{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/deeplab","slug":"deeplab","name":"DeepLab","full_name":"DeepLab","full_name_withheld":false,"description_markdown":"**DeepLab** is a semantic segmentation architecture. First, the input image goes through the network with the use of dilated convolutions. Then the output from the network is bilinearly interpolated and goes through the fully connected [CRF](https://paperswithcode.com/method/crf) to fine tune the result we obtain the final predictions.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"http://arxiv.org/abs/1412.7062v4","title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/tensorflow/models/tree/master/research/deeplab","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Semantic Segmentation Models","url":"/methods/category/semantic-segmentation-models","pwc_aliases":["segmentation-models"]}],"n_papers_tagged":55,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"slug":"weakly-supervised-localization-of-manipulated","title":"Weakly-supervised Localization of Manipulated Image Regions Using Multi-resolution Learned Features","date":"2025-05-29","arxiv_id":"2505.23586","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-approaches-to-surgical-video","title":"Deep learning approaches to surgical video segmentation and object detection: A Scoping Review","date":"2025-02-23","arxiv_id":"2502.16459","n_code_links":0,"syntology":null},{"paper":"/paper/ai-driven-water-segmentation-with-deep","slug":"ai-driven-water-segmentation-with-deep","title":"AI Driven Water Segmentation with deep learning models for Enhanced Flood Monitoring","date":"2025-01-14","arxiv_id":"2501.08266","n_code_links":1,"syntology":null},{"paper":"/paper/hyperspectral-imaging-based-perception-in","slug":"hyperspectral-imaging-based-perception-in","title":"Hyperspectral Imaging-Based Perception in Autonomous Driving Scenarios: Benchmarking Baseline Semantic Segmentation Models","date":"2024-10-29","arxiv_id":"2410.22101","n_code_links":1,"syntology":null},{"paper":null,"slug":"automated-road-extraction-from-satellite","title":"Automated Road Extraction from Satellite Imagery Integrating Dense Depthwise Dilated Separable Spatial Pyramid Pooling with DeepLabV3+","date":"2024-10-18","arxiv_id":"2410.14836","n_code_links":0,"syntology":null},{"paper":null,"slug":"squeeze-and-remember-block","title":"Squeeze-and-Remember Block","date":"2024-10-01","arxiv_id":"2410.00823","n_code_links":0,"syntology":null},{"paper":null,"slug":"ela-efficient-local-attention-for-deep","title":"ELA: Efficient Local Attention for Deep Convolutional Neural Networks","date":"2024-03-02","arxiv_id":"2403.01123","n_code_links":0,"syntology":null},{"paper":null,"slug":"equirectangular-image-construction-method-for","title":"Equirectangular image construction method for standard CNNs for Semantic Segmentation","date":"2023-10-13","arxiv_id":"2310.09122","n_code_links":0,"syntology":null},{"paper":null,"slug":"automating-global-landslide-detection-with","title":"Automating global landslide detection with heterogeneous ensemble deep-learning classification","date":"2023-09-12","arxiv_id":"2310.05959","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-validation-in-structure-from-motion","slug":"semantic-validation-in-structure-from-motion","title":"Semantic Validation in Structure from Motion","date":"2023-04-05","arxiv_id":"2304.02420","n_code_links":1,"syntology":null},{"paper":null,"slug":"i2f-a-unified-image-to-feature-approach-for","title":"I2F: A Unified Image-to-Feature Approach for Domain Adaptive Semantic Segmentation","date":"2023-01-03","arxiv_id":"2301.01149","n_code_links":0,"syntology":null},{"paper":null,"slug":"hypergraph-convolutional-networks-for-weakly","title":"Hypergraph Convolutional Networks for Weakly-Supervised Semantic Segmentation","date":"2022-10-11","arxiv_id":"2210.05564","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-segmentation-of-microvessels-in","title":"Automated segmentation of microvessels in intravascular OCT images using deep learning","date":"2022-10-01","arxiv_id":"2210.00166","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-method-for-data-augmentation-nine-dot","title":"A novel method for data augmentation: Nine Dot Moving Least Square (ND-MLS)","date":"2022-08-24","arxiv_id":"2208.11532","n_code_links":0,"syntology":null},{"paper":"/paper/transdeeplab-convolution-free-transformer","slug":"transdeeplab-convolution-free-transformer","title":"TransDeepLab: Convolution-Free Transformer-based DeepLab v3+ for Medical Image Segmentation","date":"2022-08-01","arxiv_id":"2208.00713","n_code_links":1,"syntology":null},{"paper":"/paper/waymo-open-dataset-panoramic-video-panoptic","slug":"waymo-open-dataset-panoramic-video-panoptic","title":"Waymo Open Dataset: Panoramic Video Panoptic Segmentation","date":"2022-06-15","arxiv_id":"2206.07704","n_code_links":1,"syntology":null},{"paper":"/paper/doodlenet-double-deeplab-enhanced-feature","slug":"doodlenet-double-deeplab-enhanced-feature","title":"DooDLeNet: Double DeepLab Enhanced Feature Fusion for Thermal-color Semantic Segmentation","date":"2022-04-21","arxiv_id":"2204.10266","n_code_links":0,"syntology":null},{"paper":"/paper/ftnet-feature-transverse-network-for-thermal","slug":"ftnet-feature-transverse-network-for-thermal","title":"FTNet: Feature Transverse Network for Thermal Image Semantic Segmentation","date":"2021-10-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/estimation-of-road-boundary-for-intelligent","slug":"estimation-of-road-boundary-for-intelligent","title":"Estimation of Road Boundary for Intelligent Vehicles Based on DeepLabV3+ Architecture","date":"2021-08-24","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/a-system-of-vision-sensor-based-deep-neural","slug":"a-system-of-vision-sensor-based-deep-neural","title":"A system of vision sensor based deep neural networks for complex driving scene analysis in support of crash risk assessment and prevention","date":"2021-06-18","arxiv_id":"2106.10319","n_code_links":2,"syntology":null},{"paper":"/paper/deeplab2-a-tensorflow-library-for-deep","slug":"deeplab2-a-tensorflow-library-for-deep","title":"DeepLab2: A TensorFlow Library for Deep Labeling","date":"2021-06-17","arxiv_id":"2106.09748","n_code_links":4,"syntology":null},{"paper":null,"slug":"deep-ensembles-based-on-stochastic-activation","title":"Deep ensembles based on Stochastic Activation Selection for Polyp Segmentation","date":"2021-04-02","arxiv_id":"2104.00850","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-feature-augmentation-and","slug":"adversarial-feature-augmentation-and","title":"Adversarial Feature Augmentation and Normalization for Visual Recognition","date":"2021-03-22","arxiv_id":"2103.12171","n_code_links":1,"syntology":{"ran":5,"of":11,"n_ran_checked":5,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["VITA-Group/CV_A-FAN"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"rethnet-object-by-object-learning-for","title":"RethNet: Object-by-Object Learning for Detecting Facial Skin Problems","date":"2021-01-06","arxiv_id":"2101.02127","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-model-trained-on-mobile-phone","title":"Deep learning model trained on mobile phone-acquired frozen section images effectively detects basal cell carcinoma","date":"2020-11-22","arxiv_id":"2011.11081","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-lf-net-semantic-lung-segmentation-from","title":"Deep LF-Net: Semantic Lung Segmentation from Indian Chest Radiographs Including Severely Unhealthy Images","date":"2020-11-19","arxiv_id":"2011.09695","n_code_links":0,"syntology":null},{"paper":null,"slug":"task-adaptive-feature-transformer-for-few","title":"Task-Adaptive Feature Transformer for Few-Shot Segmentation","date":"2020-10-22","arxiv_id":"2010.11437","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-attention-network-for-semantic","title":"Multi-Attention-Network for Semantic Segmentation of Fine Resolution Remote Sensing Images","date":"2020-09-03","arxiv_id":"2009.02130","n_code_links":0,"syntology":null},{"paper":null,"slug":"reinforced-wasserstein-training-for-severity","title":"Reinforced Wasserstein Training for Severity-Aware Semantic Segmentation in Autonomous Driving","date":"2020-08-11","arxiv_id":"2008.04751","n_code_links":0,"syntology":null},{"paper":"/paper/macu-net-semantic-segmentation-from-high","slug":"macu-net-semantic-segmentation-from-high","title":"MACU-Net for Semantic Segmentation of Fine-Resolution Remotely Sensed Images","date":"2020-07-26","arxiv_id":"2007.13083","n_code_links":2,"syntology":null},{"paper":null,"slug":"severity-aware-semantic-segmentation-with","title":"Severity-Aware Semantic Segmentation With Reinforced Wasserstein Training","date":"2020-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"very-high-resolution-land-cover-mapping-of","title":"Very High Resolution Land Cover Mapping of Urban Areas at Global Scale with Convolutional Neural Networks","date":"2020-05-12","arxiv_id":"2005.05652","n_code_links":0,"syntology":null},{"paper":null,"slug":"y-net-biomedical-image-segmentation-and","title":"Y-net: Biomedical Image Segmentation and Clustering","date":"2020-04-12","arxiv_id":"2004.05698","n_code_links":0,"syntology":null},{"paper":"/paper/learning-dynamic-routing-for-semantic","slug":"learning-dynamic-routing-for-semantic","title":"Learning Dynamic Routing for Semantic Segmentation","date":"2020-03-23","arxiv_id":"2003.10401","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"improving-learning-effectiveness-for-object","title":"Improving Learning Effectiveness For Object Detection and Classification in Cluttered Backgrounds","date":"2020-02-27","arxiv_id":"2002.12467","n_code_links":0,"syntology":null},{"paper":"/paper/lake-ice-monitoring-with-webcams-and-crowd","slug":"lake-ice-monitoring-with-webcams-and-crowd","title":"Lake Ice Monitoring with Webcams and Crowd-Sourced Images","date":"2020-02-18","arxiv_id":"2002.07875","n_code_links":2,"syntology":null},{"paper":"/paper/photi-lakeice-dataset","slug":"photi-lakeice-dataset","title":"Photi-LakeIce Dataset","date":"2020-02-18","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarial-loss-for-semantic-segmentation-of","title":"Adversarial Loss for Semantic Segmentation of Aerial Imagery","date":"2020-01-13","arxiv_id":"2001.04269","n_code_links":0,"syntology":null},{"paper":null,"slug":"land-cover-change-detection-via-semantic","title":"Land Cover Change Detection via Semantic Segmentation","date":"2019-11-28","arxiv_id":"1911.12903","n_code_links":0,"syntology":null},{"paper":null,"slug":"cost-efficient-segmentation-of-electron","title":"Cost-efficient segmentation of electron microscopy images using active learning","date":"2019-11-13","arxiv_id":"1911.05548","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-classification-network-for-monocular","title":"Deep Classification Network for Monocular Depth Estimation","date":"2019-10-23","arxiv_id":"1910.10369","n_code_links":0,"syntology":null},{"paper":null,"slug":"feedbackward-decoding-for-semantic","title":"Feedbackward Decoding for Semantic Segmentation","date":"2019-08-22","arxiv_id":"1908.08584","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-cloud-segmentation-in-high","title":"End-to-end Cloud Segmentation in High-Resolution Multispectral Satellite Imagery Using Deep Learning","date":"2019-04-29","arxiv_id":"1904.12743","n_code_links":0,"syntology":null},{"paper":"/paper/spatially-adaptive-filter-units-for-compact","slug":"spatially-adaptive-filter-units-for-compact","title":"Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networks","date":"2019-02-20","arxiv_id":"1902.07474","n_code_links":3,"syntology":null},{"paper":"/paper/highly-efficient-follicular-segmentation-in","slug":"highly-efficient-follicular-segmentation-in","title":"Highly Efficient Follicular Segmentation in Thyroid Cytopathological Whole Slide Image","date":"2019-02-13","arxiv_id":"1902.05431","n_code_links":1,"syntology":null},{"paper":null,"slug":"sensor-adaptation-for-improved-semantic","title":"Sensor Adaptation for Improved Semantic Segmentation of Overhead Imagery","date":"2018-11-20","arxiv_id":"1811.08328","n_code_links":0,"syntology":null},{"paper":null,"slug":"mask-propagation-network-for-video-object","title":"Mask Propagation Network for Video Object Segmentation","date":"2018-10-24","arxiv_id":"1810.10289","n_code_links":0,"syntology":null},{"paper":"/paper/associating-inter-image-salient-instances-for","slug":"associating-inter-image-salient-instances-for","title":"Associating Inter-Image Salient Instances for Weakly Supervised Semantic Segmentation","date":"2018-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/single-image-water-hazard-detection-using-fcn","slug":"single-image-water-hazard-detection-using-fcn","title":"Single Image Water Hazard Detection using FCN with Reflection Attention Units","date":"2018-09-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/skin-lesion-segmentation-using-atrous","slug":"skin-lesion-segmentation-using-atrous","title":"Skin Lesion Segmentation Using Atrous Convolution via DeepLab v3","date":"2018-07-24","arxiv_id":"1807.08891","n_code_links":0,"syntology":null},{"paper":null,"slug":"in-pixels-we-trust-from-pixel-labeling-to","title":"In pixels we trust: From Pixel Labeling to Object Localization and Scene Categorization","date":"2018-07-19","arxiv_id":"1807.07284","n_code_links":0,"syntology":null},{"paper":null,"slug":"vortex-pooling-improving-context","title":"Vortex Pooling: Improving Context Representation in Semantic Segmentation","date":"2018-04-17","arxiv_id":"1804.06242","n_code_links":0,"syntology":null},{"paper":"/paper/per-pixel-feedback-for-improving-semantic","slug":"per-pixel-feedback-for-improving-semantic","title":"Per-Pixel Feedback for improving Semantic Segmentation","date":"2017-12-07","arxiv_id":"1712.02861","n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarially-tuned-scene-generation","title":"Adversarially Tuned Scene Generation","date":"2017-01-02","arxiv_id":"1701.00405","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-image-segmentation-with-deep","slug":"semantic-image-segmentation-with-deep","title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","date":"2014-12-22","arxiv_id":"1412.7062","n_code_links":18,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["bitbucket.org/deeplab/deeplab-public"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}}],"papers_shown":55,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":55,"with_a_code_link":19,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":55,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/method/deeplab/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/deeplab/papers/ran/1","json":"/method/deeplab/papers/ran/1.json","rows":2}],"tasks":[{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":42},{"task":"/task/segmentation","name":"Segmentation","papers":27},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":12},{"task":"/task/object-detection-1","name":"object-detection","papers":8},{"task":"/task/object-detection","name":"Object Detection","papers":7},{"task":"/task/decoder","name":"Decoder","papers":6},{"task":"/task/autonomous-vehicles","name":"Autonomous Vehicles","papers":5},{"task":"/task/classification","name":"General Classification","papers":5},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":4},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":4},{"task":"/task/management","name":"Management","papers":4},{"task":"/task/scene-understanding","name":"Scene Understanding","papers":4},{"task":"/task/image-classification","name":"image-classification","papers":4},{"task":"/task/classification-1","name":"Classification","papers":3},{"task":"/task/image-classification","name":"Image Classification","papers":3},{"task":"/task/medical-image-analysis","name":"Medical Image Analysis","papers":3},{"task":"/task/medical-image-segmentation","name":"Medical Image Segmentation","papers":3},{"task":"/task/change-detection","name":"Change Detection","papers":2},{"task":"/task/change-detection-for-remote-sensing-images","name":"Change detection for remote sensing images","papers":2},{"task":"/task/clustering","name":"Clustering","papers":2}],"tasks_shown":20,"n_tasks":74,"usage_by_year":[{"year":"2014","papers":1},{"year":"2017","papers":2},{"year":"2018","papers":7},{"year":"2019","papers":7},{"year":"2020","papers":14},{"year":"2021","papers":7},{"year":"2022","papers":6},{"year":"2023","papers":4},{"year":"2024","papers":4},{"year":"2025","papers":3}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/deeplab"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=DeepLab","read_at":"2026-10-05T00:54:38+00:00","query":"DeepLab","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"DeepLab","origin_arxiv_id":"1606.00915"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"unknown","archive_paper_arxiv_id":null,"repositories":{"listed":5,"in_graph":46,"list_truncated":true,"strongest_link":"mentioned_in_github"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"1606.00915","citations":21538},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'DeepLab'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"1606.00915","page":"/paper/deeplab-semantic-image-segmentation-with-deep","syntology_url":"https://syntology.ai/paper/1606.00915","in_graph_layer":true,"samples":63,"ran":43,"n_ran_checked":35,"n_instrument":8,"unverified":20,"phrase":"43 ran (of which 12 constructed an object rather than computing a result; 35 with no instrument failure: 1 honoured, 0 violated, 34 with no contract checked; 8 where Syntology's instrument failed) · 20 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"repository known, no verified implementation (declared_code; repositories: 5 listed of 46 in the graph, strongest link: mentioned on GitHub). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:1606.00915) is about this method is not checked.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"40240038d5f72e18c6e77c06e7e65cc11dcadc0156675e7f41c42622a0a03438","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}