Matches in SemOpenAlex for { <https://semopenalex.org/work/W3147542689> ?p ?o ?g. }
- W3147542689 abstract "Semantic segmentation aims to classify every pixel of an input image. Considering the difficulty of acquiring dense labels, researchers have recently been resorting to weak labels to alleviate the annotation burden of segmentation. However, existing works mainly concentrate on expanding the seed of pseudo labels within the image's salient region. In this work, we propose a non-salient region object mining approach for weakly supervised semantic segmentation. We introduce a graph-based global reasoning unit to strengthen the classification network's ability to capture global relations among disjoint and distant regions. This helps the network activate the object features outside the salient area. To further mine the non-salient region objects, we propose to exert the segmentation network's self-correction ability. Specifically, a potential object mining module is proposed to reduce the false-negative rate in pseudo labels. Moreover, we propose a non-salient region masking module for complex images to generate masked pseudo labels. Our non-salient region masking module helps further discover the objects in the non-salient region. Extensive experiments on the PASCAL VOC dataset demonstrate state-of-the-art results compared to current methods." @default.
- W3147542689 created "2021-04-13" @default.
- W3147542689 creator A5010005244 @default.
- W3147542689 creator A5024818901 @default.
- W3147542689 creator A5027545344 @default.
- W3147542689 creator A5047128995 @default.
- W3147542689 creator A5057209439 @default.
- W3147542689 creator A5060958969 @default.
- W3147542689 creator A5074492050 @default.
- W3147542689 creator A5084688255 @default.
- W3147542689 date "2021-03-26" @default.
- W3147542689 modified "2023-10-16" @default.
- W3147542689 title "Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation" @default.
- W3147542689 cites W114517082 @default.
- W3147542689 cites W1495267108 @default.
- W3147542689 cites W1861492603 @default.
- W3147542689 cites W1903029394 @default.
- W3147542689 cites W2031489346 @default.
- W3147542689 cites W2108598243 @default.
- W3147542689 cites W2133515615 @default.
- W3147542689 cites W2144794286 @default.
- W3147542689 cites W2194775991 @default.
- W3147542689 cites W2295107390 @default.
- W3147542689 cites W2306289963 @default.
- W3147542689 cites W2337429362 @default.
- W3147542689 cites W2412782625 @default.
- W3147542689 cites W2519610629 @default.
- W3147542689 cites W2520746254 @default.
- W3147542689 cites W2524029660 @default.
- W3147542689 cites W2552414813 @default.
- W3147542689 cites W2585521554 @default.
- W3147542689 cites W2585747585 @default.
- W3147542689 cites W2600144439 @default.
- W3147542689 cites W2606129492 @default.
- W3147542689 cites W2739450375 @default.
- W3147542689 cites W2798376494 @default.
- W3147542689 cites W2799124825 @default.
- W3147542689 cites W2808711976 @default.
- W3147542689 cites W2891355224 @default.
- W3147542689 cites W2956648669 @default.
- W3147542689 cites W2962758679 @default.
- W3147542689 cites W2962867364 @default.
- W3147542689 cites W2963136578 @default.
- W3147542689 cites W2963319519 @default.
- W3147542689 cites W2963346885 @default.
- W3147542689 cites W2963606198 @default.
- W3147542689 cites W2963727650 @default.
- W3147542689 cites W2963881378 @default.
- W3147542689 cites W2963977581 @default.
- W3147542689 cites W2964015378 @default.
- W3147542689 cites W2964168984 @default.
- W3147542689 cites W2980189057 @default.
- W3147542689 cites W2982093251 @default.
- W3147542689 cites W2991083560 @default.
- W3147542689 cites W2995933538 @default.
- W3147542689 cites W3005324544 @default.
- W3147542689 cites W3034333089 @default.
- W3147542689 cites W3034930876 @default.
- W3147542689 cites W3034953667 @default.
- W3147542689 cites W3092837619 @default.
- W3147542689 cites W3093401039 @default.
- W3147542689 cites W3098191145 @default.
- W3147542689 cites W3100040694 @default.
- W3147542689 cites W3101225052 @default.
- W3147542689 cites W3102659010 @default.
- W3147542689 cites W3102714038 @default.
- W3147542689 cites W3104979525 @default.
- W3147542689 cites W3106349512 @default.
- W3147542689 cites W3107653507 @default.
- W3147542689 cites W3122412340 @default.
- W3147542689 cites W3134816589 @default.
- W3147542689 cites W3173957243 @default.
- W3147542689 cites W611457968 @default.
- W3147542689 doi "https://doi.org/10.48550/arxiv.2103.14581" @default.
- W3147542689 hasPublicationYear "2021" @default.
- W3147542689 type Work @default.
- W3147542689 sameAs 3147542689 @default.
- W3147542689 citedByCount "4" @default.
- W3147542689 countsByYear W31475426892021 @default.
- W3147542689 crossrefType "posted-content" @default.
- W3147542689 hasAuthorship W3147542689A5010005244 @default.
- W3147542689 hasAuthorship W3147542689A5024818901 @default.
- W3147542689 hasAuthorship W3147542689A5027545344 @default.
- W3147542689 hasAuthorship W3147542689A5047128995 @default.
- W3147542689 hasAuthorship W3147542689A5057209439 @default.
- W3147542689 hasAuthorship W3147542689A5060958969 @default.
- W3147542689 hasAuthorship W3147542689A5074492050 @default.
- W3147542689 hasAuthorship W3147542689A5084688255 @default.
- W3147542689 hasBestOaLocation W31475426891 @default.
- W3147542689 hasConcept C114614502 @default.
- W3147542689 hasConcept C132525143 @default.
- W3147542689 hasConcept C142362112 @default.
- W3147542689 hasConcept C153180895 @default.
- W3147542689 hasConcept C153349607 @default.
- W3147542689 hasConcept C154945302 @default.
- W3147542689 hasConcept C199360897 @default.
- W3147542689 hasConcept C2777402240 @default.
- W3147542689 hasConcept C2780719617 @default.
- W3147542689 hasConcept C2781238097 @default.
- W3147542689 hasConcept C33923547 @default.