Sökning: id:"swepub:oai:DiVA.org:liu-179904" >
Discriminative Regi...
Discriminative Region-based Multi-Label Zero-Shot Learning
-
- Narayan, Sanath (författare)
- Inception Institute of Artificial Intelligence, UAE,Incept Inst Artificial Intelligence, U Arab Emirates
-
- Gupta, Akshita (författare)
- Inception Institute of Artificial Intelligence, UAE,Incept Inst Artificial Intelligence, U Arab Emirates
-
- Khan, Salman (författare)
- Mohamed Bin Zayed University of AI, UAE,Mohamed Bin Zayed Univ AI, U Arab Emirates
-
visa fler...
-
- Khan, Fahad Shahbaz, 1983- (författare)
- Linköpings universitet,Datorseende,Tekniska fakulteten,Mohamed Bin Zayed University of AI, UAE,Mohamed Bin Zayed Univ AI, U Arab Emirates
-
- Shao, Ling (författare)
- Inception Institute of Artificial Intelligence, UAE,Incept Inst Artificial Intelligence, U Arab Emirates
-
- Shah, Mubarak (författare)
- University of Central Florida, USA,Univ Cent Florida, FL 32816 USA
-
visa färre...
-
(creator_code:org_t)
- IEEE, 2021
- Engelska.
-
Serie: arXiv.org ; 2108.09301
-
Ingår i: 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021). - : IEEE. - 9781665428125 ; , s. 8711-8720
- Relaterad länk:
-
https://arxiv.org/ab...
-
visa fler...
-
https://urn.kb.se/re...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Multi-label zero-shot learning (ZSL) is a more realistic counter-part of standard single-label ZSL since several objects can co-exist in a natural image. However, the occurrence of multiple objects complicates the reasoning and requires region-specific processing of visual features to preserve their contextual cues. We note that the best existing multi-label ZSL method takes a shared approach towards attending to region features with a common set of attention maps for all the classes. Such shared maps lead to diffused attention, which does not discriminatively focus on relevant locations when the number of classes are large. Moreover, mapping spatially-pooled visual features to the class semantics leads to inter-class feature entanglement, thus hampering the classification. Here, we propose an alternate approach towards region-based discriminability-preserving multi-label zero-shot classification. Our approach maintains the spatial resolution to preserve region-level characteristics and utilizes a bi-level attention module (BiAM) to enrich the features by incorporating both region and scene context information. The enriched region-level features are then mapped to the class semantics and only their class predictions are spatially pooled to obtain image-level predictions, thereby keeping the multi-class features disentangled. Our approach sets a new state of the art on two large-scale multi-label zero-shot benchmarks: NUS-WIDE and Open Images. On NUS-WIDE, our approach achieves an absolute gain of 6.9% mAP for ZSL, compared to the best published results.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Publikations- och innehållstyp
- vet (ämneskategori)
- ovr (ämneskategori)
Hitta via bibliotek
Till lärosätets databas