{"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/dformer-rethinking-rgbd-representation","title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","arxiv_id":"2309.09668","date":"2023-09-18","proceeding":null,"authors":["Bowen Yin","Xuying Zhang","Zhongyu Li","Li Liu","Ming-Ming Cheng","Qibin Hou"],"abstract":"We present DFormer, a novel RGB-D pretraining framework to learn transferable representations for RGB-D segmentation tasks. DFormer has two new key innovations: 1) Unlike previous works that encode RGB-D information with RGB pretrained backbone, we pretrain the backbone using image-depth pairs from ImageNet-1K, and hence the DFormer is endowed with the capacity to encode RGB-D representations; 2) DFormer comprises a sequence of RGB-D blocks, which are tailored for encoding both RGB and depth information through a novel building block design. DFormer avoids the mismatched encoding of the 3D geometry relationships in depth maps by RGB pretrained backbones, which widely lies in existing methods but has not been resolved. We finetune the pretrained DFormer on two popular RGB-D tasks, i.e., RGB-D semantic segmentation and RGB-D salient object detection, with a lightweight decoder head. Experimental results show that our DFormer achieves new state-of-the-art performance on these two tasks with less than half of the computational cost of the current best methods on two RGB-D semantic segmentation datasets and five RGB-D salient object detection datasets. Our code is available at: https://github.com/VCIP-RGBD/DFormer.","url_abs":"https://arxiv.org/abs/2309.09668v2","url_pdf":"https://arxiv.org/pdf/2309.09668v2.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":"dformer-rethinking-rgbd-representation","repo_url":"https://github.com/VCIP-RGBD/DFormer","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-geometry","task_name":"3D geometry"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"rgb-d-salient-object-detection","task_name":"RGB-D Salient Object Detection"},{"task_slug":null,"task_name":"RGBD Semantic Segmentation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"salient-object-detection-1","task_name":"Salient Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/rgb-d-salient-object-detection-on-des","task":"RGB-D Salient Object Detection","dataset":"DES","model":"DFormer-L","rank_in_archive_order":1,"of":13,"metrics":{"Average MAE":"0.013","S-Measure":"94.8","max E-Measure":"98.0","max F-Measure":"95.6"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-nju2k","task":"RGB-D Salient Object Detection","dataset":"NJU2K","model":"DFormer-L","rank_in_archive_order":1,"of":27,"metrics":{"Average MAE":"0.023","S-Measure":"93.7","max E-Measure":"96.4","max F-Measure":"94.6"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-nlpr","task":"RGB-D Salient Object Detection","dataset":"NLPR","model":"DFormer-L","rank_in_archive_order":1,"of":14,"metrics":{"Average MAE":"0.016","S-Measure":"94.2","max E-Measure":"97.1","max F-Measure":"93.9"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-sip","task":"RGB-D Salient Object Detection","dataset":"SIP","model":"DFormer-L","rank_in_archive_order":1,"of":16,"metrics":{"Average MAE":"0.032","S-Measure":"91.5","max E-Measure":"95.0","max F-Measure":"93.8"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-stere","task":"RGB-D Salient Object Detection","dataset":"STERE","model":"DFormer-L","rank_in_archive_order":1,"of":14,"metrics":{"Average MAE":"0.030","S-Measure":"92.3","max E-Measure":"95.2","max F-Measure":"92.9"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"DFormer-L","rank_in_archive_order":16,"of":121,"metrics":{"Mean IoU":"57.2%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"DFormer-B","rank_in_archive_order":25,"of":121,"metrics":{"Mean IoU":"55.6%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"DFormer-S","rank_in_archive_order":33,"of":121,"metrics":{"Mean IoU":"53.6%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"DFormer-T","rank_in_archive_order":50,"of":121,"metrics":{"Mean IoU":"51.8%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-sun-rgbd","task":"Semantic Segmentation","dataset":"SUN-RGBD","model":"DFormer-L","rank_in_archive_order":10,"of":44,"metrics":{"Mean IoU":"52.5%"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-sun-rgbd","task":"Semantic Segmentation","dataset":"SUN-RGBD","model":"DFormer-B","rank_in_archive_order":15,"of":44,"metrics":{"Mean IoU":"51.2%"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-sun-rgbd","task":"Semantic Segmentation","dataset":"SUN-RGBD","model":"TokenFusion (S)","rank_in_archive_order":19,"of":44,"metrics":{"Mean IoU":"50.0%"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-sun-rgbd","task":"Semantic Segmentation","dataset":"SUN-RGBD","model":"FSFNet","rank_in_archive_order":27,"of":44,"metrics":{"Mean IoU":"48.8%"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-syn-udtiri","task":"Semantic Segmentation","dataset":"SYN-UDTIRI","model":"DFormer","rank_in_archive_order":7,"of":10,"metrics":{"IoU":"90.88"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.09668","atlas_url":"https://app.syntology.ai/?focus=2309.09668","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":"2309.09668"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2309.09668\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2309.09668"},"call":"get_concepts_for_paper(arxiv_id=\"2309.09668\")"}],"by_repo":[{"repo":"VCIP-RGBD/DFormer","kind":"named_in_paper","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2504.04701"],"harvested_for_calls":[{"arxiv_id":"2504.04701","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2504.04701"},"call":"get_harvested_code_for_paper(arxiv_id=\"2504.04701\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"f52e46932d41aeae4d0c33e1fe17a16eb72d4cba5642756d8d6771a717235467","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}