Matches in SemOpenAlex for { <https://semopenalex.org/work/W3174368637> ?p ?o ?g. }
- W3174368637 abstract "Compared to many other dense prediction tasks, e.g., semantic segmentation, it is the arbitrary number of instances that has made instance segmentation much more challenging. In order to predict a mask for each instance, mainstream approaches either follow the 'detect-then-segment' strategy (e.g., Mask R-CNN), or predict embedding vectors first then cluster pixels into individual instances. In this paper, we view the task of instance segmentation from a completely new perspective by introducing the notion of instance categories, which assigns categories to each pixel within an instance according to the instance's location. With this notion, we propose segmenting objects by locations (SOLO), a simple, direct, and fast framework for instance segmentation with strong performance. We derive a few SOLO variants (e.g., Vanilla SOLO, Decoupled SOLO, Dynamic SOLO) following the basic principle. Our method directly maps a raw input image to the desired object categories and instance masks, eliminating the need for the grouping post-processing or the bounding box detection. Our approach achieves state-of-the-art results for instance segmentation in terms of both speed and accuracy, while being considerably simpler than the existing methods. Besides instance segmentation, our method yields state-of-the-art results in object detection (from our mask byproduct) and panoptic segmentation. We further demonstrate the flexibility and high-quality segmentation of SOLO by extending it to perform one-stage instance-level image matting. Code is available at: https://git.io/AdelaiDet" @default.
- W3174368637 created "2021-07-05" @default.
- W3174368637 creator A5006294869 @default.
- W3174368637 creator A5023005118 @default.
- W3174368637 creator A5026769100 @default.
- W3174368637 creator A5065667064 @default.
- W3174368637 creator A5075889094 @default.
- W3174368637 date "2021-06-30" @default.
- W3174368637 modified "2023-09-24" @default.
- W3174368637 title "SOLO: A Simple Framework for Instance Segmentation" @default.
- W3174368637 cites W1507506748 @default.
- W3174368637 cites W1861492603 @default.
- W3174368637 cites W1903029394 @default.
- W3174368637 cites W2035773017 @default.
- W3174368637 cites W2044673646 @default.
- W3174368637 cites W2117539524 @default.
- W3174368637 cites W2194775991 @default.
- W3174368637 cites W2295475768 @default.
- W3174368637 cites W2340897893 @default.
- W3174368637 cites W2414711238 @default.
- W3174368637 cites W2555751471 @default.
- W3174368637 cites W2565639579 @default.
- W3174368637 cites W2601564443 @default.
- W3174368637 cites W2604469346 @default.
- W3174368637 cites W2613718673 @default.
- W3174368637 cites W2744404335 @default.
- W3174368637 cites W2796347433 @default.
- W3174368637 cites W2891201469 @default.
- W3174368637 cites W2910628332 @default.
- W3174368637 cites W2920326761 @default.
- W3174368637 cites W2948672349 @default.
- W3174368637 cites W2948770160 @default.
- W3174368637 cites W2955340181 @default.
- W3174368637 cites W2962677013 @default.
- W3174368637 cites W2962766617 @default.
- W3174368637 cites W2962914239 @default.
- W3174368637 cites W2963150697 @default.
- W3174368637 cites W2963351448 @default.
- W3174368637 cites W2963393688 @default.
- W3174368637 cites W2963623257 @default.
- W3174368637 cites W2963769056 @default.
- W3174368637 cites W2963786238 @default.
- W3174368637 cites W2963849369 @default.
- W3174368637 cites W2963857746 @default.
- W3174368637 cites W2963870605 @default.
- W3174368637 cites W2963927307 @default.
- W3174368637 cites W2964080601 @default.
- W3174368637 cites W2964121718 @default.
- W3174368637 cites W2964236837 @default.
- W3174368637 cites W2965182628 @default.
- W3174368637 cites W2981537222 @default.
- W3174368637 cites W2982161360 @default.
- W3174368637 cites W2982770724 @default.
- W3174368637 cites W2985469567 @default.
- W3174368637 cites W2986357608 @default.
- W3174368637 cites W2991405684 @default.
- W3174368637 cites W2993182889 @default.
- W3174368637 cites W2995426144 @default.
- W3174368637 cites W2999219213 @default.
- W3174368637 cites W3012846999 @default.
- W3174368637 cites W3034355852 @default.
- W3174368637 cites W3034428102 @default.
- W3174368637 cites W3034549805 @default.
- W3174368637 cites W3034826836 @default.
- W3174368637 cites W3034971973 @default.
- W3174368637 cites W3035010169 @default.
- W3174368637 cites W3035358681 @default.
- W3174368637 cites W3098090606 @default.
- W3174368637 cites W3102701618 @default.
- W3174368637 cites W3106250896 @default.
- W3174368637 cites W3106546328 @default.
- W3174368637 cites W3113410735 @default.
- W3174368637 cites W603908379 @default.
- W3174368637 cites W809122546 @default.
- W3174368637 cites W1597727245 @default.
- W3174368637 doi "https://doi.org/10.48550/arxiv.2106.15947" @default.
- W3174368637 hasPublicationYear "2021" @default.
- W3174368637 type Work @default.
- W3174368637 sameAs 3174368637 @default.
- W3174368637 citedByCount "0" @default.
- W3174368637 crossrefType "posted-content" @default.
- W3174368637 hasAuthorship W3174368637A5006294869 @default.
- W3174368637 hasAuthorship W3174368637A5023005118 @default.
- W3174368637 hasAuthorship W3174368637A5026769100 @default.
- W3174368637 hasAuthorship W3174368637A5065667064 @default.
- W3174368637 hasAuthorship W3174368637A5075889094 @default.
- W3174368637 hasBestOaLocation W31743686371 @default.
- W3174368637 hasConcept C124504099 @default.
- W3174368637 hasConcept C125308379 @default.
- W3174368637 hasConcept C12713177 @default.
- W3174368637 hasConcept C144133560 @default.
- W3174368637 hasConcept C153180895 @default.
- W3174368637 hasConcept C154945302 @default.
- W3174368637 hasConcept C160633673 @default.
- W3174368637 hasConcept C162853370 @default.
- W3174368637 hasConcept C25694479 @default.
- W3174368637 hasConcept C2781238097 @default.
- W3174368637 hasConcept C31972630 @default.
- W3174368637 hasConcept C41008148 @default.
- W3174368637 hasConcept C41608201 @default.