News

Congratulations to MCL Director, Professor C.-C. Jay Kuo, for being selected as the recipient of the 2021 IEEE CASS Charles A. Desoer Technical Achievement Award. This award is named after  Charles A. Desoer, Professor of Electrical Engineering and Computer Science, Emeritus, at UC Berkeley. This award honors individuals whose exceptional technical contributions to a field within the scope of the Circuits and Systems Society have been consistently evident over a period of years. Contributions are documented by publications and based on originality and continuity of effort. Professor Kuo received this award for his contributions to visual communications and multimedia systems

The 2021 CAS Society Awards Ceremony will be held virtually in parallel with the ISCAS 2021 event on Monday, 24 May. The ceremony will be pre-recorded and presented on both the online platform and at the live banquet in Daegu. Here is Professor Kuo’s acceptance speech.

“It is my great honor to receive the 2021 IEEE CASS Charles A. Desoer Technical Achievement Award. I know that this is a highly competitive award, and there are many well qualified nominees each year. I would like to give my deepest appreciation to the Technical Achievement Award Sub-Committee and the CASS Board for their recognition.

I am also grateful for the excellent research environment provided by the University of Southern California. It is a privilege to supervise 160 hardworking PhD students at USC in the last 30 years. We brainstorm research ideas, share research frustration, and enjoy research breakthrough together. I can say that there is nothing more rewarding than working with a large number of talented young people.

I have been heavily involved in two CASS technical committees in my career. They are the visual signal processing and communication technical [...]

Block-based image coding is adopted by the JPEG standard, which has been widely used in the last three decades. The block-based discrete Cosine transform (DCT) and quantization matrices in YCbCr three color channels play key roles in JPEG. In this work, we propose a new image coding method, called DCST. It adopts data-driven colour transform and spatial transforms based on statistical properties of image pixels and machine learning. To match the data-driven forward transform, we propose a quantization table based on the human visual system (HVS). Furthermore, to efficiently compensate for the quantization error, a machine learning-based inverse transform is used. The performance of our new design is verified using the Kodak image dataset. The optimal inverse transformation can achieve 0.11-0.30dB over the standard JPEG over a wide range of quality factors. The whole pipeline outperforms JPEG with a gain of 0.5738 in the BD-PSNR (or a decrease of 9.5713 in the BD-rate) from 0.2 to 3bpp.

the colour input: previous standard use YCbCr as input which is ideal if viewed from statics while not optimal for every single image. In our case, we trained a PCA for every single image to perform color transformation which gives better de-correlate performance;
(2D)^2 PCA [1] transformation and corresponding quantization matrix designed based on the PCA kernel and HVS [2];
Machine learning inverse transform: which uses linear regression to compute the optimal inverse transform kernel for both color conversion and spatial to spectrum transform. This idea helps to estimate the quantization error and results from a better inverse result. Comparing with the previous method which compensates this error using probability mode during the post-processing stage. The ML-inverse transformation would take less time during the decoding [...]

Semantic segmentation can help people identify and locate objects, which provide important road information for upper-level navigational tasks. Due to the rapid development of deep Convolutional Neural Networks (CNNs)[1], the performance of image segmentation models has been greatly improved and CNNs is widely used for this task. However, maintaining the performance under different conditions is a non-trivial task. In the dark, rain, or fog environment, the quality of RGB images will be greatly reduced while other sensors may still get fair results. Thus, our model combines the information of RGB image and depth map. When driving, we often encounter obstacles, like the trash can, barrier, rubble, stones, and cargos. Recognizing and avoiding them is very crucial for safety. To address this problem, we apply multi-dataset learning. In this way, our model can learn more classes from other data sets, including obstacles.

In our experiment, we fully evaluate the RFNet[2] with different datasets and methods to combine them. Regarding the framework of our model, the inputs from different datasets will pass through the resizing module. Then, the depth map and RGB image are sent to the network. Ground truth will go to Relabeling module. Multi-dataset learning strategy is applied to Resizing, Relabeling and Modified Softmax layer. Finally, by comparing the results of relabeled ground truth and prediction, we can obtain the intersection of union(IoU) and value of cross-entropy loss.

Our result shows that our models have excellent performances in the urban environment and blended environment. However, in the field environment, the depth map helps the model very slightly. We also proposed a new thrifty relabeling, which can improve the performance of the model without increasing the complexity of the network. Moreover, more datasets can help the model [...]

Let us hear what she has to say about her defense and an abstract of her thesis.

Neural networks have been shown to be effective in many applications. To better explain the behaviors of the neural networks, we examine the properties of neural networks experimentally and analytically in this research.

In the first part, we conduct experiments on convolutional neural networks (CNNs) and observe the behaviors of the networks. We also propose some insight or conjectures for CNNs in this part. First, we demonstrate how the accuracy changes with the size of the convolutional layers. Second, we  develop a design to determine the size of the convolutional layers based on SSL. Third, as a case study, we analyze the SqueezeNet, which is able to achieve the same accuracy as AlexNet with 50x fewer parameters, by studying the evolution of cross-entropy values across layers and doing visualization. Fourth, we also propose some insight on  co-training based deep semi-supervised learning.

In the second part, we propose new angles to understand and interpret neural network. To understand the behaviors of multilayer perceptrons (MLPs) as classifiers,  we interpret MLPs as a generalization of a two-class LDA system so that it can handle an input composed by multiple Gaussian modalities belonging to multiple classes. An MLP design with two hidden layers that also specifies the filter weights is proposed. To understand the behaviors of multilayer perceptrons (MLPs) as a regressor we construct MLPs as a piecewise low-order polynomial approximator using a signal processing approach. The constructed MLP contains one input, one intermediate and one output layers. Its construction includes the specification of neuron numbers and all filter weights.  Through the construction, a one-to-one correspondence between the approximation of an MLP and that [...]

Let us hear what he has to say about his defense and an abstract of his thesis.

Deep learning has brought impressive improvements in many fields, thanks to end-to-end data-driven optimization. However, people have little control over the system during training and limited understanding about the structure of knowledge being learned. In this thesis, we study theory and applications of adversarial and structured knowledge learning: 1) learning adversarial knowledge with human interaction or by incorporating human-in-the-loop; 2) learning structured knowledge by modelling contexts and users’ preferences via distance metric learning.

In the first part, we teach a robotic arm to learn robust manipulation grasps that can withstand perturbations, through end-to-end optimization with a human adversary. Specifically, we formulate the problem as a two-player game with incomplete information, played by a human and a robot, where the human’s goal is to minimize the reward the robot can get. We then extend this idea to improve the sample efficiency of deep reinforcement learning by incorporating human in the training loop. We presented a portable, interactive and parallel platform for human-agent curriculum learning experience.

In the second part, we present two works that address different aspects of structured representation learning. First, we proposed a self-training framework to improve distance metric learning. The challenge is the noise in pseudo labels, which prevents exploiting additional unlabeled data. Therefore, we introduced a new feature basis learning component for the teacher-student network, which better measures pairwise similarity and selects high confidence pairs. Second, we address image-attribute query, which allows a user to customize image-to-image retrieval by designating desired attributes in target images. We achieve this by adopting a composition module, which enforces object-attribute factorization and an attribute-set synthesis module to deal with sample insufficiency.

Looking back, Prof. Kuo is [...]