Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.

/pdf/rich-feature-hierarchies-for-accurate-object-detection-and-22fvjlggyg.pdf

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

抗原变异可使得多种致病微生物易于逃避宿主免疫应答。表达在感染红细胞表面的恶性疟原虫红细胞表面蛋白1（PfPMP1）与感染红细胞、内皮细胞、树突状细胞以及胎盘的单个或多个受体作用，在黏附及免疫逃避中起关键的作用。每个单倍体基因组var基因家族编码约60种成员，通过启动转录不同的var基因变异体为抗原变异提供了分子基础。

疟原虫var基因转换速率变化导致抗原变异[英]／Paul H, Robert P, Christodoulou Z, et al//Proc Natl Acad Sci U S A

Presents a theoretically very simple, yet efficient, multiresolution approach to gray-scale and rotation invariant texture classification based on local binary patterns and nonparametric discrimination of sample and prototype distributions. The method is based on recognizing that certain local binary patterns, termed "uniform," are fundamental properties of local image texture and their occurrence histogram is proven to be a very powerful texture feature. We derive a generalized gray-scale and rotation invariant operator presentation that allows for detecting the "uniform" patterns for any quantization of the angular space and for any spatial resolution and presents a method for combining multiple operators for multiresolution analysis. The proposed approach is very robust in terms of gray-scale variations since the operator is, by definition, invariant against any monotonic transformation of the gray scale. Another advantage is computational simplicity as the operator can be realized with a few operations in a small neighborhood and a lookup table. Experimental results demonstrate that good discrimination can be achieved with the occurrence statistics of simple rotation invariant local binary patterns.

/pdf/multiresolution-gray-scale-and-rotation-invariant-texture-1b1y2fta4g.pdf

Multiresolution gray-scale and rotation invariant texture classification with local binary patterns

Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012---achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also compare R-CNN to OverFeat, a recently proposed sliding-window detector based on a similar CNN architecture. We find that R-CNN outperforms OverFeat by a large margin on the 200-class ILSVRC2013 detection dataset. Source code for the complete system is available at this http URL.

Rich feature hierarchies for accurate object detection and semantic segmentation

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

With the rapid growth of image and video data on the web, hashing has been extensively studied for image or video search in recent years. Benefiting from recent advances in deep learning, deep hashing methods have shown superior performance over the traditional hashing methods. However, there are some limitations of previous deep hashing methods (e.g., the semantic information is not fully exploited). In this paper, we develop a general deep supervised discrete hashing framework based on the assumption that the learned binary codes should be ideal for classification. Both the similarity information and the classification information are used to learn the hash codes within one stream framework. We constrain the outputs of the last layer to be binary codes directly, which is rarely investigated in deep hashing algorithms. Besides, both the pairwise similarity information and the triplet ranking information are exploited in this paper. In addition, two different loss functions are presented: 
$${l_2}$$

 loss and hinge loss, which are carefully designed for the classification term under the one stream framework. Because of the discrete nature of hash codes, an alternating minimization method is used to optimize the objective function. Experimental results have shown that our approach outperforms current state-of-the-art methods on benchmark datasets.

A General Framework for Deep Supervised Discrete Hashing

Iris texture is commonly thought to be highly discriminative between eyes and stable over individual lifetime, which makes iris particularly suitable for personal identification. However, iris texture also contains more information related to genes, which has been demonstrated by successful use of ethnic and gender classification based on iris. In this paper, we propose a novel ethnic classification method based on supervised codebook optimizing and Locality-constrained Linear Coding (LLC). The optimized codebook is composed of codes which are distinctive or mutual. Iris images from Asian and non-Asian are classified into two classes in experiments. Extensive experimental results show that the proposed method achieves encouraging classification rate and largely improves the ethnic classification performance comparing to existing algorithms.

/pdf/ethnic-classification-based-on-iris-images-1e17dm7bfc.pdf

Ethnic classification based on iris images

Mixture models are frequently used to fit skin color distributions in various color spaces. However, the high computational cost of the conventional EM algorithm makes it intractable for large data sets. We propose a novel algorithm for estimating the parameters of mixture models. Multidimensional histograms are incorporated into the EM framework to group neighboring datapoints and reduce the size of the data set. We adopt this method to build Gaussian mixture models of skin color and compare the performance of models with different number of components. Further experiments on synthetic data show the efficiency of our method as a general approach to data clustering.

Mixture clustering using multidimensional histograms for skin detection

Face aging, which aims at aesthetically rendering a given face to predict its future appearance, has received significant research attention in recent years. Although great progress has been achieved with the success of Generative Adversarial Networks (GANs) in synthesizing realistic images, most existing GAN-based face aging methods have two main problems: 1) unnatural changes of high-level semantic information (e.g. facial attributes) due to the insufficient utilization of prior knowledge of input faces, and 2) distortions of low-level image content including ghosting artifacts and modifications in age-irrelevant regions. In this paper, we introduce A3GAN, an Attribute-Aware Attentive face aging model to address the above issues. Facial attribute vectors are regarded as the conditional information and embedded into both the generator and discriminator, encouraging synthesized faces to be faithful to attributes of corresponding inputs. To improve the visual fidelity of generation results, we leverage the attention mechanism to restrict modifications to age-related areas and preserve image details. Moreover, the wavelet packet transform is employed to capture textural features at multiple scales in the frequency space. Extensive experimental results demonstrate the effectiveness of our model in synthesizing photorealistic aged face images and achieving state-of-the-art performance on popular face aging datasets.

A3GAN: An Attribute-aware Attentive Generative Adversarial Network for Face Aging.

Recognizing objectionable content draws more and more attention nowadays given the rapid proliferation of images and videos on the Internet. Although there are some investigations about violence video detection and pornographic information filtering, very few existing methods touch on the problem of violence detection in still images. However, given its potential use in violence webpage filtering, online public opinion monitoring and some other aspects, recognizing violence in still images is worth being deeply investigated. To this end, we first establish a new database containing 500 violence images and 1500 non-violence images. And we use the Bag-of-Words (BoW) model which is frequently adopted in image classification domain to discriminate violence images and non-violence images. The effectiveness of four different feature representations are tested within the BoW framework. Finally the baseline results for violence image detection on our newly built database are reported.

/pdf/baseline-results-for-violence-detection-in-still-images-5ddu9ek7pk.pdf

Tieniu Tan

Papers

A General Framework for Deep Supervised Discrete Hashing

Ethnic classification based on iris images

Mixture clustering using multidimensional histograms for skin detection

A3GAN: An Attribute-aware Attentive Generative Adversarial Network for Face Aging.

Baseline Results for Violence Detection in Still Images