We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. 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. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.

/pdf/you-only-look-once-unified-real-time-object-detection-3gan6roe1o.pdf

You Only Look Once: Unified, Real-Time Object Detection

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Visual tracking, in essence, deals with non-stationary image streams that change over time. While most existing algorithms are able to track objects well in controlled environments, they usually fail in the presence of significant variation of the object's appearance or surrounding illumination. One reason for such failures is that many algorithms employ fixed appearance models of the target. Such models are trained using only appearance data available before tracking begins, which in practice limits the range of appearances that are modeled, and ignores the large volume of information (such as shape changes or specific lighting conditions) that becomes available during tracking. In this paper, we present a tracking method that incrementally learns a low-dimensional subspace representation, efficiently adapting online to changes in the appearance of the target. The model update, based on incremental algorithms for principal component analysis, includes two important features: a method for correctly updating the sample mean, and a forgetting factor to ensure less modeling power is expended fitting older observations. Both of these features contribute measurably to improving overall tracking performance. Numerous experiments demonstrate the effectiveness of the proposed tracking algorithm in indoor and outdoor environments where the target objects undergo large changes in pose, scale, and illumination.

/pdf/incremental-learning-for-robust-visual-tracking-4wjxuilyhr.pdf

Incremental Learning for Robust Visual Tracking

The PASCAL Visual Object Classes Challenge

Describes an automated method to locate and outline blood vessels in images of the ocular fundus. Such a tool should prove useful to eye care specialists for purposes of patient screening, treatment evaluation, and clinical study. The authors' method differs from previously known methods in that it uses local and global vessel features cooperatively to segment the vessel network. The authors evaluate their method using hand-labeled ground truth segmentations of 20 images. A plot of the operating characteristic shows that the authors' method reduces false positives by as much as 15 times over basic thresholding of a matched filter response (MFR), at up to a 75% true positive rate. For a baseline, they also compared the ground truth against a second hand-labeling, yielding a 90% true positive and a 4% false positive detection rate, on average. These numbers suggest there is still room for a 15% true positive rate improvement, with the same false positive rate, over the authors' method. They are making all their images and hand labelings publicly available for interested researchers to use in evaluating related methods.

/pdf/locating-blood-vessels-in-retinal-images-by-piecewise-4lgaualy1f.pdf

Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response

We present new deterministic methods that, given two eigenspace models-each representing a set of n-dimensional observations-will: 1) merge the models to yield a representation of the union of the sets and 2) split one model from another to represent the difference between the sets. As this is done, we accurately keep track of the mean. Here, we give a theoretical derivation of the methods, empirical results relating to the efficiency and accuracy of the techniques, and three general applications, including the construction of Gaussian mixture models that are dynamically updateable.

/pdf/merging-and-splitting-eigenspace-models-1zwbwnfuj7.pdf

Merging and splitting eigenspace models

Eigenspace models are a convenient way to represent sets of observations with widespread applications, including classification. In this paper we describe a new constructive method for incrementally adding observations to an eigenspace model. Our contribution is to explicitly account for a change in origin as well as a change in the number of eigenvectors needed in the basis set. No other method we have seen considers change of origin, yet both are needed if an eigenspace model is to be used for classification purposes. We empirically compare our incremental method with two alternatives from the literature and show our method is the more useful for classification because it computes the smaller eigenspace model representing the observations.

/pdf/incremental-eigenanalysis-for-classification-2sx0wgor3e.pdf

Incremental Eigenanalysis for Classification

https://dc.tsinghuajournals.com/cgi/viewcontent.cgi?article=1181&context=tsinghua-science-and-technology

A survey of image synthesis and editing with generative adversarial networks

The contribution of this paper is a novel framework for synthesizing nonphotorealistic animations from real video sequences. We demonstrate that, through automated mid-level analysis of the video sequence as a spatiotemporal volume - a block of frames with time as the third dimension - we are able to generate animations in a wide variety of artistic styles, exhibiting a uniquely high degree of temporal coherence. In addition to rotoscoping, matting, and novel temporal effects unique to our method, we demonstrate the extension of static nonphotorealistic rendering (NPR) styles to video, including painterly, sketchy, and cartoon shading. We demonstrate how this novel coherent shading framework may be combined with our earlier motion emphasis work to produce a comprehensive "video paintbox" capable of rendering complete cartoon-styled animations from video clips.

Stroke surfaces: temporally coherent artistic animations from video

Example-guided image synthesis aims to synthesize an image from a semantic label map and an exemplary image indicating style. We use the term "style" in this problem to refer to implicit characteristics of images, for example: in portraits "style" includes gender, racial identity, age, hairstyle; in full body pictures it includes clothing; in street scenes it refers to weather and time of day and such like. A semantic label map in these cases indicates facial expression, full body pose, or scene segmentation. We propose a solution to the example-guided image synthesis problem using conditional generative adversarial networks with style consistency. Our key contributions are (i) a novel style consistency discriminator to determine whether a pair of images are consistent in style; (ii) an adaptive semantic consistency loss; and (iii) a training data sampling strategy, for synthesizing style-consistent results to the exemplar. We demonstrate the efficiency of our method on face, dance and street view synthesis tasks.

/pdf/example-guided-style-consistent-image-synthesis-from-x45hcxo7st.pdf

Peter Hall

Papers

Merging and splitting eigenspace models

Incremental Eigenanalysis for Classification

A survey of image synthesis and editing with generative adversarial networks

Stroke surfaces: temporally coherent artistic animations from video

Example-Guided Style-Consistent Image Synthesis From Semantic Labeling