We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view, while the latter networks can capture sharper object boundaries by gradually recovering the spatial information. In this work, we propose to combine the advantages from both methods. Specifically, our proposed model, DeepLabv3+, extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries. We further explore the Xception model and apply the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network. We demonstrate the effectiveness of the proposed model on PASCAL VOC 2012 and Cityscapes datasets, achieving the test set performance of 89% and 82.1% without any post-processing. Our paper is accompanied with a publicly available reference implementation of the proposed models in Tensorflow at https://github.com/tensorflow/models/tree/master/research/deeplab.

/pdf/encoder-decoder-with-atrous-separable-convolution-for-u2eqbwevbb.pdf

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

There are a huge number of features which are said to improve Convolutional Neural Network (CNN) accuracy. Practical testing of combinations of such features on large datasets, and theoretical justification of the result, is required. Some features operate on certain models exclusively and for certain problems exclusively, or only for small-scale datasets; while some features, such as batch-normalization and residual-connections, are applicable to the majority of models, tasks, and datasets. We assume that such universal features include Weighted-Residual-Connections (WRC), Cross-Stage-Partial-connections (CSP), Cross mini-Batch Normalization (CmBN), Self-adversarial-training (SAT) and Mish-activation. We use new features: WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, CmBN, DropBlock regularization, and CIoU loss, and combine some of them to achieve state-of-the-art results: 43.5% AP (65.7% AP50) for the MS COCO dataset at a realtime speed of ~65 FPS on Tesla V100. Source code is at this https URL

YOLOv4: Optimal Speed and Accuracy of Object Detection

In this work, we revisit atrous convolution, a powerful tool to explicitly adjust filter's field-of-view as well as control the resolution of feature responses computed by Deep Convolutional Neural Networks, in the application of semantic image segmentation. To handle the problem of segmenting objects at multiple scales, we design modules which employ atrous convolution in cascade or in parallel to capture multi-scale context by adopting multiple atrous rates. Furthermore, we propose to augment our previously proposed Atrous Spatial Pyramid Pooling module, which probes convolutional features at multiple scales, with image-level features encoding global context and further boost performance. We also elaborate on implementation details and share our experience on training our system. The proposed `DeepLabv3' system significantly improves over our previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 semantic image segmentation benchmark.

Rethinking Atrous Convolution for Semantic Image Segmentation

Machine learning with maximization (support) of separating margin (vector), called support vector machine (SVM) learning, is a powerful classification tool that has been used for cancer genomic classification or subtyping. Today, as advancements in high-throughput technologies lead to production of large amounts of genomic and epigenomic data, the classification feature of SVMs is expanding its use in cancer genomics, leading to the discovery of new biomarkers, new drug targets, and a better understanding of cancer driver genes. Herein we reviewed the recent progress of SVMs in cancer genomic studies. We intend to comprehend the strength of the SVM learning and its future perspective in cancer genomic applications.

Applications of Support Vector Machine (SVM) Learning in Cancer Genomics.

We consider the problem of learning deep neural networks (DNNs) for object category segmentation, where the goal is to label each pixel in an image as being part of a given object (foreground) or not (background). Deep neural networks are usually trained with simple loss functions (e.g., softmax loss). These loss functions are appropriate for standard classification problems where the performance is measured by the overall classification accuracy. For object category segmentation, the two classes (foreground and background) are very imbalanced. The intersection-over-union (IoU) is usually used to measure the performance of any object category segmentation method. In this paper, we propose an approach for directly optimizing this IoU measure in deep neural networks. Our experimental results on two object category segmentation datasets demonstrate that our approach outperforms DNNs trained with standard softmax loss.

Optimizing Intersection-Over-Union in Deep Neural Networks for Image Segmentation

We propose two new models for human action recognition from video sequences using topic models. Video sequences are represented by a novel "bag-of-words" representation, where each frame corresponds to a "word". Our models differ from previous latent topic models for visual recognition in two major aspects: first of all, the latent topics in our models directly correspond to class labels; second, some of the latent variables in previous topic models become observed in our case. Our models have several advantages over other latent topic models used in visual recognition. First of all, the training is much easier due to the decoupling of the model parameters. Second, it alleviates the issue of how to choose the appropriate number of latent topics. Third, it achieves much better performance by utilizing the information provided by the class labels in the training set. We present action classification results on five different data sets. Our results are either comparable to, or significantly better than previously published results on these data sets.

Human Action Recognition by Semilatent Topic Models

In this paper, we go beyond recognizing the actions of individuals and focus on group activities. This is motivated from the observation that human actions are rarely performed in isolation; the contextual information of what other people in the scene are doing provides a useful cue for understanding high-level activities. We propose a novel framework for recognizing group activities which jointly captures the group activity, the individual person actions, and the interactions among them. Two types of contextual information, group-person interaction and person-person interaction, are explored in a latent variable framework. In particular, we propose three different approaches to model the person-person interaction. One approach is to explore the structures of person-person interaction. Differently from most of the previous latent structured models, which assume a predefined structure for the hidden layer, e.g., a tree structure, we treat the structure of the hidden layer as a latent variable and implicitly infer it during learning and inference. The second approach explores person-person interaction in the feature level. We introduce a new feature representation called the action context (AC) descriptor. The AC descriptor encodes information about not only the action of an individual person in the video, but also the behavior of other people nearby. The third approach combines the above two. Our experimental results demonstrate the benefit of using contextual information for disambiguating group activities.

Discriminative Latent Models for Recognizing Contextual Group Activities

We consider the problem of referring image segmentation. Given an input image and a natural language expression, the goal is to segment the object referred by the language expression in the image. Existing works in this area treat the language expression and the input image separately in their representations. They do not sufficiently capture long-range correlations between these two modalities. In this paper, we propose a cross-modal self-attention (CMSA) module that effectively captures the long-range dependencies between linguistic and visual features. Our model can adaptively focus on informative words in the referring expression and important regions in the input image. In addition, we propose a gated multi-level fusion module to selectively integrate self-attentive cross-modal features corresponding to different levels in the image. This module controls the information flow of features at different levels. We validate the proposed approach on four evaluation datasets. Our proposed approach consistently outperforms existing state-of-the-art methods.

/pdf/cross-modal-self-attention-network-for-referring-image-16bjt7qz3n.pdf

Yang Wang

Papers

Applications of Support Vector Machine (SVM) Learning in Cancer Genomics.

Optimizing Intersection-Over-Union in Deep Neural Networks for Image Segmentation

Human Action Recognition by Semilatent Topic Models

Discriminative Latent Models for Recognizing Contextual Group Activities

Cross-Modal Self-Attention Network for Referring Image Segmentation