XuejingLei

Dr. Sachin Chachada, a former MCL alumnus, and Professor C.-C. Jay Kuo received the 2019 Sadaoki Furui Paper Award at the open ceremony of the 2019 APSIPA ASC held in Lanzhou, China, on November 19 for their paper below:
Sachin Chachada and C.-C. Jay Kuo, “Environmental sound recognition: a survey,” Published online: 15 December 2014, e14, APSIPA Trans. on Signal and Information Processing.
The paper has been cited by 107 in Google Scholar, the number of downloads in 2019 (to end of Sept.) is 1523. The abstract of the paper is given below.
Although research in audio recognition has traditionally focused on speech and music signals, the problem of environmental sound recognition (ESR) has received more attention in recent years. Research on ESR has significantly increased in the past decade. Recent work has focused on the appraisal of non-stationary aspects of environmental sounds, and several new features predicated on non-stationary characteristics have been proposed. These features strive to maximize their information content pertaining to signal’s temporal and spectral characteristics. Furthermore, sequential learning methods have been used to capture the long-term variation of environmental sounds. In this survey, we will offer a qualitative and elucidatory survey on recent developments. It includes four parts: (i) basic environmental sound-processing schemes, (ii) stationary ESR techniques, (iii) non-stationary ESR techniques, and (iv) performance comparison of selected methods. Finally, concluding remarks and future research and development trends in the ESR field will be given.

Recently, Professor Kuo and his students at MCL proposed a new machine learning methodology called successive subspace learning (SSL). The methodology has been widely adopted in MCL to solve image processing and computer vision problems. In 3D domain, we have observed a great success in point cloud classification task. In the PointHop paper, we develop an explainable machine learning method for point cloud classification. The classification baseline is composed by four PointHop units, we construct the local-to-global attribute building process and use saab transform to control the dimension growth in each unit. We compare the test performance on ModelNet40 with the state-of-the-art methods, our method obtains comparable performance with the others while demands much less training time. For instance, PointNet costs about 5 hours to train, while ours only takes 20 minutes to train on the same dataset. The advantages of the methodology are very clear: interpretable and much less computation complexity.

The success in point cloud classification encourages us to go deeper in 3D domain. Therefore, we further look at the segmentation task which needs to assign label to each point in the point cloud. Referring to the common image segmentation network, we use the point cloud classification baseline as an encoder and add a decoder to complete segmentation. After building local neighboring regions and extracting local attributes from neighboring points in the encoder, the features are interpolated back to finest scale layer by layer with skip connections between same scales in the decoder. Also, saab transform is adopted between layers as feedfoward convolution to control the rapid growth of the feature dimension.

Our method also has the advantage of task-agnostic ability. Specifically, by learning the parameters in a one-pass manner, our [...]

We are so happy to welcome a new graduate member of MCL, Hongyu Fu. Here is an interview with Hongyu:

1. Could you briefly introduce yourself and your research interests?
My name is Hongyu Fu, before becoming a PhD student in USC, I got my bachelor’s degree in electrical engineering from Peking University. My past research experience focuses mostly on semiconductor device physics and circuits, while exploring device and circuit based neuromorphic computing and machine learning topics, I have heard more and more about computer vision, AI and machine learning, which are always my keen interest that I haven’t got chances to learn before. Therefore, I really appreciate Prof. Kuo for giving me this opportunity to study in MCL and explore more in this exciting area.
 
2. What is your impression about MCL and USC?
I really love the beautiful campus, friendly atmosphere and enjoy the convenient facilities of USC. We have a fight-on spirit as Trojans, which makes USC a great network and everyone in this network passionate and motivated. MCL is a large and efficient group with a hard-working spirit and intelligent students with solid skills and deep knowledge under the supervision of Prof. Kuo, who is a very nice and responsible advisor profound in knowledge and research.
 

3. What is your future expectation and plan in MCL?
I will definitely work hard, learn solid skills of math, problems solving and research and hope to contribute to MCL in the future. I wish that in the near future, the MCL group and myself would have a solid standing in the machine learning and computer vision community and contribute to the improvement of this field.

The thesis is entitled “Object Classification Based on Neural-Network-Inspired Image Transforms”.

Abstract of the thesis:

Convolutional neural networks (CNNs) have recently demonstrated impressive performance in image classification and change the way building feature extractors from carefully handcrafted design to automatically deep learned from a large labeled dataset. However, a great majority of current CNN literature are application-oriented, and there is no clear understanding and theoretical foundation to explain the outstanding performance and indicate the way to improve. In this thesis, we focus on solving the image classification problem-based on the neural-network-inspired transforms.

Being motivated by the multilayer RECOS (REctified-COrrelations on a Sphere) transform, two data-driven signal transforms are proposed, called the “Subspace approximation with augmented kernels” (Saak) transform and “Subspace approximation with adjusted bias” (Saab) transform corresponding to each Convolutional layers in CNNs. Based on the Saak transform, We firstly proposed an efficient, scalable and robust approach to the handwritten digits recognition problem. Next, we also develop an ensemble method using Saab transform to solve the image classification problem. The ensemble method fuses the output decision vectors of Saab-transform-based decision system. To enhance the performance of the ensemble system, it is critical to increasing the diversity of FF-CNN models. To achieve this objective, we introduce diversities by adopting three strategies: 1) different parameter settings in convolutional layers, 2) flexible feature subsets fed into the Fully-connected (FC) layers, and 3) multiple image embeddings of the same input source.  We also extend our ensemble method to semi-supervised learning. Since unlabeled data may not always enhance semi-supervised learning, we define an effective quality score and use it to select a subset of unlabeled data in the training process. In the last, we proposed a unified framework, called successive subspace learning [...]

Congratulations to Ron Salloum for passing his PhD defense on April 10, 2019. His PhD thesis is entitled “A Data-Driven Approach to Image Splicing Localization”.

Abstract:

The availability of low-cost and user-friendly editing software has made it significantly easier to manipulate images. Thus, there has been an increasing interest in developing forensic techniques to detect and localize image manipulations or forgeries. Splicing, which is one of the most common types of image forgery, involves copying a region from one image (referred to as the donor image) and pasting it onto another image (referred to as the host image). Forgers often use splicing to give a false impression that there is an additional object present in the image, or to remove an object from the image.

Many of the current splicing detection methods only determine whether a given image has been spliced and do not attempt to localize the spliced region. Relatively few methods attempt to tackle the splicing localization problem, which refers to the problem of determining which pixels in an image have been manipulated as a result of a splicing operation.

In my dissertation, I present two different splicing localization methods that we have developed. The first is the Multi-task Fully Convolutional Network (MFCN), which is a neural-network-based method that outperforms previous methods on many datasets. The second proposed method is based on cPCA++ (where cPCA stands for contrastive Principal Component Analysis), which is a new data visualization and clustering technique that we have developed. The cPCA++ method is more efficient than the MFCN and achieves comparable performance.

PhD Experience:

Pursuing my PhD degree was a very challenging but rewarding experience. I really enjoyed my time in the Media Communications Laboratory and had the opportunity to work on exciting research projects. [...]