{"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":"/paper/self-supervised-model-adaptation-for","title":"Self-Supervised Model Adaptation for Multimodal Semantic Segmentation","arxiv_id":"1808.03833","date":"2018-08-11","proceeding":null,"authors":["Abhinav Valada","Rohit Mohan","Wolfram Burgard"],"abstract":"Learning to reliably perceive and understand the scene is an integral enabler for robots to operate in the real-world. This problem is inherently challenging due to the multitude of object types as well as appearance changes caused by varying illumination and weather conditions. Leveraging complementary modalities can enable learning of semantically richer representations that are resilient to such perturbations. Despite the tremendous progress in recent years, most multimodal convolutional neural network approaches directly concatenate feature maps from individual modality streams rendering the model incapable of focusing only on relevant complementary information for fusion. To address this limitation, we propose a mutimodal semantic segmentation framework that dynamically adapts the fusion of modality-specific features while being sensitive to the object category, spatial location and scene context in a self-supervised manner. Specifically, we propose an architecture consisting of two modality-specific encoder streams that fuse intermediate encoder representations into a single decoder using our proposed self-supervised model adaptation fusion mechanism which optimally combines complementary features. As intermediate representations are not aligned across modalities, we introduce an attention scheme for better correlation. In addition, we propose a computationally efficient unimodal segmentation architecture termed AdapNet++ that incorporates a new encoder with multiscale residual units and an efficient atrous spatial pyramid pooling that has a larger effective receptive field with more than 10x fewer parameters, complemented with a strong decoder with a multi-resolution supervision scheme that recovers high-resolution details. Comprehensive empirical evaluations on several benchmarks demonstrate that both our unimodal and multimodal architectures achieve state-of-the-art performance.","url_abs":"https://arxiv.org/abs/1808.03833v3","url_pdf":"https://arxiv.org/pdf/1808.03833v3.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":"self-supervised-model-adaptation-for","repo_url":"https://github.com/DeepSceneSeg/SSMA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"scene-recognition","task_name":"Scene Recognition"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"spatial-pyramid-pooling","method_name":"Spatial Pyramid Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-recognition-on-scannet","task":"Scene Recognition","dataset":"ScanNet","model":"SSMA","rank_in_archive_order":1,"of":1,"metrics":{"Average Recall":"54.28"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"SSMA","rank_in_archive_order":29,"of":105,"metrics":{"Mean IoU (class)":"82.3%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"AdapNet++","rank_in_archive_order":46,"of":105,"metrics":{"Mean IoU (class)":"81.24%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-freiburg-forest","task":"Semantic Segmentation","dataset":"Freiburg Forest","model":"SSMA","rank_in_archive_order":1,"of":2,"metrics":{"Mean IoU":"84.18"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-freiburg-forest","task":"Semantic Segmentation","dataset":"Freiburg Forest","model":"AdapNet++","rank_in_archive_order":2,"of":2,"metrics":{"Mean IoU":"83.09"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-sun-rgbd","task":"Semantic Segmentation","dataset":"SUN-RGBD","model":"TokenFusion (S)","rank_in_archive_order":39,"of":44,"metrics":{"Mean IoU":"45.73"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-sun-rgbd","task":"Semantic Segmentation","dataset":"SUN-RGBD","model":"DPLNet","rank_in_archive_order":43,"of":44,"metrics":{"Mean IoU":"38.4"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-synthia-cvpr16","task":"Semantic Segmentation","dataset":"SYNTHIA-CVPR’16","model":"SSMA","rank_in_archive_order":1,"of":2,"metrics":{"Mean IoU":"92.1"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-synthia-cvpr16","task":"Semantic Segmentation","dataset":"SYNTHIA-CVPR’16","model":"AdapNet++","rank_in_archive_order":2,"of":2,"metrics":{"Mean IoU":"87.87"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-scannetv2","task":"Semantic Segmentation","dataset":"ScanNetV2","model":"SSMA","rank_in_archive_order":4,"of":12,"metrics":{"Mean IoU":"57.7"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-scannetv2","task":"Semantic Segmentation","dataset":"ScanNetV2","model":"AdapNet++","rank_in_archive_order":6,"of":12,"metrics":{"Mean IoU":"50.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.03833","atlas_url":"https://app.syntology.ai/?focus=1808.03833","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1808.03833"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1808.03833\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1808.03833"},"call":"get_concepts_for_paper(arxiv_id=\"1808.03833\")"}],"by_repo":[{"repo":"DeepSceneSeg/SSMA","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"bf8d7ed5d4bbc3e9ec0aea9a20db1722bfb44ae2f63456bca58fc14f4d6ebced","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}