FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384616601> ?p ?o ?g. }

• W4384616601 endingPage "6446" @default.
• W4384616601 startingPage "6446" @default.
• W4384616601 abstract "Instance segmentation is a challenging task in computer vision, as it requires distinguishing objects and predicting dense areas. Currently, segmentation models based on complex designs and large parameters have achieved remarkable accuracy. However, from a practical standpoint, achieving a balance between accuracy and speed is even more desirable. To address this need, this paper presents ESAMask, a real-time segmentation model fused with efficient sparse attention, which adheres to the principles of lightweight design and efficiency. In this work, we propose several key contributions. Firstly, we introduce a dynamic and sparse Related Semantic Perceived Attention mechanism (RSPA) for adaptive perception of different semantic information of various targets during feature extraction. RSPA uses the adjacency matrix to search for regions with high semantic correlation of the same target, which reduces computational cost. Additionally, we design the GSInvSAM structure to reduce redundant calculations of spliced features while enhancing interaction between channels when merging feature layers of different scales. Lastly, we introduce the Mixed Receptive Field Context Perception Module (MRFCPM) in the prototype branch to enable targets of different scales to capture the feature representation of the corresponding area during mask generation. MRFCPM fuses information from three branches of global content awareness, large kernel region awareness, and convolutional channel attention to explicitly model features at different scales. Through extensive experimental evaluation, ESAMask achieves a mask AP of 45.4 at a frame rate of 45.2 FPS on the COCO dataset, surpassing current instance segmentation methods in terms of the accuracy-speed trade-off, as demonstrated by our comprehensive experimental results. In addition, the high-quality segmentation results of our proposed method for objects of various classes and scales can be intuitively observed from the visualized segmentation outputs." @default.
• W4384616601 created "2023-07-18" @default.
• W4384616601 creator A5002795351 @default.
• W4384616601 creator A5023610301 @default.
• W4384616601 creator A5029022229 @default.
• W4384616601 creator A5052441498 @default.
• W4384616601 creator A5072912487 @default.
• W4384616601 date "2023-07-16" @default.
• W4384616601 modified "2023-10-01" @default.
• W4384616601 title "ESAMask: Real-Time Instance Segmentation Fused with Efficient Sparse Attention" @default.
• W4384616601 cites W1536680647 @default.
• W4384616601 cites W1861492603 @default.
• W4384616601 cites W1903029394 @default.
• W4384616601 cites W2920326761 @default.
• W4384616601 cites W2963150697 @default.
• W4384616601 cites W2963857746 @default.
• W4384616601 cites W2970987838 @default.
• W4384616601 cites W2993182889 @default.
• W4384616601 cites W3034681942 @default.
• W4384616601 cites W3034826836 @default.
• W4384616601 cites W3035049382 @default.
• W4384616601 cites W3035358681 @default.
• W4384616601 cites W3047032303 @default.
• W4384616601 cites W3106651317 @default.
• W4384616601 cites W3113410735 @default.
• W4384616601 cites W3138516171 @default.
• W4384616601 cites W3172752666 @default.
• W4384616601 cites W3175701034 @default.
• W4384616601 cites W3177388720 @default.
• W4384616601 cites W3212169088 @default.
• W4384616601 cites W3214740560 @default.
• W4384616601 cites W4214613769 @default.
• W4384616601 cites W4286493870 @default.
• W4384616601 cites W4309026313 @default.
• W4384616601 cites W4311425951 @default.
• W4384616601 cites W4312460151 @default.
• W4384616601 cites W4312616451 @default.
• W4384616601 cites W4312815172 @default.
• W4384616601 cites W4312940821 @default.
• W4384616601 cites W4313036592 @default.
• W4384616601 cites W4316673310 @default.
• W4384616601 cites W4353061895 @default.
• W4384616601 doi "https://doi.org/10.3390/s23146446" @default.
• W4384616601 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37514740" @default.
• W4384616601 hasPublicationYear "2023" @default.
• W4384616601 type Work @default.
• W4384616601 citedByCount "1" @default.
• W4384616601 countsByYear W43846166012023 @default.
• W4384616601 crossrefType "journal-article" @default.
• W4384616601 hasAuthorship W4384616601A5002795351 @default.
• W4384616601 hasAuthorship W4384616601A5023610301 @default.
• W4384616601 hasAuthorship W4384616601A5029022229 @default.
• W4384616601 hasAuthorship W4384616601A5052441498 @default.
• W4384616601 hasAuthorship W4384616601A5072912487 @default.
• W4384616601 hasBestOaLocation W43846166011 @default.
• W4384616601 hasConcept C138885662 @default.
• W4384616601 hasConcept C151730666 @default.
• W4384616601 hasConcept C153180895 @default.
• W4384616601 hasConcept C154945302 @default.
• W4384616601 hasConcept C17744445 @default.
• W4384616601 hasConcept C199539241 @default.
• W4384616601 hasConcept C2776359362 @default.
• W4384616601 hasConcept C2776401178 @default.
• W4384616601 hasConcept C2779343474 @default.
• W4384616601 hasConcept C41008148 @default.
• W4384616601 hasConcept C41895202 @default.
• W4384616601 hasConcept C86803240 @default.
• W4384616601 hasConcept C89600930 @default.
• W4384616601 hasConcept C94625758 @default.
• W4384616601 hasConceptScore W4384616601C138885662 @default.
• W4384616601 hasConceptScore W4384616601C151730666 @default.
• W4384616601 hasConceptScore W4384616601C153180895 @default.
• W4384616601 hasConceptScore W4384616601C154945302 @default.
• W4384616601 hasConceptScore W4384616601C17744445 @default.
• W4384616601 hasConceptScore W4384616601C199539241 @default.
• W4384616601 hasConceptScore W4384616601C2776359362 @default.
• W4384616601 hasConceptScore W4384616601C2776401178 @default.
• W4384616601 hasConceptScore W4384616601C2779343474 @default.
• W4384616601 hasConceptScore W4384616601C41008148 @default.
• W4384616601 hasConceptScore W4384616601C41895202 @default.
• W4384616601 hasConceptScore W4384616601C86803240 @default.
• W4384616601 hasConceptScore W4384616601C89600930 @default.
• W4384616601 hasConceptScore W4384616601C94625758 @default.
• W4384616601 hasIssue "14" @default.
• W4384616601 hasLocation W43846166011 @default.
• W4384616601 hasLocation W43846166012 @default.
• W4384616601 hasOpenAccess W4384616601 @default.
• W4384616601 hasPrimaryLocation W43846166011 @default.
• W4384616601 hasRelatedWork W2033914206 @default.
• W4384616601 hasRelatedWork W2146076056 @default.
• W4384616601 hasRelatedWork W2163831990 @default.
• W4384616601 hasRelatedWork W2358941527 @default.
• W4384616601 hasRelatedWork W2382607599 @default.
• W4384616601 hasRelatedWork W2394327295 @default.
• W4384616601 hasRelatedWork W2521850565 @default.
• W4384616601 hasRelatedWork W2532775738 @default.
• W4384616601 hasRelatedWork W2546942002 @default.
• W4384616601 hasRelatedWork W2970216048 @default.

• next