Sunggyun Park

AttentionNet: Aggregating Weak Directions for Accurate Object Detection

We present a novel detection method using a deep convolutional neural network (CNN), named AttentionNet. We cast an object detection problem as an iterative classification problem, which is the most suitable form of a CNN. AttentionNet provides quantized weak directions pointing a target object and the ensemble of iterative predictions from AttentionNet converges to an accurate object boundary box. Since AttentionNet is a unified network for object detection, it detects objects without any separated models from the object proposal to the post bounding-box regression. We evaluate AttentionNet by a human detection task and achieve the state-of-the-art performance of 65% (AP) on PASCAL VOC 2007/2012 with an 8-layered architecture only.

Multi-scale pyramid pooling for deep convolutional representation

Compared to image representation based on low-level local descriptors, deep neural activations of Convolutional Neural Networks (CNNs) are richer in mid-level representation, but poorer in geometric invariance properties. In this paper, we present a straightforward framework for better image representation by combining the two approaches. To take advantages of both representations, we extract a fair amount of multi-scale dense local activations from a pre-trained CNN. We then aggregate the activations by Fisher kernel framework, which has been modified with a simple scale-wise normalization essential to make it suitable for CNN activations. Our representation demonstrates new state-of-the-art performances on three public datasets: 80.78% (Acc.) on MIT Indoor 67, 83.20% (mAP) on PASCAL VOC 2007 and 91.28% (Acc.) on Oxford 102 Flowers. The results suggest that our proposal can be used as a primary image representation for better performances in wide visual recognition tasks.

Pixel-Level Domain Transfer

We present an image-conditional image generation model. The model transfers an input domain to a target domain in semantic level, and generates the target image in pixel level. To generate realistic target images, we employ the real/fake-discriminator as in Generative Adversarial Nets, but also introduce a novel domain-discriminator to make the generated image relevant to the input image. We verify our model through a challenging task of generating a piece of clothing from an input image of a dressed person. We present a high quality clothing dataset containing the two domains, and succeed in demonstrating decent results.

Verification of NC tool path and manual and automatic editing of NC code

We describe the method of verification and manual and automatic editing of the NC code. A new method was proposed to find out the errors quickly and to edit the errors easily. Both wireframe display of tool path and solid display of machined part are used to detect the motion command errors and auxiliary command errors in NC code. The Z-map method was used for the shaded image display and the comparing the CAD data and CAM data. Using the verification result, the NC program was edited manually without returning to the programming stage. In addition, an automatic editing was proposed to overcome the limit of manual editing. The method was implemented as a software in an IBM/PC with the MS-Windows.

A Unified Framework for Tumor Proliferation Score Prediction in Breast Histopathology

We present a unified framework to predict tumor proliferation scores from breast histopathology whole slide images. Our system offers a fully automated solution to predicting both a molecular data-based, and a mitosis counting-based tumor proliferation score. The framework integrates three modules, each fine-tuned to maximize the overall performance: An image processing component for handling whole slide images, a deep learning based mitosis detection network, and a proliferation scores prediction module. We have achieved 0.567 quadratic weighted Cohen’s kappa in mitosis counting-based score prediction and 0.652 F1-score in mitosis detection. On Spearman’s correlation coefficient, which evaluates predictive accuracy on the molecular data based score, the system obtained 0.6171. Our approach won first place in all of the three tasks in Tumor Proliferation Assessment Challenge 2016 which is MICCAI grand challenge.

Dynamic pricing with ‘BOGO’ promotion in revenue management

We consider a dynamic pricing problem when a seller, facing uncertain demands, sells a single product in a finite horizon. The seller actively adopts dynamic pricing and quantity discount schemes. The proposed model is based on the assumption that each customer has random reservation prices and the purchase size depends on the posted price and discount. We particularly focus on the widely adopted promotional schemes ‘buy one get one free’ and ‘50% off’ and study the optimal strategic choices of the seller. Analytical results together with numerical experiments are presented to help us obtain managerial insights. Additional numerical results for a generalised model are provided so as to examine the effectiveness of promotional schemes.

Accurate Lung Segmentation via Network-Wise Training of Convolutional Networks

We introduce an accurate lung segmentation model for chest radiographs based on deep convolutional neural networks. Our model is based on atrous convolutional layers to increase the field-of-view of filters efficiently. To improve segmentation performances further, we also propose a multi-stage training strategy, network-wise training, which the current stage network is fed with both input images and the outputs from pre-stage network. It is shown that this strategy has an ability to reduce falsely predicted labels and produce smooth boundaries of lung fields. We evaluate the proposed model on a common benchmark dataset, JSRT, and achieve the state-of-the-art segmentation performances with much fewer model parameters.

PRISM: a system for weighted multi-color browsing of fashion products

Multiple color search technology helps users find fashion products in a more intuitive manner. Although fashion product images can be represented not only by a set of dominant colors but also by the relative ratio of colors, current online fashion shopping malls often provide rather simple color filters. In this demo, we present PRISM (Perceptual Representation of Image SiMilarity), a weighted multi-color browsing system for fashion products retrieval. Our system combines widely accepted backend web service stacks and various computer vision techniques including a product area parsing and a compact yet effective multi-color description. Finally, we demonstrate the benefits of PRISM system via web service in which users freely browse fashion products.