Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312458399> ?p ?o ?g. }
- W4312458399 endingPage "491" @default.
- W4312458399 startingPage "473" @default.
- W4312458399 abstract "Image restoration algorithms such as super resolution (SR) are indispensable pre-processing modules for object detection in low quality images. Most of these algorithms assume the degradation is fixed and known a priori. However, in practical, either the real degradation or optimal up-sampling ratio rate is unknown or differs from assumption, leading to a deteriorating performance for both the pre-processing module and the consequent high-level task such as object detection. Here, we propose a novel self-supervised framework to detect objects in degraded low resolution images. We utilizes the downsampling degradation as a kind of transformation for self-supervised signals to explore the equivariant representation against various resolutions and other degradation conditions. The Auto Encoding Resolution in Self-supervision (AERIS) framework could further take the advantage of advanced SR architectures with an arbitrary resolution restoring decoder to reconstruct the original correspondence from the degraded input image. Both the representation learning and object detection are optimized jointly in an end-to-end training fashion. The generic AERIS framework could be implemented on various mainstream object detection architectures with different backbones. The extensive experiments show that our methods has achieved superior performance compared with existing methods when facing variant degradation situations. Code is available at this link https://github.com/cuiziteng/ECCV_AERIS ." @default.
- W4312458399 created "2023-01-04" @default.
- W4312458399 creator A5035551115 @default.
- W4312458399 creator A5042711470 @default.
- W4312458399 creator A5053647594 @default.
- W4312458399 creator A5059094652 @default.
- W4312458399 creator A5068185303 @default.
- W4312458399 creator A5079180694 @default.
- W4312458399 creator A5082230753 @default.
- W4312458399 creator A5088533080 @default.
- W4312458399 date "2022-01-01" @default.
- W4312458399 modified "2023-10-10" @default.
- W4312458399 title "Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection" @default.
- W4312458399 cites W1536680647 @default.
- W4312458399 cites W1861492603 @default.
- W4312458399 cites W2010981316 @default.
- W4312458399 cites W2031489346 @default.
- W4312458399 cites W2054515210 @default.
- W4312458399 cites W2108238208 @default.
- W4312458399 cites W2108598243 @default.
- W4312458399 cites W2115548755 @default.
- W4312458399 cites W2146782367 @default.
- W4312458399 cites W2150066425 @default.
- W4312458399 cites W2172275395 @default.
- W4312458399 cites W2194775991 @default.
- W4312458399 cites W2242218935 @default.
- W4312458399 cites W2331128040 @default.
- W4312458399 cites W2476548250 @default.
- W4312458399 cites W2519963891 @default.
- W4312458399 cites W2607041014 @default.
- W4312458399 cites W2613155248 @default.
- W4312458399 cites W2626739722 @default.
- W4312458399 cites W2768489488 @default.
- W4312458399 cites W2780544323 @default.
- W4312458399 cites W2794849006 @default.
- W4312458399 cites W2798748382 @default.
- W4312458399 cites W2962814024 @default.
- W4312458399 cites W2963031226 @default.
- W4312458399 cites W2963037989 @default.
- W4312458399 cites W2963102887 @default.
- W4312458399 cites W2963372104 @default.
- W4312458399 cites W2963470893 @default.
- W4312458399 cites W2963606888 @default.
- W4312458399 cites W2963729050 @default.
- W4312458399 cites W2964277374 @default.
- W4312458399 cites W2964325192 @default.
- W4312458399 cites W2982143932 @default.
- W4312458399 cites W2982376094 @default.
- W4312458399 cites W2987150909 @default.
- W4312458399 cites W3013338555 @default.
- W4312458399 cites W3034239311 @default.
- W4312458399 cites W3035028692 @default.
- W4312458399 cites W3035302306 @default.
- W4312458399 cites W3106297436 @default.
- W4312458399 cites W3138516171 @default.
- W4312458399 cites W3168684807 @default.
- W4312458399 cites W3174865552 @default.
- W4312458399 cites W3176165731 @default.
- W4312458399 cites W3203631022 @default.
- W4312458399 cites W3204374989 @default.
- W4312458399 cites W3207918547 @default.
- W4312458399 cites W4214753187 @default.
- W4312458399 cites W4225672218 @default.
- W4312458399 cites W4312368691 @default.
- W4312458399 cites W54257720 @default.
- W4312458399 doi "https://doi.org/10.1007/978-3-031-20077-9_28" @default.
- W4312458399 hasPublicationYear "2022" @default.
- W4312458399 type Work @default.
- W4312458399 citedByCount "0" @default.
- W4312458399 crossrefType "book-chapter" @default.
- W4312458399 hasAuthorship W4312458399A5035551115 @default.
- W4312458399 hasAuthorship W4312458399A5042711470 @default.
- W4312458399 hasAuthorship W4312458399A5053647594 @default.
- W4312458399 hasAuthorship W4312458399A5059094652 @default.
- W4312458399 hasAuthorship W4312458399A5068185303 @default.
- W4312458399 hasAuthorship W4312458399A5079180694 @default.
- W4312458399 hasAuthorship W4312458399A5082230753 @default.
- W4312458399 hasAuthorship W4312458399A5088533080 @default.
- W4312458399 hasBestOaLocation W43124583992 @default.
- W4312458399 hasConcept C104317684 @default.
- W4312458399 hasConcept C110384440 @default.
- W4312458399 hasConcept C115961682 @default.
- W4312458399 hasConcept C153180895 @default.
- W4312458399 hasConcept C154945302 @default.
- W4312458399 hasConcept C177264268 @default.
- W4312458399 hasConcept C17744445 @default.
- W4312458399 hasConcept C185592680 @default.
- W4312458399 hasConcept C199360897 @default.
- W4312458399 hasConcept C199539241 @default.
- W4312458399 hasConcept C204241405 @default.
- W4312458399 hasConcept C2776151529 @default.
- W4312458399 hasConcept C2776359362 @default.
- W4312458399 hasConcept C2776760102 @default.
- W4312458399 hasConcept C2779679103 @default.
- W4312458399 hasConcept C2781238097 @default.
- W4312458399 hasConcept C31972630 @default.
- W4312458399 hasConcept C41008148 @default.
- W4312458399 hasConcept C55493867 @default.