{"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/uninet-a-unified-scene-understanding-network","title":"UniNet: A Unified Scene Understanding Network and Exploring Multi-Task Relationships through the Lens of Adversarial Attacks","arxiv_id":"2108.04584","date":"2021-08-10","proceeding":null,"authors":["Naresh Kumar Gurulingan","Elahe Arani","Bahram Zonooz"],"abstract":"Scene understanding is crucial for autonomous systems which intend to operate in the real world. Single task vision networks extract information only based on some aspects of the scene. In multi-task learning (MTL), on the other hand, these single tasks are jointly learned, thereby providing an opportunity for tasks to share information and obtain a more comprehensive understanding. To this end, we develop UniNet, a unified scene understanding network that accurately and efficiently infers vital vision tasks including object detection, semantic segmentation, instance segmentation, monocular depth estimation, and monocular instance depth prediction. As these tasks look at different semantic and geometric information, they can either complement or conflict with each other. Therefore, understanding inter-task relationships can provide useful cues to enable complementary information sharing. We evaluate the task relationships in UniNet through the lens of adversarial attacks based on the notion that they can exploit learned biases and task interactions in the neural network. Extensive experiments on the Cityscapes dataset, using untargeted and targeted attacks reveal that semantic tasks strongly interact amongst themselves, and the same holds for geometric tasks. Additionally, we show that the relationship between semantic and geometric tasks is asymmetric and their interaction becomes weaker as we move towards higher-level representations.","url_abs":"https://arxiv.org/abs/2108.04584v2","url_pdf":"https://arxiv.org/pdf/2108.04584v2.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":"uninet-a-unified-scene-understanding-network","repo_url":"https://github.com/NeurAI-Lab/UniNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.04584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04584"}},"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/NeurAI-Lab/UniNet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"ran":0,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"e13e152fbb36748b","entry":"conv1x1","repo":"NeurAI-Lab/UniNet","repo_kind":"official","path":"encoding_custom/backbones/vovnet.py","file_url":"https://github.com/NeurAI-Lab/UniNet/blob/HEAD/encoding_custom/backbones/vovnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e13e152fbb36748b"}},{"code_sha256_prefix":"d1fbadb5d1136a50","entry":"conv3x3","repo":"NeurAI-Lab/UniNet","repo_kind":"official","path":"encoding_custom/backbones/vovnet.py","file_url":"https://github.com/NeurAI-Lab/UniNet/blob/HEAD/encoding_custom/backbones/vovnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d1fbadb5d1136a50"}},{"code_sha256_prefix":"5f67ca80df21fa9b","entry":"dilate","repo":"NeurAI-Lab/UniNet","repo_kind":"official","path":"encoding_custom/losses/aux_losses.py","file_url":"https://github.com/NeurAI-Lab/UniNet/blob/HEAD/encoding_custom/losses/aux_losses.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f67ca80df21fa9b"}},{"code_sha256_prefix":"72cc03000cea45ba","entry":"dw_conv3x3","repo":"NeurAI-Lab/UniNet","repo_kind":"official","path":"encoding_custom/backbones/vovnet.py","file_url":"https://github.com/NeurAI-Lab/UniNet/blob/HEAD/encoding_custom/backbones/vovnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"72cc03000cea45ba"}},{"code_sha256_prefix":"23a56af97258a878","entry":"extract_semantic_contours","repo":"NeurAI-Lab/UniNet","repo_kind":"official","path":"encoding_custom/losses/aux_losses.py","file_url":"https://github.com/NeurAI-Lab/UniNet/blob/HEAD/encoding_custom/losses/aux_losses.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"23a56af97258a878"}},{"code_sha256_prefix":"a3aa2800740d499d","entry":"extract_surface_normals","repo":"NeurAI-Lab/UniNet","repo_kind":"official","path":"encoding_custom/losses/aux_losses.py","file_url":"https://github.com/NeurAI-Lab/UniNet/blob/HEAD/encoding_custom/losses/aux_losses.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3aa2800740d499d"}},{"code_sha256_prefix":"ca0c391e4de37786","entry":"get_city_pairs","repo":"NeurAI-Lab/UniNet","repo_kind":"official","path":"encoding_custom/datasets/uninet_cs.py","file_url":"https://github.com/NeurAI-Lab/UniNet/blob/HEAD/encoding_custom/datasets/uninet_cs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca0c391e4de37786"}},{"code_sha256_prefix":"c4200f79888d9a2f","entry":"get_image_paths","repo":"NeurAI-Lab/UniNet","repo_kind":"official","path":"encoding_custom/datasets/uninet_cs.py","file_url":"https://github.com/NeurAI-Lab/UniNet/blob/HEAD/encoding_custom/datasets/uninet_cs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c4200f79888d9a2f"}},{"code_sha256_prefix":"c3100dbadeb7098b","entry":"get_intrisics","repo":"NeurAI-Lab/UniNet","repo_kind":"official","path":"encoding_custom/datasets/uninet_cs.py","file_url":"https://github.com/NeurAI-Lab/UniNet/blob/HEAD/encoding_custom/datasets/uninet_cs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c3100dbadeb7098b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}