Matches in SemOpenAlex for { <https://semopenalex.org/work/W2898861608> ?p ?o ?g. }
- W2898861608 abstract "Learning feature detection has been largely an unexplored area when compared to handcrafted feature detection. Recent learning formulations use the covariant constraint in their loss function to learn covariant detectors. However, just learning from covariant constraint can lead to detection of unstable features. To impart further, stability detectors are trained to extract pre-determined features obtained by hand-crafted detectors. However, in the process they lose the ability to detect novel features. In an attempt to overcome the above limitations, we propose an improved scheme by incorporating covariant constraints in form of triplets with addition to an affine covariant constraint. We show that using these additional constraints one can learn to detect novel and stable features without using pre-determined features for training. Extensive experiments show our model achieves state-of-the-art performance in repeatability score on the well known datasets such as Vgg-Affine, EF, and Webcam." @default.
- W2898861608 created "2018-11-09" @default.
- W2898861608 creator A5011626061 @default.
- W2898861608 creator A5019742155 @default.
- W2898861608 creator A5030539587 @default.
- W2898861608 creator A5086822138 @default.
- W2898861608 date "2018-11-01" @default.
- W2898861608 modified "2023-09-27" @default.
- W2898861608 title "An Improved Learning Framework for Covariant Local Feature Detection" @default.
- W2898861608 cites W1532362218 @default.
- W2898861608 cites W1677409904 @default.
- W2898861608 cites W1945298332 @default.
- W2898861608 cites W2028285070 @default.
- W2898861608 cites W2083833836 @default.
- W2898861608 cites W2111308925 @default.
- W2898861608 cites W2119747362 @default.
- W2898861608 cites W2122015342 @default.
- W2898861608 cites W2126060993 @default.
- W2898861608 cites W2147555557 @default.
- W2898861608 cites W2151103935 @default.
- W2898861608 cites W2156598602 @default.
- W2898861608 cites W2170282673 @default.
- W2898861608 cites W2556970001 @default.
- W2898861608 cites W2612112834 @default.
- W2898861608 cites W2737260104 @default.
- W2898861608 cites W2749224737 @default.
- W2898861608 cites W2949896259 @default.
- W2898861608 cites W2952052436 @default.
- W2898861608 cites W2963157250 @default.
- W2898861608 hasPublicationYear "2018" @default.
- W2898861608 type Work @default.
- W2898861608 sameAs 2898861608 @default.
- W2898861608 citedByCount "1" @default.
- W2898861608 countsByYear W28988616082019 @default.
- W2898861608 crossrefType "posted-content" @default.
- W2898861608 hasAuthorship W2898861608A5011626061 @default.
- W2898861608 hasAuthorship W2898861608A5019742155 @default.
- W2898861608 hasAuthorship W2898861608A5030539587 @default.
- W2898861608 hasAuthorship W2898861608A5086822138 @default.
- W2898861608 hasConcept C112972136 @default.
- W2898861608 hasConcept C119857082 @default.
- W2898861608 hasConcept C138885662 @default.
- W2898861608 hasConcept C14036430 @default.
- W2898861608 hasConcept C153180895 @default.
- W2898861608 hasConcept C154945302 @default.
- W2898861608 hasConcept C202444582 @default.
- W2898861608 hasConcept C2524010 @default.
- W2898861608 hasConcept C2776036281 @default.
- W2898861608 hasConcept C2776401178 @default.
- W2898861608 hasConcept C33923547 @default.
- W2898861608 hasConcept C41008148 @default.
- W2898861608 hasConcept C41895202 @default.
- W2898861608 hasConcept C76155785 @default.
- W2898861608 hasConcept C78458016 @default.
- W2898861608 hasConcept C86803240 @default.
- W2898861608 hasConcept C9136319 @default.
- W2898861608 hasConcept C92757383 @default.
- W2898861608 hasConcept C94915269 @default.
- W2898861608 hasConceptScore W2898861608C112972136 @default.
- W2898861608 hasConceptScore W2898861608C119857082 @default.
- W2898861608 hasConceptScore W2898861608C138885662 @default.
- W2898861608 hasConceptScore W2898861608C14036430 @default.
- W2898861608 hasConceptScore W2898861608C153180895 @default.
- W2898861608 hasConceptScore W2898861608C154945302 @default.
- W2898861608 hasConceptScore W2898861608C202444582 @default.
- W2898861608 hasConceptScore W2898861608C2524010 @default.
- W2898861608 hasConceptScore W2898861608C2776036281 @default.
- W2898861608 hasConceptScore W2898861608C2776401178 @default.
- W2898861608 hasConceptScore W2898861608C33923547 @default.
- W2898861608 hasConceptScore W2898861608C41008148 @default.
- W2898861608 hasConceptScore W2898861608C41895202 @default.
- W2898861608 hasConceptScore W2898861608C76155785 @default.
- W2898861608 hasConceptScore W2898861608C78458016 @default.
- W2898861608 hasConceptScore W2898861608C86803240 @default.
- W2898861608 hasConceptScore W2898861608C9136319 @default.
- W2898861608 hasConceptScore W2898861608C92757383 @default.
- W2898861608 hasConceptScore W2898861608C94915269 @default.
- W2898861608 hasLocation W28988616081 @default.
- W2898861608 hasOpenAccess W2898861608 @default.
- W2898861608 hasPrimaryLocation W28988616081 @default.
- W2898861608 hasRelatedWork W1978590356 @default.
- W2898861608 hasRelatedWork W2009668020 @default.
- W2898861608 hasRelatedWork W2108125228 @default.
- W2898861608 hasRelatedWork W2128031471 @default.
- W2898861608 hasRelatedWork W2168812120 @default.
- W2898861608 hasRelatedWork W2803106019 @default.
- W2898861608 hasRelatedWork W2807036115 @default.
- W2898861608 hasRelatedWork W2934576922 @default.
- W2898861608 hasRelatedWork W2949896259 @default.
- W2898861608 hasRelatedWork W2965379890 @default.
- W2898861608 hasRelatedWork W3013160170 @default.
- W2898861608 hasRelatedWork W3100826576 @default.
- W2898861608 hasRelatedWork W3171333242 @default.
- W2898861608 hasRelatedWork W3180805579 @default.
- W2898861608 hasRelatedWork W3189569440 @default.
- W2898861608 hasRelatedWork W3200416288 @default.
- W2898861608 hasRelatedWork W3204231799 @default.
- W2898861608 hasRelatedWork W3205662376 @default.
- W2898861608 hasRelatedWork W3208297503 @default.
- W2898861608 hasRelatedWork W4226327324 @default.