Linking pages
- Deep Learning for Computer Vision is not just Transformers: Facebook AI and UC Berkeley Propose a Convolutional Network for the 2020s - MarkTechPost https://www.marktechpost.com/2022/02/07/deep-learning-for-computer-vision-is-not-just-transformers-facebook-ai-and-uc-berkeley-propose-a-convolutional-network-for-the-2020s/ 5 comments
- Google Research Proposes MaskGIT: A New Deep Learning Technique Based on Bi-Directional Generative Transformers For High-Quality and Fast Image Synthesis - MarkTechPost https://www.marktechpost.com/2022/03/22/google-research-proposes-maskgit-a-new-deep-learning-technique-based-on-bi-directional-generative-transformers-for-high-quality-and-fast-image-synthesis/ 1 comment
- Researchers from Microsoft Asia and Peking University Proposed NUWA-Infinity, a Model to Generate High-Resolution, Arbitrarily-Sized Images and Videos - MarkTechPost https://www.marktechpost.com/2022/08/26/researchers-from-microsoft-asia-and-peking-university-proposed-nuwa-infinity-a-model-to-generate-high-resolution-arbitrarily-sized-images-and-videos/ 0 comments
- NVIDIA and Tel-Aviv University Researchers Propose a Computer Vision Method based on Textual Inversion to Insert New Concepts into Pre-Trained Text-to-Image Models - MarkTechPost https://www.marktechpost.com/2022/08/31/nvidia-and-tel-aviv-university-researchers-propose-a-computer-vision-method-based-on-textual-inversion-to-insert-new-concepts-into-pre-trained-text-to-image-models/ 0 comments
- Cool Computer Vision Startups in 2022 - MarkTechPost https://www.marktechpost.com/2022/09/13/cool-computer-vision-startups-in-2022/ 0 comments
- Google AI Introduces A Multi-Axis Approach for Vision Transformer and MLP Models - MarkTechPost https://www.marktechpost.com/2022/09/14/google-ai-introduces-a-multi-axis-approach-for-vision-transformer-and-mlp-models/ 0 comments
- Latest Computer Vision Research Proposes SLaK (Sparse Large Kernel Network), a Pure Convolutional Neural Network (CNN) Architecture based on Dynamic Sparsity Equipped with an Unprecedented Kernel Size of 51x51 - MarkTechPost https://www.marktechpost.com/2022/10/05/latest-computer-vision-research-proposes-slak-sparse-large-kernel-network-a-pure-convolutional-neural-network-cnn-architecture-based-on-dynamic-sparsity-equipped-with-an-unprecedented-kernel-size/ 0 comments
- Nota AI Introduces New Machine Learning Tools Under Its NetsPresso Platform For Automatically Searching Optimized Models And Making Compression Process Easy And Fast - MarkTechPost https://www.marktechpost.com/2022/04/24/nota-ai-introduces-new-machine-learning-tools-under-its-netspresso-platform-for-automatically-searching-optimized-models-and-making-compression-process-easy-and-fast/ 0 comments
- Researchers from China Propose DAT: a Deformable Vision Transformer to Compute Self-Attention in a Data-Aware Fashion - MarkTechPost https://www.marktechpost.com/2022/07/15/researchers-from-china-propose-dat-a-deformable-vision-transformer-to-compute-self-attention-in-a-data-aware-fashion/ 0 comments
- Stanford Researchers Introduced a Novel Deep Learning Computer-Assisted System for Real-Time Open Surgery and AVOS (the Annotation Videos of Open Surgery) Dataset - MarkTechPost https://www.marktechpost.com/2022/04/12/stanford-researchers-introduced-a-novel-deep-learning-computer-assisted-system-for-real-time-open-surgery-and-avos-the-annotation-videos-of-open-surgery-dataset%ef%bf%bc/ 0 comments
- Meta AI Introduces 'Make-A-Scene': A Deep Generative Technique Based On An Autoregressive Transformer For Text-To-Image Synthesis With Human Priors - MarkTechPost https://www.marktechpost.com/2022/05/12/meta-ai-introduces-make-a-scene-a-deep-generative-technique-based-on-an-autoregressive-transformer-for-text-to-image-synthesis-with-human-priors/ 0 comments
- Latest Artificial Intelligence (AI) Research At Google Presents 'Imagic,' An Effective Technique Based On Diffusion Models To Edit Images With Text Prompts - MarkTechPost https://www.marktechpost.com/2022/10/31/latest-artificial-intelligence-ai-research-at-google-presents-imagic-an-effective-technique-based-on-diffusion-models-to-edit-images-with-text-prompts/ 0 comments
Linked pages
- [2208.12242] DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation https://arxiv.org/abs/2208.12242 2 comments
- DreamBooth https://dreambooth.github.io/ 1 comment
- Researchers from Microsoft Asia and Peking University Proposed NUWA-Infinity, a Model to Generate High-Resolution, Arbitrarily-Sized Images and Videos - MarkTechPost https://www.marktechpost.com/2022/08/26/researchers-from-microsoft-asia-and-peking-university-proposed-nuwa-infinity-a-model-to-generate-high-resolution-arbitrarily-sized-images-and-videos/ 0 comments
- NVIDIA and Tel-Aviv University Researchers Propose a Computer Vision Method based on Textual Inversion to Insert New Concepts into Pre-Trained Text-to-Image Models - MarkTechPost https://www.marktechpost.com/2022/08/31/nvidia-and-tel-aviv-university-researchers-propose-a-computer-vision-method-based-on-textual-inversion-to-insert-new-concepts-into-pre-trained-text-to-image-models/ 0 comments
- Cool Computer Vision Startups in 2022 - MarkTechPost https://www.marktechpost.com/2022/09/13/cool-computer-vision-startups-in-2022/ 0 comments
- Google AI Introduces A Multi-Axis Approach for Vision Transformer and MLP Models - MarkTechPost https://www.marktechpost.com/2022/09/14/google-ai-introduces-a-multi-axis-approach-for-vision-transformer-and-mlp-models/ 0 comments
- Latest Computer Vision Research Proposes SLaK (Sparse Large Kernel Network), a Pure Convolutional Neural Network (CNN) Architecture based on Dynamic Sparsity Equipped with an Unprecedented Kernel Size of 51x51 - MarkTechPost https://www.marktechpost.com/2022/10/05/latest-computer-vision-research-proposes-slak-sparse-large-kernel-network-a-pure-convolutional-neural-network-cnn-architecture-based-on-dynamic-sparsity-equipped-with-an-unprecedented-kernel-size/ 0 comments
- Researchers From China Propose 'LViT', A Language-Vision Model To Leverage Text Medical Reports For Improved Segmentation - MarkTechPost https://www.marktechpost.com/2022/08/02/researchers-from-china-propose-lvit-a-language-vision-model-to-leverage-text-medical-reports-for-improved-segmentation/ 0 comments