Matches in SemOpenAlex for { <https://semopenalex.org/work/W4212823076> ?p ?o ?g. }
- W4212823076 endingPage "2897" @default.
- W4212823076 startingPage "2888" @default.
- W4212823076 abstract "Weakly supervised salient object detection (WSOD) aims at training saliency detection models with weak supervision. Normally, the WSOD methods use pseudo labels converted from image-level classification labels to train the saliency network. However, the converted pseudo labels always contain noise information compared to ground truth. Previous methods are directly affected by pseudo label noise to generate error-prone predictions. To mitigate this problem, we design a noise-robust adversarial learning framework and propose a noise-sensitive training strategy for the framework. The framework consists of a saliency network and a noise-robust discriminator network. With the guidance of noise-robust discriminator network, our saliency network is robust to noise information in pseudo labels. The proposed noise-sensitive training strategy can make good use of both superior and inferior samples in the pseudo label dataset. With the noise-sensitive training strategy, our framework can further balance the learning of saliency information and the robustness of noise information. Comprehensive experiments on five public datasets demonstrate that our method outperforms the existing image-level classification label based WSOD methods." @default.
- W4212823076 created "2022-02-24" @default.
- W4212823076 creator A5006986293 @default.
- W4212823076 creator A5014975416 @default.
- W4212823076 creator A5015297129 @default.
- W4212823076 creator A5036031567 @default.
- W4212823076 creator A5067064849 @default.
- W4212823076 date "2023-01-01" @default.
- W4212823076 modified "2023-10-14" @default.
- W4212823076 title "Noise-Sensitive Adversarial Learning for Weakly Supervised Salient Object Detection" @default.
- W4212823076 cites W1514928307 @default.
- W4212823076 cites W1982075130 @default.
- W4212823076 cites W2002781701 @default.
- W4212823076 cites W2031489346 @default.
- W4212823076 cites W2038913936 @default.
- W4212823076 cites W2039313011 @default.
- W4212823076 cites W2086791339 @default.
- W4212823076 cites W2100470808 @default.
- W4212823076 cites W2108598243 @default.
- W4212823076 cites W2158535435 @default.
- W4212823076 cites W2161185676 @default.
- W4212823076 cites W2165826763 @default.
- W4212823076 cites W2461475918 @default.
- W4212823076 cites W2519528544 @default.
- W4212823076 cites W2569272946 @default.
- W4212823076 cites W2738588019 @default.
- W4212823076 cites W2740667773 @default.
- W4212823076 cites W2744613561 @default.
- W4212823076 cites W2793668851 @default.
- W4212823076 cites W2798791651 @default.
- W4212823076 cites W2798825526 @default.
- W4212823076 cites W2805199679 @default.
- W4212823076 cites W2807746031 @default.
- W4212823076 cites W2884944276 @default.
- W4212823076 cites W2903398871 @default.
- W4212823076 cites W2918123657 @default.
- W4212823076 cites W2948510860 @default.
- W4212823076 cites W2955278847 @default.
- W4212823076 cites W2961348656 @default.
- W4212823076 cites W2962858109 @default.
- W4212823076 cites W2962867364 @default.
- W4212823076 cites W2963020481 @default.
- W4212823076 cites W2963112696 @default.
- W4212823076 cites W2963136160 @default.
- W4212823076 cites W2963450895 @default.
- W4212823076 cites W2963529609 @default.
- W4212823076 cites W2963572583 @default.
- W4212823076 cites W2963685207 @default.
- W4212823076 cites W2963868681 @default.
- W4212823076 cites W2987701848 @default.
- W4212823076 cites W2997851315 @default.
- W4212823076 cites W3034453930 @default.
- W4212823076 cites W3035290198 @default.
- W4212823076 cites W3035422681 @default.
- W4212823076 cites W3043547428 @default.
- W4212823076 cites W3091936831 @default.
- W4212823076 cites W3097336090 @default.
- W4212823076 cites W3098241816 @default.
- W4212823076 cites W3103516890 @default.
- W4212823076 cites W3104979525 @default.
- W4212823076 cites W3108948422 @default.
- W4212823076 cites W3157190320 @default.
- W4212823076 cites W3177087374 @default.
- W4212823076 doi "https://doi.org/10.1109/tmm.2022.3152567" @default.
- W4212823076 hasPublicationYear "2023" @default.
- W4212823076 type Work @default.
- W4212823076 citedByCount "5" @default.
- W4212823076 countsByYear W42128230762022 @default.
- W4212823076 countsByYear W42128230762023 @default.
- W4212823076 crossrefType "journal-article" @default.
- W4212823076 hasAuthorship W4212823076A5006986293 @default.
- W4212823076 hasAuthorship W4212823076A5014975416 @default.
- W4212823076 hasAuthorship W4212823076A5015297129 @default.
- W4212823076 hasAuthorship W4212823076A5036031567 @default.
- W4212823076 hasAuthorship W4212823076A5067064849 @default.
- W4212823076 hasConcept C104317684 @default.
- W4212823076 hasConcept C115961682 @default.
- W4212823076 hasConcept C119857082 @default.
- W4212823076 hasConcept C136389625 @default.
- W4212823076 hasConcept C146849305 @default.
- W4212823076 hasConcept C153180895 @default.
- W4212823076 hasConcept C154945302 @default.
- W4212823076 hasConcept C163294075 @default.
- W4212823076 hasConcept C185592680 @default.
- W4212823076 hasConcept C2776151529 @default.
- W4212823076 hasConcept C2779803651 @default.
- W4212823076 hasConcept C2780719617 @default.
- W4212823076 hasConcept C29265498 @default.
- W4212823076 hasConcept C31972630 @default.
- W4212823076 hasConcept C41008148 @default.
- W4212823076 hasConcept C50644808 @default.
- W4212823076 hasConcept C55493867 @default.
- W4212823076 hasConcept C63479239 @default.
- W4212823076 hasConcept C76155785 @default.
- W4212823076 hasConcept C94915269 @default.
- W4212823076 hasConcept C99498987 @default.
- W4212823076 hasConceptScore W4212823076C104317684 @default.
- W4212823076 hasConceptScore W4212823076C115961682 @default.