Matches in SemOpenAlex for { <https://semopenalex.org/work/W2925338335> ?p ?o ?g. }
- W2925338335 abstract "We treat shape co-segmentation as a representation learning problem and introduce BAE-NET, a branched autoencoder network, for the task. The unsupervised BAE-NET is trained with a collection of un-segmented shapes, using a shape reconstruction loss, without any ground-truth labels. Specifically, the network takes an input shape and encodes it using a convolutional neural network, whereas the decoder concatenates the resulting feature code with a point coordinate and outputs a value indicating whether the point is inside/outside the shape. Importantly, the decoder is branched: each branch learns a compact representation for one commonly recurring part of the shape collection, e.g., airplane wings. By complementing the shape reconstruction loss with a label loss, BAE-NET is easily tuned for one-shot learning. We show unsupervised, weakly supervised, and one-shot learning results by BAE-NET, demonstrating that using only a couple of exemplars, our network can generally outperform state-of-the-art supervised methods trained on hundreds of segmented shapes. Code is available at this https URL." @default.
- W2925338335 created "2019-04-01" @default.
- W2925338335 creator A5026664609 @default.
- W2925338335 creator A5049341927 @default.
- W2925338335 creator A5066922088 @default.
- W2925338335 creator A5081400079 @default.
- W2925338335 creator A5086893989 @default.
- W2925338335 date "2019-03-27" @default.
- W2925338335 modified "2023-09-24" @default.
- W2925338335 title "BAE-NET: Branched Autoencoder for Shape Co-Segmentation" @default.
- W2925338335 cites W1409522266 @default.
- W2925338335 cites W1495267108 @default.
- W2925338335 cites W1529410181 @default.
- W2925338335 cites W1783315696 @default.
- W2925338335 cites W1903029394 @default.
- W2925338335 cites W1915142102 @default.
- W2925338335 cites W1945608308 @default.
- W2925338335 cites W1963920598 @default.
- W2925338335 cites W1994488211 @default.
- W2925338335 cites W1996140089 @default.
- W2925338335 cites W2003940193 @default.
- W2925338335 cites W2023808821 @default.
- W2925338335 cites W2029524207 @default.
- W2925338335 cites W2031760064 @default.
- W2925338335 cites W2042239476 @default.
- W2925338335 cites W2053008628 @default.
- W2925338335 cites W2063513338 @default.
- W2925338335 cites W2086052791 @default.
- W2925338335 cites W2096674800 @default.
- W2925338335 cites W2101104841 @default.
- W2925338335 cites W2103837466 @default.
- W2925338335 cites W2106210044 @default.
- W2925338335 cites W2107558380 @default.
- W2925338335 cites W2133324800 @default.
- W2925338335 cites W2138761194 @default.
- W2925338335 cites W2143485206 @default.
- W2925338335 cites W2157244733 @default.
- W2925338335 cites W2159939615 @default.
- W2925338335 cites W2160847065 @default.
- W2925338335 cites W2165308258 @default.
- W2925338335 cites W2190691619 @default.
- W2925338335 cites W22297218 @default.
- W2925338335 cites W2277007198 @default.
- W2925338335 cites W2306289963 @default.
- W2925338335 cites W2396622801 @default.
- W2925338335 cites W2516803306 @default.
- W2925338335 cites W2552414813 @default.
- W2925338335 cites W2553307952 @default.
- W2925338335 cites W2557269700 @default.
- W2925338335 cites W2560609797 @default.
- W2925338335 cites W2565662353 @default.
- W2925338335 cites W2664923123 @default.
- W2925338335 cites W2734779477 @default.
- W2925338335 cites W2738853914 @default.
- W2925338335 cites W2799124825 @default.
- W2925338335 cites W2807912089 @default.
- W2925338335 cites W2962758679 @default.
- W2925338335 cites W2962841641 @default.
- W2925338335 cites W2962849139 @default.
- W2925338335 cites W2963121255 @default.
- W2925338335 cites W2963182550 @default.
- W2925338335 cites W2963517242 @default.
- W2925338335 cites W2963627347 @default.
- W2925338335 cites W2963697527 @default.
- W2925338335 cites W2963798052 @default.
- W2925338335 cites W2963881378 @default.
- W2925338335 cites W2963921921 @default.
- W2925338335 cites W2963926543 @default.
- W2925338335 cites W2964013315 @default.
- W2925338335 cites W2964074439 @default.
- W2925338335 cites W2964228567 @default.
- W2925338335 cites W2964274719 @default.
- W2925338335 cites W2973014570 @default.
- W2925338335 cites W318792885 @default.
- W2925338335 hasPublicationYear "2019" @default.
- W2925338335 type Work @default.
- W2925338335 sameAs 2925338335 @default.
- W2925338335 citedByCount "3" @default.
- W2925338335 countsByYear W29253383352019 @default.
- W2925338335 countsByYear W29253383352020 @default.
- W2925338335 crossrefType "posted-content" @default.
- W2925338335 hasAuthorship W2925338335A5026664609 @default.
- W2925338335 hasAuthorship W2925338335A5049341927 @default.
- W2925338335 hasAuthorship W2925338335A5066922088 @default.
- W2925338335 hasAuthorship W2925338335A5081400079 @default.
- W2925338335 hasAuthorship W2925338335A5086893989 @default.
- W2925338335 hasConcept C101738243 @default.
- W2925338335 hasConcept C108583219 @default.
- W2925338335 hasConcept C138885662 @default.
- W2925338335 hasConcept C14166107 @default.
- W2925338335 hasConcept C146849305 @default.
- W2925338335 hasConcept C153180895 @default.
- W2925338335 hasConcept C154945302 @default.
- W2925338335 hasConcept C177264268 @default.
- W2925338335 hasConcept C17744445 @default.
- W2925338335 hasConcept C199360897 @default.
- W2925338335 hasConcept C199539241 @default.
- W2925338335 hasConcept C2524010 @default.
- W2925338335 hasConcept C2776359362 @default.
- W2925338335 hasConcept C2776401178 @default.