🟢 Green Hierarchical Vision Transformer for Masked Image Modeling
Github: https://github.com/layneh/greenmim
Paper: https://arxiv.org/abs/2205.13515v1
Dataset: https://paperswithcode.com/dataset/coco
@ai_machinelearning_big_data
Github: https://github.com/layneh/greenmim
Paper: https://arxiv.org/abs/2205.13515v1
Dataset: https://paperswithcode.com/dataset/coco
@ai_machinelearning_big_data
👍13
This media is not supported in your browser
VIEW IN TELEGRAM
🔻 AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition
Github: https://github.com/ShoufaChen/AdaptFormer
Paper: https://arxiv.org/abs/2205.13535v1
Dataset: https://paperswithcode.com/dataset/something-something-v2
@ai_machinelearning_big_data
Github: https://github.com/ShoufaChen/AdaptFormer
Paper: https://arxiv.org/abs/2205.13535v1
Dataset: https://paperswithcode.com/dataset/something-something-v2
@ai_machinelearning_big_data
👍15
Surface Vision Transformers
Github: https://github.com/metrics-lab/surface-vision-transformers
Paper: https://arxiv.org/abs/2205.15836v1
@ai_machinelearning_big_data
Github: https://github.com/metrics-lab/surface-vision-transformers
Paper: https://arxiv.org/abs/2205.15836v1
@ai_machinelearning_big_data
👍7👎5
✈️ HIRL: A General Framework for Hierarchical Image Representation Learning
Github: https://github.com/hirl-team/hirl
Paper: https://arxiv.org/abs/2205.13159v1
Dataset: https://paperswithcode.com/dataset/places205
@ai_machinelearning_big_data
Github: https://github.com/hirl-team/hirl
Paper: https://arxiv.org/abs/2205.13159v1
Dataset: https://paperswithcode.com/dataset/places205
@ai_machinelearning_big_data
👍15👎1
🔝 PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation
Github: https://github.com/naiyugao/panopticdepth
Paper: http://arxiv.org/abs/2206.00468
Dataset: https://paperswithcode.com/dataset/cityscapes
@ai_machinelearning_big_data
Github: https://github.com/naiyugao/panopticdepth
Paper: http://arxiv.org/abs/2206.00468
Dataset: https://paperswithcode.com/dataset/cityscapes
@ai_machinelearning_big_data
👍10
🦠 MaSIF- Molecular Surface Interaction Fingerprints: Geometric deep learning to decipher patterns in protein molecular surfaces.
MaSIF is a proof-of-concept method to decipher patterns in protein surfaces important for specific biomolecular interactions.
Github: https://github.com/LPDI-EPFL/masif
Paper: https://www.nature.com/articles/s41592-019-0666-6
Data: https://github.com/LPDI-EPFL/masif#MaSIF-data-preparation
@ai_machinelearning_big_data
MaSIF is a proof-of-concept method to decipher patterns in protein surfaces important for specific biomolecular interactions.
Github: https://github.com/LPDI-EPFL/masif
Paper: https://www.nature.com/articles/s41592-019-0666-6
Data: https://github.com/LPDI-EPFL/masif#MaSIF-data-preparation
@ai_machinelearning_big_data
👍15🔥3
🔊A Python library for audio feature extraction, classification, segmentation and applications.
Code: PyAudioAnalysis
Code: PyAudioAnalysis
👍11👎2🔥1
🪄 Investigating the Role of Image Retrieval for Visual Localization -- An exhaustive benchmark.
Github: https://github.com/naver/kapture-localization
Paper: https://arxiv.org/abs/2205.15761v1
Data: https://paperswithcode.com/dataset/inloc
@ai_machinelearning_big_data
Github: https://github.com/naver/kapture-localization
Paper: https://arxiv.org/abs/2205.15761v1
Data: https://paperswithcode.com/dataset/inloc
@ai_machinelearning_big_data
👍9🔥3❤1
This media is not supported in your browser
VIEW IN TELEGRAM
💬 Text2Human - Official PyTorch Implementation
We synthesize full-body human images starting from a given human pose
Github: https://github.com/yumingj/Text2Human
Project: https://yumingj.github.io/projects/Text2Human.html
StyleGAN: https://github.com/stylegan-human/stylegan-human
Paper: https://arxiv.org/abs/2205.15996v1
Dataset: https://github.com/yumingj/DeepFashion-MultiModal
Demo video: https://youtu.be/yKh4VORA_E0
@ai_machinelearning_big_data
We synthesize full-body human images starting from a given human pose
Github: https://github.com/yumingj/Text2Human
Project: https://yumingj.github.io/projects/Text2Human.html
StyleGAN: https://github.com/stylegan-human/stylegan-human
Paper: https://arxiv.org/abs/2205.15996v1
Dataset: https://github.com/yumingj/DeepFashion-MultiModal
Demo video: https://youtu.be/yKh4VORA_E0
@ai_machinelearning_big_data
👍28
🎆 Optimizing Relevance Maps of Vision Transformers Improves Robustness
This code allows to finetune the explainability maps of Vision Transformers to enhance robustness.
Github: https://github.com/hila-chefer/robustvit
Colab: https://colab.research.google.com/github/hila-chefer/RobustViT/blob/master/RobustViT.ipynb
Paper: https://arxiv.org/abs/2206.01161
Dataset: https://github.com/UnsupervisedSemanticSegmentation/ImageNet-S
@ai_machinelearning_big_data
This code allows to finetune the explainability maps of Vision Transformers to enhance robustness.
Github: https://github.com/hila-chefer/robustvit
Colab: https://colab.research.google.com/github/hila-chefer/RobustViT/blob/master/RobustViT.ipynb
Paper: https://arxiv.org/abs/2206.01161
Dataset: https://github.com/UnsupervisedSemanticSegmentation/ImageNet-S
@ai_machinelearning_big_data
👍18🔥2
UniSRec
The proposed approach utilizes the associated denoscription text of items to learn transferable representations across different recommendation scenarios.
Github: https://github.com/rucaibox/unisrec
Paper: https://arxiv.org/abs/2206.05941v1
Google Drive: https://drive.google.com/drive/folders/1Uik0fMk4oquV_bS9lXTZuExAYbIDkEMW?usp=sharing
The proposed approach utilizes the associated denoscription text of items to learn transferable representations across different recommendation scenarios.
Github: https://github.com/rucaibox/unisrec
Paper: https://arxiv.org/abs/2206.05941v1
Google Drive: https://drive.google.com/drive/folders/1Uik0fMk4oquV_bS9lXTZuExAYbIDkEMW?usp=sharing
🔥8👍3
🔘 Squeezeformer: An Efficient Transformer for Automatic Speech Recognition
Github: https://github.com/kssteven418/squeezeformer
Paper: https://arxiv.org/abs/2206.00888v1
Dataset: https://paperswithcode.com/dataset/librispeech
@ai_machinelearning_big_data
Github: https://github.com/kssteven418/squeezeformer
Paper: https://arxiv.org/abs/2206.00888v1
Dataset: https://paperswithcode.com/dataset/librispeech
@ai_machinelearning_big_data
👍12❤3
OntoMerger: An Ontology Integration Library for Deduplicating and Connecting Knowledge Graph Nodes
OntoMerger is an ontology alignment library for deduplicating knowledge graph nodes
Github: https://github.com/astrazeneca/onto_merger
Paper: https://arxiv.org/abs/2206.02238v1
Documentation: https://ontomerger.readthedocs.io/
@ai_machinelearning_big_data
OntoMerger is an ontology alignment library for deduplicating knowledge graph nodes
Github: https://github.com/astrazeneca/onto_merger
Paper: https://arxiv.org/abs/2206.02238v1
Documentation: https://ontomerger.readthedocs.io/
@ai_machinelearning_big_data
👍13👎6😱1
👁🗨 CVNets: A library for training computer vision networks
Improved model, MobileViTv2, is state-of-the-art on several mobile vision tasks, including ImageNet object classification and MS-COCO object detection.
Github: https://github.com/apple/ml-cvnets
Examples: https://github.com/apple/ml-cvnets/blob/main/docs/source/en/models
Paper: https://arxiv.org/abs/2206.02680v1
Dataset: https://paperswithcode.com/dataset/coco
@ai_machinelearning_big_data
Improved model, MobileViTv2, is state-of-the-art on several mobile vision tasks, including ImageNet object classification and MS-COCO object detection.
Github: https://github.com/apple/ml-cvnets
Examples: https://github.com/apple/ml-cvnets/blob/main/docs/source/en/models
Paper: https://arxiv.org/abs/2206.02680v1
Dataset: https://paperswithcode.com/dataset/coco
@ai_machinelearning_big_data
👍20
This media is not supported in your browser
VIEW IN TELEGRAM
🔥 EG3D: Efficient Geometry-aware 3D Generative Adversarial Networks by Nvidia
Expressive hybrid explicit-implicit network architecture that, together with other design choices, synthesizes not only high-resolution multi-view-consistent images in real time but also produces high-quality 3D geometry.
Github: https://github.com/NVlabs/eg3d
Project: https://nvlabs.github.io/eg3d/
Video: https://www.youtube.com/watch?v=cXxEwI7QbKg&feature=emb_logo&ab_channel=StanfordComputationalImagingLab
Paper: https://nvlabs.github.io/eg3d/media/eg3d.pdf
@ai_machinelearning_big_data
Expressive hybrid explicit-implicit network architecture that, together with other design choices, synthesizes not only high-resolution multi-view-consistent images in real time but also produces high-quality 3D geometry.
Github: https://github.com/NVlabs/eg3d
Project: https://nvlabs.github.io/eg3d/
Video: https://www.youtube.com/watch?v=cXxEwI7QbKg&feature=emb_logo&ab_channel=StanfordComputationalImagingLab
Paper: https://nvlabs.github.io/eg3d/media/eg3d.pdf
@ai_machinelearning_big_data
👍20🔥12❤1😱1
🔦 Featurized Query R-CNN
Featurized object queries predicted by a query generation network in the well-established Faster R-CNN framework and develop a Featurized Query R-CN
Github: https://github.com/hustvl/featurized-queryrcnn
Paper: https://arxiv.org/abs/2206.06258v1
Dataset: https://paperswithcode.com/dataset/crowdhuman
@ai_machinelearning_big_data
Featurized object queries predicted by a query generation network in the well-established Faster R-CNN framework and develop a Featurized Query R-CN
Github: https://github.com/hustvl/featurized-queryrcnn
Paper: https://arxiv.org/abs/2206.06258v1
Dataset: https://paperswithcode.com/dataset/crowdhuman
@ai_machinelearning_big_data
GitHub
GitHub - hustvl/Featurized-QueryRCNN: Featurized Query R-CNN
Featurized Query R-CNN. Contribute to hustvl/Featurized-QueryRCNN development by creating an account on GitHub.
👍10
Can CNNs Be More Robust Than Transformers?
CNN architectures without any attention-like operations that is as robust as, or even more robust than, Transformers.
Github: https://github.com/ucsc-vlaa/robustcnn
Paper: https://arxiv.org/abs/2206.03452v1
Dataset: https://paperswithcode.com/dataset/imagenet-r
@ai_machinelearning_big_data
CNN architectures without any attention-like operations that is as robust as, or even more robust than, Transformers.
Github: https://github.com/ucsc-vlaa/robustcnn
Paper: https://arxiv.org/abs/2206.03452v1
Dataset: https://paperswithcode.com/dataset/imagenet-r
@ai_machinelearning_big_data
👍28🔥1
@itchannels_telegram - data science, machine learning useful channels
👍6