Matches in SemOpenAlex for { <https://semopenalex.org/work/W3011408759> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W3011408759 abstract "Human drivers learn driving skills from both regular (non-accidental) and accidental driving experiences, while most of current self-driving research focuses on regular driving only. We argue that learning from accidental driving data is necessary for robustly modeling driving behavior. A main challenge, however, is how accident data can be effectively used together with regular data to learn vehicle motion, since manually labeling accident data without expertise is significantly difficult. Our proposed solution for robust vehicle motion learning, in this paper, is to integrate layer-level discriminability and neuron coverage(neuron-level robustness) regulariziers into an unsupervised generative network for video prediction. Layer-level discriminability increases divergence of feature distribution between the regular data and accident data at network layers. Neuron coverage regulariziers enlarge interval span of neuron activation adopted by training samples, to reduce probability that a sample falls into untested interval regions. To accelerate training process, we propose adaptive filter reuse based on neuron coverage. Our strategies of filter reuse reduce structural network parameters, encourage memory reuse, and guarantee effectiveness of robust vehicle motion learning. Experiments results show that our model improves the inference accuracy by 1.1% compared to FCMLSTM, and cut down 10.2% training time over the traditional method with negligible accuracy loss." @default.
- W3011408759 created "2020-03-23" @default.
- W3011408759 creator A5048629905 @default.
- W3011408759 creator A5058073627 @default.
- W3011408759 creator A5059605240 @default.
- W3011408759 creator A5083581319 @default.
- W3011408759 date "2019-10-01" @default.
- W3011408759 modified "2023-09-26" @default.
- W3011408759 title "Efficiently Learning a Robust Self-Driving Model with Neuron Coverage Aware Adaptive Filter Reuse" @default.
- W3011408759 doi "https://doi.org/10.1109/sips47522.2019.9020572" @default.
- W3011408759 hasPublicationYear "2019" @default.
- W3011408759 type Work @default.
- W3011408759 sameAs 3011408759 @default.
- W3011408759 citedByCount "0" @default.
- W3011408759 crossrefType "proceedings-article" @default.
- W3011408759 hasAuthorship W3011408759A5048629905 @default.
- W3011408759 hasAuthorship W3011408759A5058073627 @default.
- W3011408759 hasAuthorship W3011408759A5059605240 @default.
- W3011408759 hasAuthorship W3011408759A5083581319 @default.
- W3011408759 hasConcept C104317684 @default.
- W3011408759 hasConcept C106131492 @default.
- W3011408759 hasConcept C111919701 @default.
- W3011408759 hasConcept C119857082 @default.
- W3011408759 hasConcept C127413603 @default.
- W3011408759 hasConcept C154945302 @default.
- W3011408759 hasConcept C185592680 @default.
- W3011408759 hasConcept C206588197 @default.
- W3011408759 hasConcept C31972630 @default.
- W3011408759 hasConcept C41008148 @default.
- W3011408759 hasConcept C548081761 @default.
- W3011408759 hasConcept C55493867 @default.
- W3011408759 hasConcept C63479239 @default.
- W3011408759 hasConcept C98045186 @default.
- W3011408759 hasConceptScore W3011408759C104317684 @default.
- W3011408759 hasConceptScore W3011408759C106131492 @default.
- W3011408759 hasConceptScore W3011408759C111919701 @default.
- W3011408759 hasConceptScore W3011408759C119857082 @default.
- W3011408759 hasConceptScore W3011408759C127413603 @default.
- W3011408759 hasConceptScore W3011408759C154945302 @default.
- W3011408759 hasConceptScore W3011408759C185592680 @default.
- W3011408759 hasConceptScore W3011408759C206588197 @default.
- W3011408759 hasConceptScore W3011408759C31972630 @default.
- W3011408759 hasConceptScore W3011408759C41008148 @default.
- W3011408759 hasConceptScore W3011408759C548081761 @default.
- W3011408759 hasConceptScore W3011408759C55493867 @default.
- W3011408759 hasConceptScore W3011408759C63479239 @default.
- W3011408759 hasConceptScore W3011408759C98045186 @default.
- W3011408759 hasLocation W30114087591 @default.
- W3011408759 hasOpenAccess W3011408759 @default.
- W3011408759 hasPrimaryLocation W30114087591 @default.
- W3011408759 hasRelatedWork W11738893 @default.
- W3011408759 hasRelatedWork W12219208 @default.
- W3011408759 hasRelatedWork W12803709 @default.
- W3011408759 hasRelatedWork W12829028 @default.
- W3011408759 hasRelatedWork W4972971 @default.
- W3011408759 hasRelatedWork W5668360 @default.
- W3011408759 hasRelatedWork W7619760 @default.
- W3011408759 hasRelatedWork W8218506 @default.
- W3011408759 hasRelatedWork W929682 @default.
- W3011408759 hasRelatedWork W9948473 @default.
- W3011408759 isParatext "false" @default.
- W3011408759 isRetracted "false" @default.
- W3011408759 magId "3011408759" @default.
- W3011408759 workType "article" @default.