Bello","orcid":null,"position":0,"is_corresponding":true}],"reference_count":55,"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,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}