Full camouflage fixation training dataset is available!
The full camouflage fixation training dataset is available with the full fixation maps for the COD10K training dataset, which can be downloaded from: https://drive.google.com/file/d/1inb5iNTDswFPDm4SpzBbVgZdI4puAv_3/view?usp=sharing
Github: https://github.com/JingZhang617/COD-Rank-Localize-and-Segment
Paper: https://arxiv.org/abs/2205.11333v1
Dataset: https://paperswithcode.com/dataset/salicon
@ArtificialIntelligencedl
The full camouflage fixation training dataset is available with the full fixation maps for the COD10K training dataset, which can be downloaded from: https://drive.google.com/file/d/1inb5iNTDswFPDm4SpzBbVgZdI4puAv_3/view?usp=sharing
Github: https://github.com/JingZhang617/COD-Rank-Localize-and-Segment
Paper: https://arxiv.org/abs/2205.11333v1
Dataset: https://paperswithcode.com/dataset/salicon
@ArtificialIntelligencedl
π3
ASSET: Autoregressive Semantic Scene Editing with Transformers at High Resolutions
Github: https://github.com/difanliu/asset
Paper: https://arxiv.org/abs/2205.12231v1
Dataset: https://paperswithcode.com/dataset/ade20k
Pretrained model: https://www.dropbox.com/s/5kyov71ko340ra0/landscape.zip?dl=0
@ArtificialIntelligencedl
Github: https://github.com/difanliu/asset
Paper: https://arxiv.org/abs/2205.12231v1
Dataset: https://paperswithcode.com/dataset/ade20k
Pretrained model: https://www.dropbox.com/s/5kyov71ko340ra0/landscape.zip?dl=0
@ArtificialIntelligencedl
π4
Recipe for a General, Powerful, Scalable Graph Transformer
Github: https://github.com/rampasek/GraphGPS
Paper: https://arxiv.org/abs/2205.12454v1
Dataset: https://paperswithcode.com/dataset/malnet
@ArtificialIntelligencedl
Github: https://github.com/rampasek/GraphGPS
Paper: https://arxiv.org/abs/2205.12454v1
Dataset: https://paperswithcode.com/dataset/malnet
@ArtificialIntelligencedl
π₯3
On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition
Github: https://github.com/KingJamesSong/DifferentiableSVD
Paper: https://arxiv.org/abs/2205.13282v1
Dataset: https://paperswithcode.com/dataset/imagenet
@ArtificialIntelligencedl
Github: https://github.com/KingJamesSong/DifferentiableSVD
Paper: https://arxiv.org/abs/2205.13282v1
Dataset: https://paperswithcode.com/dataset/imagenet
@ArtificialIntelligencedl
π6
SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation
Github: https://github.com/wangzy22/SemAffiNet
Paper: https://arxiv.org/abs/2205.13490v1
Dataset: https://paperswithcode.com/dataset/cityscapes
@ArtificialIntelligencedl
Github: https://github.com/wangzy22/SemAffiNet
Paper: https://arxiv.org/abs/2205.13490v1
Dataset: https://paperswithcode.com/dataset/cityscapes
@ArtificialIntelligencedl
β€3π1
This media is not supported in your browser
VIEW IN TELEGRAM
CMA-ES with Margin
CMA-ES with Margin (CMA-ESwM) [1] is a CMA-ES variant proposed for mixed-integer black-box optimization, which introduces a lower bound on the marginal probability associated with integer variables.
Github: https://github.com/evoconjp/cma-es_with_margin
Paper: https://arxiv.org/abs/2205.13482v1
@ArtificialIntelligencedl
CMA-ES with Margin (CMA-ESwM) [1] is a CMA-ES variant proposed for mixed-integer black-box optimization, which introduces a lower bound on the marginal probability associated with integer variables.
Github: https://github.com/evoconjp/cma-es_with_margin
Paper: https://arxiv.org/abs/2205.13482v1
@ArtificialIntelligencedl
π5
π» BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework
Github: https://github.com/adlab-autodrive/bevfusion
Paper: https://arxiv.org/abs/2205.13790v1
Dataset: https://paperswithcode.com/dataset/kitti
@ArtificialIntelligencedl
Github: https://github.com/adlab-autodrive/bevfusion
Paper: https://arxiv.org/abs/2205.13790v1
Dataset: https://paperswithcode.com/dataset/kitti
@ArtificialIntelligencedl
π5
Surface Vision Transformers
Github: https://github.com/metrics-lab/surface-vision-transformers
Paper: https://arxiv.org/abs/2205.15836v1
@ArtificialIntelligencedl
Github: https://github.com/metrics-lab/surface-vision-transformers
Paper: https://arxiv.org/abs/2205.15836v1
@ArtificialIntelligencedl
β€4
Good Intentions: Adaptive Parameter Servers via Intent Signaling
AdaPS is efficient for many machine learning tasks out of the box because it automatically adapts to the underlying task
Github: https://github.com/alexrenz/adaps
Paper: https://arxiv.org/abs/2206.00470v1
Docs: https://github.com/alexrenz/AdaPS/blob/vldb20/docs/experiments-vldb20.md
@ArtificialIntelligencedl
AdaPS is efficient for many machine learning tasks out of the box because it automatically adapts to the underlying task
Github: https://github.com/alexrenz/adaps
Paper: https://arxiv.org/abs/2206.00470v1
Docs: https://github.com/alexrenz/AdaPS/blob/vldb20/docs/experiments-vldb20.md
@ArtificialIntelligencedl
π6
π PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation
Github: https://github.com/naiyugao/panopticdepth
Paper: https://arxiv.org/abs/2206.00468
Dataset: https://paperswithcode.com/dataset/cityscapes
@ArtificialIntelligencedl
Github: https://github.com/naiyugao/panopticdepth
Paper: https://arxiv.org/abs/2206.00468
Dataset: https://paperswithcode.com/dataset/cityscapes
@ArtificialIntelligencedl
π5
β© XBound-Former: Toward Cross-scale Boundary Modeling in Transformers
Github: https://github.com/naiyugao/panopticdepth
Paper: https://arxiv.org/abs/2206.00806v1
Dataset: https://paperswithcode.com/dataset/kvasir-seg
@ArtificialIntelligencedl
Github: https://github.com/naiyugao/panopticdepth
Paper: https://arxiv.org/abs/2206.00806v1
Dataset: https://paperswithcode.com/dataset/kvasir-seg
@ArtificialIntelligencedl
π6
Invertible Neural Networks for Graph Prediction
Github: https://github.com/hamrel-cxu/invertible-graph-neural-network-ignn
Paper: https://arxiv.org/abs/2206.01163v1
@ArtificialIntelligencedl
Github: https://github.com/hamrel-cxu/invertible-graph-neural-network-ignn
Paper: https://arxiv.org/abs/2206.01163v1
@ArtificialIntelligencedl
π4β€1
SNAKE: Shape-aware Neural 3D Keypoint Field
Github: https://github.com/zhongcl-thu/snake
Paper: https://paperswithcode.com/dataset/modelnet
@ArtificialIntelligencedl
Github: https://github.com/zhongcl-thu/snake
Paper: https://paperswithcode.com/dataset/modelnet
@ArtificialIntelligencedl
β€4
Forwarded from Python/ django
πA Python library for audio feature extraction, classification, segmentation and applications.
Code: PyAudioAnalysis
#Python #Audio #Analyzer
@pythonl
Code: PyAudioAnalysis
#Python #Audio #Analyzer
@pythonl
π5β€1
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/
@ArtificialIntelligencedl
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/
@ArtificialIntelligencedl
π6
Tutel: Adaptive Mixture-of-Experts at Scale
Tutel, a highly scalable stack design and implementation for MoE with dynamically adaptive parallelism and pipelining.
Github: https://github.com/microsoft/tutel
Examples: https://github.com/microsoft/tutel/blob/main/tutel/examples
Paper: https://paperswithcode.com/dataset/coco
Documentation: https://ontomerger.readthedocs.io/
@ArtificialIntelligencedl
Tutel, a highly scalable stack design and implementation for MoE with dynamically adaptive parallelism and pipelining.
Github: https://github.com/microsoft/tutel
Examples: https://github.com/microsoft/tutel/blob/main/tutel/examples
Paper: https://paperswithcode.com/dataset/coco
Documentation: https://ontomerger.readthedocs.io/
@ArtificialIntelligencedl
π6
π Sparse Fusion Mixture-of-Experts are Domain Generalizable Learners
Sparse Fusion Mixture-of-Experts (SF-MoE), which incorporates sparsity and fusion mechanisms into the MoE framework to keep the model both sparse and predictive.
Github: https://github.com/luodian/sf-moe-dg
Paper: https://arxiv.org/abs/2206.04046v1
Documentation: https://paperswithcode.com/dataset/domainnet
@ArtificialIntelligencedl
Sparse Fusion Mixture-of-Experts (SF-MoE), which incorporates sparsity and fusion mechanisms into the MoE framework to keep the model both sparse and predictive.
Github: https://github.com/luodian/sf-moe-dg
Paper: https://arxiv.org/abs/2206.04046v1
Documentation: https://paperswithcode.com/dataset/domainnet
@ArtificialIntelligencedl
π4
πΉ PointNeXt & OpenPoints Library
improved training and model scaling strategies to boost PointNet++ to the state-of-the-art level.
Github: https://github.com/guochengqian/pointnext
Paper: https://paperswithcode.com/dataset/shapenet
@ArtificialIntelligencedl
improved training and model scaling strategies to boost PointNet++ to the state-of-the-art level.
Github: https://github.com/guochengqian/pointnext
Paper: https://paperswithcode.com/dataset/shapenet
@ArtificialIntelligencedl
π5
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Github: https://github.com/google/BIG-bench
Paper: https://arxiv.org/abs/2206.04615v1
Dataset: https://paperswithcode.com/dataset/glue
@ArtificialIntelligencedl
Github: https://github.com/google/BIG-bench
Paper: https://arxiv.org/abs/2206.04615v1
Dataset: https://paperswithcode.com/dataset/glue
@ArtificialIntelligencedl
β€8