{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/adaptive-affinity-fields-for-semantic","title":"Adaptive Affinity Fields for Semantic Segmentation","arxiv_id":"1803.10335","date":"2018-03-27","proceeding":"ECCV 2018 9","authors":["Tsung-Wei Ke","Jyh-Jing Hwang","Ziwei Liu","Stella X. Yu"],"abstract":"Semantic segmentation has made much progress with increasingly powerful\npixel-wise classifiers and incorporating structural priors via Conditional\nRandom Fields (CRF) or Generative Adversarial Networks (GAN). We propose a\nsimpler alternative that learns to verify the spatial structure of segmentation\nduring training only. Unlike existing approaches that enforce semantic labels\non individual pixels and match labels between neighbouring pixels, we propose\nthe concept of Adaptive Affinity Fields (AAF) to capture and match the semantic\nrelations between neighbouring pixels in the label space. We use adversarial\nlearning to select the optimal affinity field size for each semantic category.\nIt is formulated as a minimax problem, optimizing our segmentation neural\nnetwork in a best worst-case learning scenario. AAF is versatile for\nrepresenting structures as a collection of pixel-centric relations, easier to\ntrain than GAN and more efficient than CRF without run-time inference. Our\nextensive evaluations on PASCAL VOC 2012, Cityscapes, and GTA5 datasets\ndemonstrate its above-par segmentation performance and robust generalization\nacross domains.","url_abs":"http://arxiv.org/abs/1803.10335v3","url_pdf":"http://arxiv.org/pdf/1803.10335v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"adaptive-affinity-fields-for-semantic","repo_url":"https://github.com/twke18/Adaptive_Affinity_Fields","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"crf","method_name":"CRF"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"AAF (ResNet-101)","rank_in_archive_order":56,"of":105,"metrics":{"Mean IoU (class)":"79.1%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.10335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.10335"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/twke18/Adaptive_Affinity_Fields","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_honours":1},"by_repo_kind":{},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"9c1264338253562e","entry":"parse_commastr","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"9c1264338253562e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}