• Semantic3D.net

  • Referenced in 2 articles [sw36654]
  • presents a new 3D point cloud classification benchmark data set with over four billion manually ... data-hungry (deep) learning methods. We also discuss first submissions to the benchmark that ... many tasks in computer vision and machine learning like semantic segmentation or object detection...
  • HPatches

  • Referenced in 3 articles [sw31213]
  • this paper, we propose a novel benchmark for evaluating local image descriptors. We demonstrate that ... recent improvements in local descriptors obtained by learning them from large annotated datasets. Therefore ... level of deep learning based descriptors within a realistic benchmarks evaluation...
  • OpenLORIS

  • Referenced in 1 article [sw37994]
  • Robotic Vision Dataset and Benchmark for Lifelong Deep Learning. The recent breakthroughs in computer vision ... where lifelong learning is a fundamental capability. However, very few datasets and benchmarks are available...
  • ExKaldi-RT

  • Referenced in 1 article [sw38118]
  • acoustic model trained with deep learning frameworks. We performed benchmark experiments on the minimum LibriSpeech...
  • Chiron

  • Referenced in 1 article [sw32566]
  • evaluate Chiron on popular deep learning models, focusing on benchmark image classification tasks such...
  • subgraph2vec

  • Referenced in 4 articles [sw36496]
  • deep learning variant of Weisfeiler-Lehman graph kernel. Our experiments on several benchmark and large...
  • Cityscapes

  • Referenced in 7 articles [sw36624]
  • datasets, especially in the context of deep learning. For semantic urban scene understanding, however ... address this, we introduce Cityscapes, a benchmark suite and large-scale dataset to train...
  • DIG

  • Referenced in 1 article [sw37858]
  • operations for graph deep learning. In the research community, implementing and benchmarking various advanced tasks ... with existing libraries. To facilitate graph deep learning research, we introduce DIG: Dive into Graphs...
  • InteriorNet

  • Referenced in 1 article [sw36667]
  • training and evaluation of Deep Learning-based methods to benchmarking Simultaneous Localization and Mapping (SLAM...
  • Dopamine

  • Referenced in 6 articles [sw31151]
  • Deep Reinforcement Learning. Deep reinforcement learning (deep RL) research has grown significantly in recent years ... exist that provide stable, comprehensive implementations for benchmarking. At the same time, recent deep...
  • pLoc-mGneg

  • Referenced in 23 articles [sw25190]
  • Gram-negative bacterial proteins by deep gene ontology learning via general PseAAC. Information ... Rigorous cross-validation on a high quality benchmark dataset indicated that the proposed predictor...
  • Flappy

  • Referenced in 2 articles [sw38067]
  • learning control algorithms such as Reinforcement Learning. The interface of the simulation is fully compatible ... benchmark study, we present a linear controller for hovering stabilization and a Deep Reinforcement Learning...
  • NeuroVectorizer

  • Referenced in 1 article [sw32381]
  • instructions, dependencies, and data structures to enable learning a sophisticated model that can better predict ... that integrates deep RL in the LLVM compiler. Our proposed framework takes benchmark codes ... embedding generator that learns an embedding for these loops. Finally, the learned embeddings are used ... input to a Deep RL agent, which determines the vectorization factors for all the loops...
  • PartNet

  • Referenced in 1 article [sw31210]
  • instance segmentation. We benchmark four state-of-the-art 3D deep learning algorithms for fine...
  • MNN

  • Referenced in 1 article [sw37167]
  • Universal and Efficient Inference Engine. Deploying deep learning models on mobile devices draws more ... Extensive benchmark experiments demonstrate that MNN performs favorably against other popular lightweight deep learning frameworks...
  • MLaut

  • Referenced in 1 article [sw27171]
  • automates large-scale evaluation and benchmarking of machine learning algorithms on a large number ... hyper-parameter tuning, pipeline composition, or deep learning architecture. As a principal test case ... order to benchmark the performance of a number of machine learning algorithms - to our knowledge ... study on standard supervised learning data sets to include deep learning algorithms. While corroborating...
  • CNN-RNN

  • Referenced in 8 articles [sw28401]
  • Framework for Multi-label Image Classification. While deep convolutional neural networks (CNNs) have shown ... Traditional approaches to multi-label image classification learn independent classifiers for each category and employ ... with CNNs, the proposed CNN-RNN framework learns a joint image-label embedding to characterize ... unified framework. Experimental results on public benchmark datasets demonstrate that the proposed architecture achieves better...
  • SegNet

  • Referenced in 16 articles [sw27575]
  • segmentation. We present a novel and practical deep fully convolutional neural network architecture for semantic ... linear upsampling. This eliminates the need for learning to upsample. The upsampled maps are sparse ... competing architectures. We also performed a controlled benchmark of SegNet and other architectures on both...
  • RecBole

  • Referenced in 1 article [sw37574]
  • implement 53 recommendation models on 27 benchmark datasets, covering the categories of general recommendation, sequential ... most popular deep learning frameworks. Our library is featured in many aspects, including general ... extensible data structures, comprehensive benchmark models and datasets, efficient GPU-accelerated execution, and extensive...
  • MMFashion

  • Referenced in 1 article [sw33964]
  • deep learning era, with more functionalities to be added. This toolbox and the benchmark could...