Hierarchical Residual Learning Based Vector Quantized Variational Autoencoder for Image Reconstruction and Generation
Hierarchical Residual Learning Based Vector Quantized Variational Autoencoder for Image Reconstruction and Generation
We propose a multi-layer variational autoencoder method, we call HR-VQVAE, that learns hierarchical discrete representations of the data. By utilizing a novel objective function, each layer in HR-VQVAE learns a discrete representation of the residual from previous layers through a vector quantized encoder. Furthermore, the representations at each layer are hierarchically linked to those at previous layers. We evaluate our method on the tasks of image reconstruction and generation. Experimental results demonstrate that the discrete representations learned by HR-VQVAE enable the decoder to reconstruct high-quality images with less distortion than the baseline methods, namely VQVAE and VQVAE-2. HR-VQVAE can also generate high-quality and diverse images that outperform state-of-the-art generative models, providing further verification of the efficiency of the learned representations. The hierarchical nature of HR-VQVAE i) reduces the decoding search time, making the method particularly suitable for high-load tasks and ii) allows to increase the codebook size without incurring the codebook collapse problem.
12 pages plus supplementary material. Submitted to BMVC 2022
- Royal Institute of Technology Sweden
- University of Palermo Italy
- University of Palermo Argentina
Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazioni, I.2, FOS: Computer and information sciences, Computer Science - Machine Learning, I.4, Computer Sciences, namely VQVAE and VQVAE-2. HR-VQVAE can also generate high-quality and diverse images that outper- form state-of-the-art generative models, Computer Vision and Pattern Recognition (cs.CV), the representations at each layer are hierarchically linked to those at previous layers. We evaluate our method on the tasks of image reconstruction and generation. Experimental results demonstrate that the discrete representations learned by HR-VQVAE enable the decoder to reconstruct high-quality images with less distortion than the baseline methods, Computer Science - Computer Vision and Pattern Recognition, each layer in HR-VQVAE learns a discrete representation of the residual from previous layers through a vector quantized encoder. Furthermore, We propose a multi-layer variational autoencoder method, we call HR-VQVAE, that learns hierarchical discrete representations of the data. By utilizing a novel objective function, each layer in HR-VQVAE learns a discrete representation of the residual from previous layers through a vector quantized encoder. Furthermore, the representations at each layer are hierarchically linked to those at previous layers. We evaluate our method on the tasks of image reconstruction and generation. Experimental results demonstrate that the discrete representations learned by HR-VQVAE enable the decoder to reconstruct high-quality images with less distortion than the baseline methods, namely VQVAE and VQVAE-2. HR-VQVAE can also generate high-quality and diverse images that outper- form state-of-the-art generative models, providing further verification of the efficiency of the learned representations. The hierarchical nature of HR-VQVAE i) reduces the decoing search time, making the method particularly suitable for high-load tasks and ii) allows to increase the codebook size without incurring the codebook collapse problem., that learns hierarchical discrete representations of the data. By utilizing a novel objective function, Machine Learning (cs.LG), Datavetenskap (datalogi), I.4; I.2, We propose a multi-layer variational autoencoder method, providing further verification of the efficiency of the learned representations. The hierarchical nature of HR-VQVAE i) reduces the decoing search time, making the method particularly suitable for high-load tasks and ii) allows to increase the codebook size without incurring the codebook collapse problem, we call HR-VQVAE
Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazioni, I.2, FOS: Computer and information sciences, Computer Science - Machine Learning, I.4, Computer Sciences, namely VQVAE and VQVAE-2. HR-VQVAE can also generate high-quality and diverse images that outper- form state-of-the-art generative models, Computer Vision and Pattern Recognition (cs.CV), the representations at each layer are hierarchically linked to those at previous layers. We evaluate our method on the tasks of image reconstruction and generation. Experimental results demonstrate that the discrete representations learned by HR-VQVAE enable the decoder to reconstruct high-quality images with less distortion than the baseline methods, Computer Science - Computer Vision and Pattern Recognition, each layer in HR-VQVAE learns a discrete representation of the residual from previous layers through a vector quantized encoder. Furthermore, We propose a multi-layer variational autoencoder method, we call HR-VQVAE, that learns hierarchical discrete representations of the data. By utilizing a novel objective function, each layer in HR-VQVAE learns a discrete representation of the residual from previous layers through a vector quantized encoder. Furthermore, the representations at each layer are hierarchically linked to those at previous layers. We evaluate our method on the tasks of image reconstruction and generation. Experimental results demonstrate that the discrete representations learned by HR-VQVAE enable the decoder to reconstruct high-quality images with less distortion than the baseline methods, namely VQVAE and VQVAE-2. HR-VQVAE can also generate high-quality and diverse images that outper- form state-of-the-art generative models, providing further verification of the efficiency of the learned representations. The hierarchical nature of HR-VQVAE i) reduces the decoing search time, making the method particularly suitable for high-load tasks and ii) allows to increase the codebook size without incurring the codebook collapse problem., that learns hierarchical discrete representations of the data. By utilizing a novel objective function, Machine Learning (cs.LG), Datavetenskap (datalogi), I.4; I.2, We propose a multi-layer variational autoencoder method, providing further verification of the efficiency of the learned representations. The hierarchical nature of HR-VQVAE i) reduces the decoing search time, making the method particularly suitable for high-load tasks and ii) allows to increase the codebook size without incurring the codebook collapse problem, we call HR-VQVAE
selected citations These citations are derived from selected sources.This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).0 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Average influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Average impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Average
Citations provided by BIP!Popularity provided by BIP!