Matches in SemOpenAlex for { <https://semopenalex.org/work/W4321353575> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4321353575 endingPage "302" @default.
- W4321353575 startingPage "286" @default.
- W4321353575 abstract "Object Detection, a fundamental computer vision problem, has paramount importance in smart camera systems. However, a truly reliable camera system could be achieved if and only if the underlying object detection component is robust enough across varying imaging conditions (or domains), for instance, different times of the day, adverse weather conditions, etc. In an effort to achieving a reliable camera system, in this paper, we make an attempt to train such a robust detector. Unfortunately, to build a well-performing detector across varying imaging conditions, one would require labeled training images (often in large numbers) from a plethora of corner cases. As manually obtaining such a large labeled dataset may be infeasible, we suggest using synthetic images, to mimic different training image domains. We propose a novel, contrastive learning method to align the latent representations of a pair of real and synthetic images, to make the detector robust to the different domains. However, we found that merely contrasting the embeddings may lead to catastrophic forgetting of the information essential for object detection. Hence, we employ a continual learning based penalty, to alleviate the issue of forgetting, while contrasting the representations. We showcase that our proposed method outperforms a wide range of alternatives to address the extremely challenging, yet under-studied scenario of object detection at night-time." @default.
- W4321353575 created "2023-02-20" @default.
- W4321353575 creator A5038904282 @default.
- W4321353575 date "2023-01-01" @default.
- W4321353575 modified "2023-10-07" @default.
- W4321353575 title "Seeing Objects in Dark with Continual Contrastive Learning" @default.
- W4321353575 cites W1861492603 @default.
- W4321353575 cites W1910108985 @default.
- W4321353575 cites W2031454541 @default.
- W4321353575 cites W2110405746 @default.
- W4321353575 cites W2560647685 @default.
- W4321353575 cites W2894931878 @default.
- W4321353575 cites W2908973513 @default.
- W4321353575 cites W2963351448 @default.
- W4321353575 cites W2963890275 @default.
- W4321353575 cites W2969121634 @default.
- W4321353575 cites W2981718299 @default.
- W4321353575 cites W2998273021 @default.
- W4321353575 cites W3000172657 @default.
- W4321353575 cites W3034305572 @default.
- W4321353575 cites W3035172746 @default.
- W4321353575 cites W3035294798 @default.
- W4321353575 cites W3035564946 @default.
- W4321353575 cites W3035574168 @default.
- W4321353575 cites W3096609285 @default.
- W4321353575 cites W3102057471 @default.
- W4321353575 cites W3108910236 @default.
- W4321353575 cites W3121661546 @default.
- W4321353575 cites W3134649899 @default.
- W4321353575 cites W3168347507 @default.
- W4321353575 cites W3179888767 @default.
- W4321353575 cites W3180134609 @default.
- W4321353575 cites W3207649350 @default.
- W4321353575 doi "https://doi.org/10.1007/978-3-031-25075-0_21" @default.
- W4321353575 hasPublicationYear "2023" @default.
- W4321353575 type Work @default.
- W4321353575 citedByCount "0" @default.
- W4321353575 crossrefType "book-chapter" @default.
- W4321353575 hasAuthorship W4321353575A5038904282 @default.
- W4321353575 hasBestOaLocation W43213535752 @default.
- W4321353575 hasConcept C108583219 @default.
- W4321353575 hasConcept C119857082 @default.
- W4321353575 hasConcept C121332964 @default.
- W4321353575 hasConcept C138885662 @default.
- W4321353575 hasConcept C153180895 @default.
- W4321353575 hasConcept C154945302 @default.
- W4321353575 hasConcept C168167062 @default.
- W4321353575 hasConcept C2776151529 @default.
- W4321353575 hasConcept C2781238097 @default.
- W4321353575 hasConcept C31972630 @default.
- W4321353575 hasConcept C41008148 @default.
- W4321353575 hasConcept C41895202 @default.
- W4321353575 hasConcept C7149132 @default.
- W4321353575 hasConcept C76155785 @default.
- W4321353575 hasConcept C94915269 @default.
- W4321353575 hasConcept C97355855 @default.
- W4321353575 hasConceptScore W4321353575C108583219 @default.
- W4321353575 hasConceptScore W4321353575C119857082 @default.
- W4321353575 hasConceptScore W4321353575C121332964 @default.
- W4321353575 hasConceptScore W4321353575C138885662 @default.
- W4321353575 hasConceptScore W4321353575C153180895 @default.
- W4321353575 hasConceptScore W4321353575C154945302 @default.
- W4321353575 hasConceptScore W4321353575C168167062 @default.
- W4321353575 hasConceptScore W4321353575C2776151529 @default.
- W4321353575 hasConceptScore W4321353575C2781238097 @default.
- W4321353575 hasConceptScore W4321353575C31972630 @default.
- W4321353575 hasConceptScore W4321353575C41008148 @default.
- W4321353575 hasConceptScore W4321353575C41895202 @default.
- W4321353575 hasConceptScore W4321353575C7149132 @default.
- W4321353575 hasConceptScore W4321353575C76155785 @default.
- W4321353575 hasConceptScore W4321353575C94915269 @default.
- W4321353575 hasConceptScore W4321353575C97355855 @default.
- W4321353575 hasLocation W43213535751 @default.
- W4321353575 hasLocation W43213535752 @default.
- W4321353575 hasOpenAccess W4321353575 @default.
- W4321353575 hasPrimaryLocation W43213535751 @default.
- W4321353575 hasRelatedWork W2145559838 @default.
- W4321353575 hasRelatedWork W2164121020 @default.
- W4321353575 hasRelatedWork W2970686063 @default.
- W4321353575 hasRelatedWork W3116498279 @default.
- W4321353575 hasRelatedWork W3183027292 @default.
- W4321353575 hasRelatedWork W3210378990 @default.
- W4321353575 hasRelatedWork W4254103348 @default.
- W4321353575 hasRelatedWork W4287549553 @default.
- W4321353575 hasRelatedWork W4289718052 @default.
- W4321353575 hasRelatedWork W4310285384 @default.
- W4321353575 isParatext "false" @default.
- W4321353575 isRetracted "false" @default.
- W4321353575 workType "book-chapter" @default.