Matches in SemOpenAlex for { <https://semopenalex.org/work/W2337758703> ?p ?o ?g. }
- W2337758703 abstract "Machine-learning algorithms offer immense possibilities in the development of several cognitive applications. In fact, large scale machine-learning classifiers now represent the state-of-the-art in a wide range of object detection/classification problems. However, the network complexities of large-scale classifiers present them as one of the most challenging and energy intensive workloads across the computing spectrum. In this paper, we present a new approach to optimize energy efficiency of object detection tasks using semantic decomposition to build a hierarchical classification framework. We observe that certain semantic information like color/texture are common across various images in real-world datasets for object detection applications. We exploit these common semantic features to distinguish the objects of interest from the remaining inputs (non-objects of interest) in a dataset at a lower computational effort. We propose a 2-stage hierarchical classification framework, with increasing levels of complexity, wherein the first stage is trained to recognize the broad representative semantic features relevant to the object of interest. The first stage rejects the input instances that do not have the representative features and passes only the relevant instances to the second stage. Our methodology thus allows us to reject certain information at lower complexity and utilize the full computational effort of a network only on a smaller fraction of inputs to perform detection. We use color and texture as distinctive traits to carry out several experiments for object detection. Our experiments on the Caltech101/CIFAR10 dataset show that the proposed method yields 1.93x/1.46x improvement in average energy, respectively, over the traditional single classifier model." @default.
- W2337758703 created "2016-06-24" @default.
- W2337758703 creator A5010094713 @default.
- W2337758703 creator A5031161187 @default.
- W2337758703 creator A5032635465 @default.
- W2337758703 creator A5050310538 @default.
- W2337758703 creator A5065766721 @default.
- W2337758703 date "2015-09-29" @default.
- W2337758703 modified "2023-09-27" @default.
- W2337758703 title "Energy-Efficient Object Detection using Semantic Decomposition" @default.
- W2337758703 cites W1686810756 @default.
- W2337758703 cites W1958328135 @default.
- W2337758703 cites W1964545824 @default.
- W2337758703 cites W1969840923 @default.
- W2337758703 cites W1972472058 @default.
- W2337758703 cites W1976948919 @default.
- W2337758703 cites W1994967090 @default.
- W2337758703 cites W1998305460 @default.
- W2337758703 cites W1998901019 @default.
- W2337758703 cites W1998917233 @default.
- W2337758703 cites W2012844989 @default.
- W2337758703 cites W2034076462 @default.
- W2337758703 cites W2057434193 @default.
- W2337758703 cites W2091432990 @default.
- W2337758703 cites W2098633863 @default.
- W2337758703 cites W2104167780 @default.
- W2337758703 cites W2110819057 @default.
- W2337758703 cites W2124868070 @default.
- W2337758703 cites W2160815625 @default.
- W2337758703 cites W2161969291 @default.
- W2337758703 cites W2164598857 @default.
- W2337758703 cites W2168231600 @default.
- W2337758703 cites W2293873019 @default.
- W2337758703 cites W2335728318 @default.
- W2337758703 cites W2395106899 @default.
- W2337758703 cites W2546302380 @default.
- W2337758703 cites W2912573428 @default.
- W2337758703 cites W2952183644 @default.
- W2337758703 cites W587794757 @default.
- W2337758703 cites W2001336994 @default.
- W2337758703 hasPublicationYear "2015" @default.
- W2337758703 type Work @default.
- W2337758703 sameAs 2337758703 @default.
- W2337758703 citedByCount "1" @default.
- W2337758703 countsByYear W23377587032016 @default.
- W2337758703 crossrefType "posted-content" @default.
- W2337758703 hasAuthorship W2337758703A5010094713 @default.
- W2337758703 hasAuthorship W2337758703A5031161187 @default.
- W2337758703 hasAuthorship W2337758703A5032635465 @default.
- W2337758703 hasAuthorship W2337758703A5050310538 @default.
- W2337758703 hasAuthorship W2337758703A5065766721 @default.
- W2337758703 hasConcept C105795698 @default.
- W2337758703 hasConcept C11413529 @default.
- W2337758703 hasConcept C119857082 @default.
- W2337758703 hasConcept C121332964 @default.
- W2337758703 hasConcept C124681953 @default.
- W2337758703 hasConcept C153180895 @default.
- W2337758703 hasConcept C154945302 @default.
- W2337758703 hasConcept C165696696 @default.
- W2337758703 hasConcept C179799912 @default.
- W2337758703 hasConcept C186370098 @default.
- W2337758703 hasConcept C18903297 @default.
- W2337758703 hasConcept C2776151529 @default.
- W2337758703 hasConcept C2778755073 @default.
- W2337758703 hasConcept C2781238097 @default.
- W2337758703 hasConcept C33923547 @default.
- W2337758703 hasConcept C38652104 @default.
- W2337758703 hasConcept C41008148 @default.
- W2337758703 hasConcept C62520636 @default.
- W2337758703 hasConcept C64876066 @default.
- W2337758703 hasConcept C86803240 @default.
- W2337758703 hasConceptScore W2337758703C105795698 @default.
- W2337758703 hasConceptScore W2337758703C11413529 @default.
- W2337758703 hasConceptScore W2337758703C119857082 @default.
- W2337758703 hasConceptScore W2337758703C121332964 @default.
- W2337758703 hasConceptScore W2337758703C124681953 @default.
- W2337758703 hasConceptScore W2337758703C153180895 @default.
- W2337758703 hasConceptScore W2337758703C154945302 @default.
- W2337758703 hasConceptScore W2337758703C165696696 @default.
- W2337758703 hasConceptScore W2337758703C179799912 @default.
- W2337758703 hasConceptScore W2337758703C186370098 @default.
- W2337758703 hasConceptScore W2337758703C18903297 @default.
- W2337758703 hasConceptScore W2337758703C2776151529 @default.
- W2337758703 hasConceptScore W2337758703C2778755073 @default.
- W2337758703 hasConceptScore W2337758703C2781238097 @default.
- W2337758703 hasConceptScore W2337758703C33923547 @default.
- W2337758703 hasConceptScore W2337758703C38652104 @default.
- W2337758703 hasConceptScore W2337758703C41008148 @default.
- W2337758703 hasConceptScore W2337758703C62520636 @default.
- W2337758703 hasConceptScore W2337758703C64876066 @default.
- W2337758703 hasConceptScore W2337758703C86803240 @default.
- W2337758703 hasLocation W23377587031 @default.
- W2337758703 hasOpenAccess W2337758703 @default.
- W2337758703 hasPrimaryLocation W23377587031 @default.
- W2337758703 hasRelatedWork W109283469 @default.
- W2337758703 hasRelatedWork W1842053956 @default.
- W2337758703 hasRelatedWork W2070927566 @default.
- W2337758703 hasRelatedWork W2120176405 @default.
- W2337758703 hasRelatedWork W2592414189 @default.
- W2337758703 hasRelatedWork W2613048230 @default.