SSD is a single-shot multi-box detector that detects objects in images using a single deep neural network. The approach discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location. At prediction time, the network generates scores for the presence of each object category in each default box and produces adjustments to the box to better match the object shape. Additionally, the network combines predictions from multiple feature maps with different resolutions to naturally handle objects of various sizes. SSD is simple relative to methods that require object proposals because it completely eliminates proposal generation and subsequent pixel or feature resampling stages and encapsulates all computation in a single network. This makes SSD easy to train and straightforward to integrate into systems that require a detection component. 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 training and inference. For 300×300 input, SSD achieves 74.3% mAP on VOC2007 test at 59 FPS on a Nvidia Titan X and for 512×512 input, SSD achieves 76.9% mAP, outperforming a comparable state of the art Faster R-CNN model. Compared to other single stage methods, SSD has much better accuracy even with a smaller input image size. Code is available at https://github.com/weiliu89/caffe/tree/ssd. Keywords: Real-time object detection · Convolutional neural network. The SSD framework uses multi-scale feature maps for detection and convolutional predictors for detection. Each added feature layer can produce a fixed set of detection predictions using a set of convolutional filters. Default boxes and aspect ratios are used to associate a set of default bounding boxes with each feature map cell. These design features lead to simple end-to-end training and high accuracy, even on low resolution input images, further improving the speed vs accuracy trade-off. Experiments include timing and accuracy analysis on models with varying input size evaluated on PASCAL VOC, COCO, and ILSVRC and are compared to a range of recent state-of-the-art approaches. The SSD approach is based on a feed-forward convolutional network that produces a fixed-size collection of bounding boxes and scores for the presence of object class instances in those boxes, followed by a non-maximum suppression step to produce the final detections. The early network layers are based on a standard architecture used for high quality image classification. We add auxiliary structure to the network to produce detections with the following key features: multi-scale feature maps for detection, convolutional predictors for detection, default boxes and aspect ratios. The key difference between training SSD and training a typical detector that uses region proposals is that ground truth information needs to be assigned to specific outputs in the fixed set of detector outputs. OnceSSD is a single-shot multi-box detector that detects objects in images using a single deep neural network. The approach discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location. At prediction time, the network generates scores for the presence of each object category in each default box and produces adjustments to the box to better match the object shape. Additionally, the network combines predictions from multiple feature maps with different resolutions to naturally handle objects of various sizes. SSD is simple relative to methods that require object proposals because it completely eliminates proposal generation and subsequent pixel or feature resampling stages and encapsulates all computation in a single network. This makes SSD easy to train and straightforward to integrate into systems that require a detection component. 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 training and inference. For 300×300 input, SSD achieves 74.3% mAP on VOC2007 test at 59 FPS on a Nvidia Titan X and for 512×512 input, SSD achieves 76.9% mAP, outperforming a comparable state of the art Faster R-CNN model. Compared to other single stage methods, SSD has much better accuracy even with a smaller input image size. Code is available at https://github.com/weiliu89/caffe/tree/ssd. Keywords: Real-time object detection · Convolutional neural network. The SSD framework uses multi-scale feature maps for detection and convolutional predictors for detection. Each added feature layer can produce a fixed set of detection predictions using a set of convolutional filters. Default boxes and aspect ratios are used to associate a set of default bounding boxes with each feature map cell. These design features lead to simple end-to-end training and high accuracy, even on low resolution input images, further improving the speed vs accuracy trade-off. Experiments include timing and accuracy analysis on models with varying input size evaluated on PASCAL VOC, COCO, and ILSVRC and are compared to a range of recent state-of-the-art approaches. The SSD approach is based on a feed-forward convolutional network that produces a fixed-size collection of bounding boxes and scores for the presence of object class instances in those boxes, followed by a non-maximum suppression step to produce the final detections. The early network layers are based on a standard architecture used for high quality image classification. We add auxiliary structure to the network to produce detections with the following key features: multi-scale feature maps for detection, convolutional predictors for detection, default boxes and aspect ratios. The key difference between training SSD and training a typical detector that uses region proposals is that ground truth information needs to be assigned to specific outputs in the fixed set of detector outputs. Once