Kwang-Ting Cheng

Bio: Kwang-Ting Cheng is an academic researcher from Hong Kong University of Science and Technology. The author has contributed to research in topics: Automatic test pattern generation & Sequential logic. The author has an hindex of 63, co-authored 525 publications receiving 16332 citations. Previous affiliations of Kwang-Ting Cheng include University of California, Los Angeles & University of California.

Fast Human Detection Using a Cascade of Histograms of Oriented Gradients

Abstract: We integrate the cascade-of-rejectors approach with the Histograms of Oriented Gradients (HoG) features to achieve a fast and accurate human detection system. The features used in our system are HoGs of variable-size blocks that capture salient features of humans automatically. Using AdaBoost for feature selection, we identify the appropriate set of blocks, from a large set of possible blocks. In our system, we use the integral image representation and a rejection cascade which significantly speed up the computation. For a 320 × 280 image, the system can process 5 to 30 frames per second depending on the density in which we scan the image, while maintaining an accuracy level similar to existing methods.

Bi-Real Net: Enhancing the Performance of 1-Bit CNNs with Improved Representational Capability and Advanced Training Algorithm

Abstract: In this work, we study the 1-bit convolutional neural networks (CNNs), of which both the weights and activations are binary. While being efficient, the classification accuracy of the current 1-bit CNNs is much worse compared to their counterpart real-valued CNN models on the large-scale dataset, like ImageNet. To minimize the performance gap between the 1-bit and real-valued CNN models, we propose a novel model, dubbed Bi-Real net, which connects the real activations (after the 1-bit convolution and/or BatchNorm layer, before the sign function) to activations of the consecutive block, through an identity shortcut. Consequently, compared to the standard 1-bit CNN, the representational capability of the Bi-Real net is significantly enhanced and the additional cost on computation is negligible. Moreover, we develop a specific training algorithm including three technical novelties for 1-bit CNNs. Firstly, we derive a tight approximation to the derivative of the non-differentiable sign function with respect to activation. Secondly, we propose a magnitude-aware gradient with respect to the weight for updating the weight parameters. Thirdly, we pre-train the real-valued CNN model with a clip function, rather than the ReLU function, to better initialize the Bi-Real net. Experiments on ImageNet show that the Bi-Real net with the proposed training algorithm achieves 56.4% and 62.2% top-1 accuracy with 18 layers and 34 layers, respectively. Compared to the state-of-the-arts (e.g., XNOR Net), Bi-Real net achieves up to 10% higher top-1 accuracy with more memory saving and lower computational cost.

A partial scan method for sequential circuits with feedback

Abstract: A method of partial scan design is presented in which the selection of scan flip-flops is aimed at breaking up the cyclic structure of the circuit. Experimental data are given to show that the test generation complexity may grow exponentially with the length of the cycles in the circuit. This complexity grows only linearly with the sequential depth. Graph-theoretic algorithms are presented to select a minimal set of flip-flops for eliminating cycles and reducing the sequential depth. Tests for the resulting circuit are generated by a sequential logic test generator. An independent control of the scan clock allows insertion of scan sequences within the vector sequence produced by the test generator. An independent control of the scan clock allows insertion of scan sequences within the vector sequences produced by the test generator. 98% fault coverage is obtained for a 5000-gate circuit by scanning just 5% of the flip-flops. >

Biocompatible and totally disintegrable semiconducting polymer for ultrathin and ultralightweight transient electronics

Abstract: Increasing performance demands and shorter use lifetimes of consumer electronics have resulted in the rapid growth of electronic waste. Currently, consumer electronics are typically made with nondecomposable, nonbiocompatible, and sometimes even toxic materials, leading to serious ecological challenges worldwide. Here, we report an example of totally disintegrable and biocompatible semiconducting polymers for thin-film transistors. The polymer consists of reversible imine bonds and building blocks that can be easily decomposed under mild acidic conditions. In addition, an ultrathin (800-nm) biodegradable cellulose substrate with high chemical and thermal stability is developed. Coupled with iron electrodes, we have successfully fabricated fully disintegrable and biocompatible polymer transistors. Furthermore, disintegrable and biocompatible pseudo-complementary metal–oxide–semiconductor (CMOS) flexible circuits are demonstrated. These flexible circuits are ultrathin ( 2 ) with low operating voltage (4 V), yielding potential applications of these disintegrable semiconducting polymers in low-cost, biocompatible, and ultralightweight transient electronics.

Joint Segment-Level and Pixel-Wise Losses for Deep Learning Based Retinal Vessel Segmentation

Abstract: Objective: Deep learning based methods for retinal vessel segmentation are usually trained based on pixel-wise losses, which treat all vessel pixels with equal importance in pixel-to-pixel matching between a predicted probability map and the corresponding manually annotated segmentation. However, due to the highly imbalanced pixel ratio between thick and thin vessels in fundus images, a pixel-wise loss would limit deep learning models to learn features for accurate segmentation of thin vessels, which is an important task for clinical diagnosis of eye-related diseases. Methods: In this paper, we propose a new segment-level loss which emphasizes more on the thickness consistency of thin vessels in the training process. By jointly adopting both the segment-level and the pixel-wise losses, the importance between thick and thin vessels in the loss calculation would be more balanced. As a result, more effective features can be learned for vessel segmentation without increasing the overall model complexity. Results: Experimental results on public data sets demonstrate that the model trained by the joint losses outperforms the current state-of-the-art methods in both separate-training and cross-training evaluations. Conclusion: Compared to the pixel-wise loss, utilizing the proposed joint-loss framework is able to learn more distinguishable features for vessel segmentation. In addition, the segment-level loss can bring consistent performance improvement for both deep and shallow network architectures. Significance: The findings from this study of using joint losses can be applied to other deep learning models for performance improvement without significantly changing the network architectures.

I and i

Abstract: There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality. Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

ORB-SLAM: A Versatile and Accurate Monocular SLAM System

Abstract: This paper presents ORB-SLAM, a feature-based monocular simultaneous localization and mapping (SLAM) system that operates in real time, in small and large indoor and outdoor environments. The system is robust to severe motion clutter, allows wide baseline loop closing and relocalization, and includes full automatic initialization. Building on excellent algorithms of recent years, we designed from scratch a novel system that uses the same features for all SLAM tasks: tracking, mapping, relocalization, and loop closing. A survival of the fittest strategy that selects the points and keyframes of the reconstruction leads to excellent robustness and generates a compact and trackable map that only grows if the scene content changes, allowing lifelong operation. We present an exhaustive evaluation in 27 sequences from the most popular datasets. ORB-SLAM achieves unprecedented performance with respect to other state-of-the-art monocular SLAM approaches. For the benefit of the community, we make the source code public.

Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks

Abstract: Face detection and alignment in unconstrained environment are challenging due to various poses, illuminations, and occlusions. Recent studies show that deep learning approaches can achieve impressive performance on these two tasks. In this letter, we propose a deep cascaded multitask framework that exploits the inherent correlation between detection and alignment to boost up their performance. In particular, our framework leverages a cascaded architecture with three stages of carefully designed deep convolutional networks to predict face and landmark location in a coarse-to-fine manner. In addition, we propose a new online hard sample mining strategy that further improves the performance in practice. Our method achieves superior accuracy over the state-of-the-art techniques on the challenging face detection dataset and benchmark and WIDER FACE benchmarks for face detection, and annotated facial landmarks in the wild benchmark for face alignment, while keeps real-time performance.