{"doi":"10.1609/aaai.v34i07.6831","title":"Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training","abstract":"Semantic segmentation (SS) is an important perception manner for self-driving cars and robotics, which classifies each pixel into a pre-determined class. The widely-used cross entropy (CE) loss-based deep networks has achieved significant progress w.r.t. the mean Intersection-over Union (mIoU). However, the cross entropy loss can not take the different importance of each class in an self-driving system into account. For example, pedestrians in the image should be much more important than the surrounding buildings when make a decisions in the driving, so their segmentation results are expected to be as accurate as possible. In this paper, we propose to incorporate the importance-aware inter-class correlation in a Wasserstein training framework by configuring its ground distance matrix. The ground distance matrix can be pre-defined following a priori in a specific task, and the previous importance-ignored methods can be the particular cases. From an optimization perspective, we also extend our ground metric to a linear, convex or concave increasing function w.r.t. pre-defined ground distance. We evaluate our method on CamVid and Cityscapes datasets with different backbones (SegNet, ENet, FCN and Deeplab) in a plug and play fashion. In our extenssive experiments, Wasserstein loss demonstrates superior segmentation performance on the predefined critical classes for safe-driving.","journal":"Proceedings of the AAAI Conference on Artificial Intelligence","year":2020,"id":118615,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":54,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9537,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2020-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":552921,"name":"Yuzhuo Han","orcid":null,"position":1,"is_corresponding":false},{"id":551635,"name":"Song Bai","orcid":"0000-0002-2570-9118","position":2,"is_corresponding":false},{"id":551636,"name":"Yi Ge","orcid":"0000-0002-7186-9024","position":3,"is_corresponding":false},{"id":552922,"name":"Tianxing Wang","orcid":null,"position":4,"is_corresponding":false},{"id":551637,"name":"Xu Han","orcid":"0000-0003-3491-8576","position":5,"is_corresponding":false},{"id":551638,"name":"Site Li","orcid":"0000-0002-7221-1814","position":6,"is_corresponding":false},{"id":551639,"name":"Jane You","orcid":"0000-0002-8181-4836","position":7,"is_corresponding":false},{"id":551640,"name":"Jun Lu","orcid":"0000-0001-6656-4587","position":8,"is_corresponding":false},{"id":551634,"name":"Xiaofeng Liu","orcid":"0000-0002-4514-2016","position":0,"is_corresponding":true}],"reference_count":53,"raw_metadata":null,"created_at":"2026-07-18T23:14:03.409507Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}