Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320154002> ?p ?o ?g. }
- W4320154002 endingPage "7918" @default.
- W4320154002 startingPage "7907" @default.
- W4320154002 abstract "Existing object detection algorithms rely excessively on instance-level labels, which are both time-consuming and expensive. In particular, for remote sensing images (RSI) with small and dense objects, the labeling cost is much higher than that of general images. Moreover, the propagation process of the labels over the noisy channel results in blurred and noisy information. To address the problem of obtaining RSI instance-level labels, we aim to propose a collaborative learning-based network for weakly supervised remote sensing object detection (CLN-RSOD). Compared with the state-of-the-art, the proposed model combines the advantages of two object detection sub-networks by jointly training. This improves the model's capability and thereby enhances the detection effect for multi-object in RSI. Moreover, we employ a mask-based proposal refinement algorithm for remote sensing images (MPR-RS) to optimize the candidate boxes. In addition, according to the data distribution characteristics of RSI, we introduce a new joint pooling module (JPM) in CLN-RSOD to enhance the backbone network's characterization of RSI. Finally, the experimental results on two public remote sensing datasets illustrate that the proposed weakly supervised learning method is superior to other weakly supervised methods and demonstrates the effectiveness of the proposed CLN-RSOD." @default.
- W4320154002 created "2023-02-13" @default.
- W4320154002 creator A5020214478 @default.
- W4320154002 creator A5066309268 @default.
- W4320154002 creator A5066710236 @default.
- W4320154002 creator A5074695364 @default.
- W4320154002 date "2023-01-01" @default.
- W4320154002 modified "2023-09-27" @default.
- W4320154002 title "Collaborative Learning-based Network for Weakly Supervised Remote Sensing Object Detection" @default.
- W4320154002 cites W1536680647 @default.
- W4320154002 cites W2006623133 @default.
- W4320154002 cites W2037227137 @default.
- W4320154002 cites W2085625911 @default.
- W4320154002 cites W2088049833 @default.
- W4320154002 cites W2097117768 @default.
- W4320154002 cites W2102605133 @default.
- W4320154002 cites W2108598243 @default.
- W4320154002 cites W2109255472 @default.
- W4320154002 cites W2194775991 @default.
- W4320154002 cites W2270801692 @default.
- W4320154002 cites W2295107390 @default.
- W4320154002 cites W2512351403 @default.
- W4320154002 cites W2565639579 @default.
- W4320154002 cites W2570343428 @default.
- W4320154002 cites W2604260814 @default.
- W4320154002 cites W2618530766 @default.
- W4320154002 cites W2746791238 @default.
- W4320154002 cites W2752782242 @default.
- W4320154002 cites W2765793020 @default.
- W4320154002 cites W2813911573 @default.
- W4320154002 cites W2883363148 @default.
- W4320154002 cites W2919115771 @default.
- W4320154002 cites W2935079508 @default.
- W4320154002 cites W2954087924 @default.
- W4320154002 cites W2962766617 @default.
- W4320154002 cites W2962858109 @default.
- W4320154002 cites W2963037989 @default.
- W4320154002 cites W2963603913 @default.
- W4320154002 cites W2963681621 @default.
- W4320154002 cites W2988452521 @default.
- W4320154002 cites W2988916019 @default.
- W4320154002 cites W2992240579 @default.
- W4320154002 cites W2994041372 @default.
- W4320154002 cites W3017351200 @default.
- W4320154002 cites W3019659794 @default.
- W4320154002 cites W3026303927 @default.
- W4320154002 cites W3034329658 @default.
- W4320154002 cites W3035725370 @default.
- W4320154002 cites W3097947628 @default.
- W4320154002 cites W3117854388 @default.
- W4320154002 cites W3138516171 @default.
- W4320154002 cites W3171125843 @default.
- W4320154002 cites W639708223 @default.
- W4320154002 cites W7746136 @default.
- W4320154002 doi "https://doi.org/10.1109/jstars.2022.3223845" @default.
- W4320154002 hasPublicationYear "2023" @default.
- W4320154002 type Work @default.
- W4320154002 citedByCount "2" @default.
- W4320154002 countsByYear W43201540022023 @default.
- W4320154002 crossrefType "journal-article" @default.
- W4320154002 hasAuthorship W4320154002A5020214478 @default.
- W4320154002 hasAuthorship W4320154002A5066309268 @default.
- W4320154002 hasAuthorship W4320154002A5066710236 @default.
- W4320154002 hasAuthorship W4320154002A5074695364 @default.
- W4320154002 hasBestOaLocation W43201540021 @default.
- W4320154002 hasConcept C111919701 @default.
- W4320154002 hasConcept C119857082 @default.
- W4320154002 hasConcept C124101348 @default.
- W4320154002 hasConcept C127162648 @default.
- W4320154002 hasConcept C153180895 @default.
- W4320154002 hasConcept C154945302 @default.
- W4320154002 hasConcept C2776151529 @default.
- W4320154002 hasConcept C2781238097 @default.
- W4320154002 hasConcept C31258907 @default.
- W4320154002 hasConcept C41008148 @default.
- W4320154002 hasConcept C70437156 @default.
- W4320154002 hasConcept C98045186 @default.
- W4320154002 hasConceptScore W4320154002C111919701 @default.
- W4320154002 hasConceptScore W4320154002C119857082 @default.
- W4320154002 hasConceptScore W4320154002C124101348 @default.
- W4320154002 hasConceptScore W4320154002C127162648 @default.
- W4320154002 hasConceptScore W4320154002C153180895 @default.
- W4320154002 hasConceptScore W4320154002C154945302 @default.
- W4320154002 hasConceptScore W4320154002C2776151529 @default.
- W4320154002 hasConceptScore W4320154002C2781238097 @default.
- W4320154002 hasConceptScore W4320154002C31258907 @default.
- W4320154002 hasConceptScore W4320154002C41008148 @default.
- W4320154002 hasConceptScore W4320154002C70437156 @default.
- W4320154002 hasConceptScore W4320154002C98045186 @default.
- W4320154002 hasFunder F4320321001 @default.
- W4320154002 hasFunder F4320327518 @default.
- W4320154002 hasLocation W43201540021 @default.
- W4320154002 hasOpenAccess W4320154002 @default.
- W4320154002 hasPrimaryLocation W43201540021 @default.
- W4320154002 hasRelatedWork W2043075591 @default.
- W4320154002 hasRelatedWork W2095705906 @default.
- W4320154002 hasRelatedWork W2127769904 @default.
- W4320154002 hasRelatedWork W2291847203 @default.