Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
RRRamprasaath R. SelvarajuMCMichael CogswellADAbhishek DasRVRamakrishna VedantamDPDevi Parikh
Georgia Institute of Technology · Menlo School · +1 more institution
Indexed inarxivcrossref
Abstract
No abstract available for this paper.
Citation impact
5,456
total citations
- FWCI
- 141.97
- Percentile
- 100%
- References
- 52
Citations per year
Authors
6- RRRamprasaath R. SelvarajuCorresponding
Georgia Institute of Technology
- MCMichael Cogswell
Georgia Institute of Technology
- ADAbhishek Das
Georgia Institute of Technology
- RVRamakrishna Vedantam
Georgia Institute of Technology
- DPDevi Parikh
Menlo School, Georgia Institute of Technology, Meta (United States)
Topics & keywords
Topics
Keywords
- Closed captioning
- Discriminative model
- Convolutional neural network
- Generalization
- Context (archaeology)
- Class (philosophy)
- Pattern recognition (psychology)
- Image (mathematics)
No related works found for this paper.
Funding
- NSNational Science FoundationAward: CAREER
- APAlfred P. Sloan Foundation
- PGPaul G. Allen Family Foundation
- GGoogle
- NNvidia
- VPVirginia Polytechnic Institute and State University
- AWAmazon Web Services
- DADefense Advanced Research Projects Agency
- OOOffice of Naval ResearchAwards: N00014-14-1-0679, N00014
- ARArmy Research Office