Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308233944> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4308233944 abstract "Domain adaptation is an efficient technique to improve the performance of a system by adapting a pre-trained model to the given input data. The adaptation technique has been generally applied in conventional video codecs. For neural network-based systems, the encoder may adapt the decoder to the input data by fine-tuning a pre-trained model present at the decoder side. The weight update is then transferred to the decoder and the updated model is used to decode the bitstream. However, due to the large number of parameters in deep neural networks, the overhead of the weight update may diminish the gain from the adaptation technique. In recent years, various methods have been proposed to reduce the overhead without significantly compromising the gain. In this paper, we propose an adaptive multi-scale progressive probability model for lossless image compression. The proposed method uses the data that has already been processed at the inference stage to fine-tune the probability model. Importantly, the decoder can apply the fine-tuning by itself resulting a small adaptation overhead to help the decoder in performing the fine-tuning. The proposed method achieves up to 0.28 bits-per-pixel (BPP) reduction on four benchmark datasets compared to the state-of-the-art method." @default.
- W4308233944 created "2022-11-09" @default.
- W4308233944 creator A5002546998 @default.
- W4308233944 creator A5029604638 @default.
- W4308233944 creator A5035296788 @default.
- W4308233944 creator A5044816664 @default.
- W4308233944 creator A5049106121 @default.
- W4308233944 date "2022-10-16" @default.
- W4308233944 modified "2023-10-14" @default.
- W4308233944 title "Adaptive Multi-Scale Progressive Probability Model for Lossless Image Compression" @default.
- W4308233944 cites W2064674198 @default.
- W4308233944 cites W2099419573 @default.
- W4308233944 cites W2129768577 @default.
- W4308233944 cites W2146395539 @default.
- W4308233944 cites W2786808285 @default.
- W4308233944 cites W2965631471 @default.
- W4308233944 cites W2984555515 @default.
- W4308233944 cites W3094954034 @default.
- W4308233944 cites W3117485197 @default.
- W4308233944 cites W3197337676 @default.
- W4308233944 cites W3202918664 @default.
- W4308233944 cites W4205266802 @default.
- W4308233944 cites W4288083516 @default.
- W4308233944 doi "https://doi.org/10.1109/icip46576.2022.9897690" @default.
- W4308233944 hasPublicationYear "2022" @default.
- W4308233944 type Work @default.
- W4308233944 citedByCount "0" @default.
- W4308233944 crossrefType "proceedings-article" @default.
- W4308233944 hasAuthorship W4308233944A5002546998 @default.
- W4308233944 hasAuthorship W4308233944A5029604638 @default.
- W4308233944 hasAuthorship W4308233944A5035296788 @default.
- W4308233944 hasAuthorship W4308233944A5044816664 @default.
- W4308233944 hasAuthorship W4308233944A5049106121 @default.
- W4308233944 hasConcept C111919701 @default.
- W4308233944 hasConcept C11413529 @default.
- W4308233944 hasConcept C118505674 @default.
- W4308233944 hasConcept C13280743 @default.
- W4308233944 hasConcept C136695289 @default.
- W4308233944 hasConcept C154945302 @default.
- W4308233944 hasConcept C161765866 @default.
- W4308233944 hasConcept C185798385 @default.
- W4308233944 hasConcept C205649164 @default.
- W4308233944 hasConcept C2779960059 @default.
- W4308233944 hasConcept C41008148 @default.
- W4308233944 hasConcept C50644808 @default.
- W4308233944 hasConcept C57273362 @default.
- W4308233944 hasConcept C78548338 @default.
- W4308233944 hasConcept C81081738 @default.
- W4308233944 hasConcept C9390403 @default.
- W4308233944 hasConceptScore W4308233944C111919701 @default.
- W4308233944 hasConceptScore W4308233944C11413529 @default.
- W4308233944 hasConceptScore W4308233944C118505674 @default.
- W4308233944 hasConceptScore W4308233944C13280743 @default.
- W4308233944 hasConceptScore W4308233944C136695289 @default.
- W4308233944 hasConceptScore W4308233944C154945302 @default.
- W4308233944 hasConceptScore W4308233944C161765866 @default.
- W4308233944 hasConceptScore W4308233944C185798385 @default.
- W4308233944 hasConceptScore W4308233944C205649164 @default.
- W4308233944 hasConceptScore W4308233944C2779960059 @default.
- W4308233944 hasConceptScore W4308233944C41008148 @default.
- W4308233944 hasConceptScore W4308233944C50644808 @default.
- W4308233944 hasConceptScore W4308233944C57273362 @default.
- W4308233944 hasConceptScore W4308233944C78548338 @default.
- W4308233944 hasConceptScore W4308233944C81081738 @default.
- W4308233944 hasConceptScore W4308233944C9390403 @default.
- W4308233944 hasLocation W43082339441 @default.
- W4308233944 hasOpenAccess W4308233944 @default.
- W4308233944 hasPrimaryLocation W43082339441 @default.
- W4308233944 hasRelatedWork W2061492147 @default.
- W4308233944 hasRelatedWork W2075543035 @default.
- W4308233944 hasRelatedWork W2123886553 @default.
- W4308233944 hasRelatedWork W2129906755 @default.
- W4308233944 hasRelatedWork W2143341136 @default.
- W4308233944 hasRelatedWork W2150225017 @default.
- W4308233944 hasRelatedWork W2610181890 @default.
- W4308233944 hasRelatedWork W2755766871 @default.
- W4308233944 hasRelatedWork W4206534210 @default.
- W4308233944 hasRelatedWork W4386942242 @default.
- W4308233944 isParatext "false" @default.
- W4308233944 isRetracted "false" @default.
- W4308233944 workType "article" @default.