Matches in SemOpenAlex for { <https://semopenalex.org/work/W3122006940> ?p ?o ?g. }
- W3122006940 endingPage "1" @default.
- W3122006940 startingPage "1" @default.
- W3122006940 abstract "Although current salient object detection (SOD) works have achieved significant progress, they are limited when it comes to the integrity of the predicted salient regions. We define the concept of integrity at both a micro and macro level. Specifically, at the micro level, the model should highlight all parts that belong to a certain salient object. Meanwhile, at the macro level, the model needs to discover all salient objects in a given image. To facilitate integrity learning for SOD, we design a novel Integrity Cognition Network (ICON), which explores three important components for learning strong integrity features. 1) Unlike existing models, which focus more on feature discriminability, we introduce a diverse feature aggregation (DFA) component to aggregate features with various receptive fields (i.e., kernel shape and context) and increase feature diversity. Such diversity is the foundation for mining the integral salient objects. 2) Based on the DFA features, we introduce an integrity channel enhancement (ICE) component with the goal of enhancing feature channels that highlight the integral salient objects, while suppressing the other distracting ones. 3) After extracting the enhanced features, the part-whole verification (PWV) method is employed to determine whether the part and whole object features have strong agreement. Such part-whole agreements can further improve the micro-level integrity for each salient object. To demonstrate the effectiveness of our ICON, comprehensive experiments are conducted on seven challenging benchmarks. Our ICON outperforms the baseline methods in terms of a wide range of metrics. Notably, our ICON achieves ~10% relative improvement over the previous best model in terms of average false negative ratio (FNR), on six datasets." @default.
- W3122006940 created "2021-02-01" @default.
- W3122006940 creator A5030077358 @default.
- W3122006940 creator A5036881486 @default.
- W3122006940 creator A5056294284 @default.
- W3122006940 creator A5081226638 @default.
- W3122006940 creator A5082181536 @default.
- W3122006940 creator A5082634513 @default.
- W3122006940 date "2022-01-01" @default.
- W3122006940 modified "2023-10-16" @default.
- W3122006940 title "Salient Object Detection via Integrity Learning" @default.
- W3122006940 cites W1485009520 @default.
- W3122006940 cites W1677182931 @default.
- W3122006940 cites W1894057436 @default.
- W3122006940 cites W1955857676 @default.
- W3122006940 cites W1994922096 @default.
- W3122006940 cites W2002781701 @default.
- W3122006940 cites W2011900468 @default.
- W3122006940 cites W2037954058 @default.
- W3122006940 cites W2039313011 @default.
- W3122006940 cites W2047670868 @default.
- W3122006940 cites W2078132377 @default.
- W3122006940 cites W2086791339 @default.
- W3122006940 cites W2100470808 @default.
- W3122006940 cites W2128272608 @default.
- W3122006940 cites W2133515615 @default.
- W3122006940 cites W2135957164 @default.
- W3122006940 cites W2147880316 @default.
- W3122006940 cites W2161185676 @default.
- W3122006940 cites W2171378720 @default.
- W3122006940 cites W2183341477 @default.
- W3122006940 cites W2194775991 @default.
- W3122006940 cites W2293332611 @default.
- W3122006940 cites W2314707829 @default.
- W3122006940 cites W2342491128 @default.
- W3122006940 cites W2412782625 @default.
- W3122006940 cites W2519528544 @default.
- W3122006940 cites W2560023338 @default.
- W3122006940 cites W2585592883 @default.
- W3122006940 cites W2605929543 @default.
- W3122006940 cites W2630837129 @default.
- W3122006940 cites W2740652190 @default.
- W3122006940 cites W2740667773 @default.
- W3122006940 cites W2744613561 @default.
- W3122006940 cites W2757028014 @default.
- W3122006940 cites W2765838470 @default.
- W3122006940 cites W2772161954 @default.
- W3122006940 cites W2777511827 @default.
- W3122006940 cites W2780708736 @default.
- W3122006940 cites W2780861787 @default.
- W3122006940 cites W2783231089 @default.
- W3122006940 cites W2785994986 @default.
- W3122006940 cites W2788154928 @default.
- W3122006940 cites W2792965491 @default.
- W3122006940 cites W2797472209 @default.
- W3122006940 cites W2798791651 @default.
- W3122006940 cites W2798825526 @default.
- W3122006940 cites W2799074129 @default.
- W3122006940 cites W2799231793 @default.
- W3122006940 cites W2807746031 @default.
- W3122006940 cites W2808442315 @default.
- W3122006940 cites W2884555738 @default.
- W3122006940 cites W2884585870 @default.
- W3122006940 cites W2889081631 @default.
- W3122006940 cites W2895251968 @default.
- W3122006940 cites W2895340898 @default.
- W3122006940 cites W2897059831 @default.
- W3122006940 cites W2904454836 @default.
- W3122006940 cites W2917790938 @default.
- W3122006940 cites W2938260698 @default.
- W3122006940 cites W2939217524 @default.
- W3122006940 cites W2948500402 @default.
- W3122006940 cites W2948510860 @default.
- W3122006940 cites W2948537313 @default.
- W3122006940 cites W2957414648 @default.
- W3122006940 cites W2961348656 @default.
- W3122006940 cites W2962159375 @default.
- W3122006940 cites W2962680827 @default.
- W3122006940 cites W2962835968 @default.
- W3122006940 cites W2963020481 @default.
- W3122006940 cites W2963032190 @default.
- W3122006940 cites W2963112696 @default.
- W3122006940 cites W2963136160 @default.
- W3122006940 cites W2963299740 @default.
- W3122006940 cites W2963334022 @default.
- W3122006940 cites W2963342032 @default.
- W3122006940 cites W2963420686 @default.
- W3122006940 cites W2963529609 @default.
- W3122006940 cites W2963685207 @default.
- W3122006940 cites W2963703618 @default.
- W3122006940 cites W2963706010 @default.
- W3122006940 cites W2963868681 @default.
- W3122006940 cites W2963951674 @default.
- W3122006940 cites W2964352379 @default.
- W3122006940 cites W2965638232 @default.
- W3122006940 cites W2970005358 @default.
- W3122006940 cites W2970642899 @default.
- W3122006940 cites W2981510929 @default.