Compared to previous work, Fast R-CNN employs several innovations to improve training and testing speed while also increasing detection accuracy. Ross Girshick, "Fast R-CNN" https://arxiv.org/abs/1504.08083 物体検出タスクにおいて、特徴マッ…

The third contribution is a method for combining increasingly more complex classifiers in a “cascade” which allows background regions of the image to be quickly discarded while spending more computation on promising object-like regions. Pa…

This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance. David G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints" https://www.cs.ubc.ca/~lowe/paper…

Large networks are also slow to use, making it difficult to deal with overfitting by combining the predictions of many different large neural nets at test time. Nitish Srivastava, et al., "Dropout: A Simple Way to Prevent Neural Networks f…

How can we perform efficient inference and learning in directed probabilistic models, in the presence of continuous latent variables with intractable posterior distributions, and large datasets? Diederik P Kingma, et al., "Auto-Encoding Va…

This explanation is supported by new quantitative results while giving the first explanation of the most intriguing fact about them: their generalization across architectures and training sets. Ian J. Goodfellow, "Explaining and Harnessing…

Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Ashish Vaswani, et al., "Attention Is All You Need" https://arxiv.org/…

Building on a recently proposed method called Grad-CAM, we propose a generalized method called Grad-CAM++ that can provide better visual explanations of CNN model predictions, in terms of better object localization as well as explaining oc…

The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameter…

Experimental results on the PASCAL VOC, COCO, and ILSVRC datasets confirm that SSD has competitive accuracy to methods that utilize an additional object proposal step and is much faster, while providing a unified framework for both trainin…

This makes SSD easy to train and straightforward to integrate into systems that require a detection component. Wei Liu, et al., "SSD: Single Shot MultiBox Detector" https://arxiv.org/abs/1512.02325 物体検出タスクにおいて、YOLOよりも高速で…

It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork. Joseph Redmon, et al., "You Only Look Once: Unified, Real-Time Object Detection" https://arxiv.org/abs/15…

A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Joseph Redmon, et al., "You Only Look Once: Unified, Real-Time Object Detection" …

For the very deep VGG-16 model, our detection system has a frame rate of 5fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007, 2012, and MS COCO datasets with only 300 proposals…

We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features—using the recently popular terminology of neural networks with “attention” mechanisms, the RPN component tells the unified network where to l…

This was achieved by a carefully crafted design that allows for increasing the depth and width of the network while keeping the computational budget constant. Christian Szegedy, et al., "Going Deeper with Convolutions" https://arxiv.org/ab…

The depth of representations is of central importance for many visual recognition tasks. Kaiming He, et al., "Deep Residual Learning for Image Recognition" https://arxiv.org/abs/1512.03385 2015年のILSVRCで1位になったディープラーニングモデ…

We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. Kaiming He, et al., "Deep Residual Learning for Image Recognition" https://ar…

Deeper neural networks are more difficult to train. Kaiming He, et al., "Deep Residual Learning for Image Recognition" https://arxiv.org/abs/1512.03385 2015年のILSVRCで1位になったディープラーニングモデルであるResNetの論文の"Deep Residual L…