Zhiding Yu

SphereFace: Deep Hypersphere Embedding for Face Recognition

This paper addresses deep face recognition (FR) problem under open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal inter-class distance under a suitably chosen metric space. However, few existing algorithms can effectively achieve this criterion. To this end, we propose the angular softmax (A-Softmax) loss that enables convolutional neural networks (CNNs) to learn angularly discriminative features. Geometrically, A-Softmax loss can be viewed as imposing discriminative constraints on a hypersphere manifold, which intrinsically matches the prior that faces also lie on a manifold. Moreover, the size of angular margin can be quantitatively adjusted by a parameter m. We further derive specific m to approximate the ideal feature criterion. Extensive analysis and experiments on Labeled Face in the Wild (LFW), Youtube Faces (YTF) and MegaFace Challenge 1 show the superiority of A-Softmax loss in FR tasks.

Joint kernel dictionary and classifier learning for sparse coding via locality preserving K-SVD

We present a locality preserving K-SVD (LP-KSVD) algorithm for joint dictionary and classifier learning, and further incorporate kernel into our framework. In LP-KSVD, we construct a locality preserving term based on the relations between input samples and dictionary atoms, and introduce the locality via nearest neighborhood to enforce the locality of representation. Motivated by the fact that locality-related methods works better in a more discriminative and separable space, we map the original feature space to the kernel space, where samples of different classes become more separable. Experimental results show the proposed approach has strong discrimination power and is comparable or outperforms some state-of-the-art approaches on public databases.

CASENet: Deep Category-Aware Semantic Edge Detection

Boundary and edge cues are highly beneficial in improving a wide variety of vision tasks such as semantic segmentation, object recognition, stereo, and object proposal generation. Recently, the problem of edge detection has been revisited and significant progress has been made with deep learning. While classical edge detection is a challenging binary problem in itself, the category-aware semantic edge detection by nature is an even more challenging multi-label problem. We model the problem such that each edge pixel can be associated with more than one class as they appear in contours or junctions belonging to two or more semantic classes. To this end, we propose a novel end-to-end deep semantic edge learning architecture based on ResNet and a new skip-layer architecture where category-wise edge activations at the top convolution layer share and are fused with the same set of bottom layer features. We then propose a multi-label loss function to supervise the fused activations. We show that our proposed architecture benefits this problem with better performance, and we outperform the current state-of-the-art semantic edge detection methods by a large margin on standard data sets such as SBD and Cityscapes.

Transitive Distance Clustering with K-Means Duality

We propose a very intuitive and simple approximation for the conventional spectral clustering methods. It effectively alleviates the computational burden of spectral clustering - reducing the time complexity from O(n3) to O(n2) - while capable of gaining better performance in our experiments. Specifically, by involving a more realistic and effective distance and the k-means duality property, our algorithm can handle datasets with complex cluster shapes, multi-scale clusters and noise. We also show its superiority in a series of its real applications on tasks including digit clustering as well as image segmentation.

Jointly Learning Non-negative Projection and Dictionary with Discriminative Graph Constraints for Classification

Sparse coding with dictionary learning (DL) has shown excellent classification performance. Despite the considerable number of existing works, how to obtain features on top of which dictionaries can be better learned remains an open and interesting question. Many current prevailing DL methods directly adopt well-performing crafted features. While such strategy may empirically work well, it ignores certain intrinsic relationship between dictionaries and features. We propose a framework where features and dictionaries are jointly learned and optimized. The framework, named joint non-negative projection and dictionary learning (JNPDL), enables interaction between the input features and the dictionaries. The non-negative projection leads to discriminative parts-based object features while DL seeks a more suitable representation. Discriminative graph constraints are further imposed to simultaneously maximize intra-class compactness and inter-class separability. Experiments on both image and image set classification show the excellent performance of JNPDL by outperforming several state-of-the-art approaches.

Multi-kernel collaborative representation for image classification

We consider the image classification problem via multiple kernel collaborative representation (MKCR). We generalize the kernel collaborative representation based classification to a multi-kernel framework where multiple kernels are jointly learned with the representation coefficients. The intrinsic idea of multiple kernel learning is adopted in our MKCR model. Experimental results show MKCR converges within reasonable iterations and achieves state-of-the-art performance.

Robust rear-view ground surface detection with hidden state conditional random field and confidence propagation

We address the problem of detecting rear-view (obstacle free) ground surface using a vehicle production camera. This task is considerably more challenging than general front-view road detection, as the associated challenges widely range from low picture quality, fisheye distortion and large objects, to the absence of useful priors such as vanishing points and road structure. Regarding the challenges, we propose a feature that can simultaneously capture local appearance and context information. In addition, the task suffers from strong appearance variations such as shadows and ground markers. Therefore, we propose a novel conditional random field (CRF) model which includes hidden states indicating confident nodes and propagate their confidence to neighboring nodes. We show that our proposed feature and model can jointly achieve robustness against large objects and shadows/markers, showing excellent detection performance under low quality inputs.

Semi-supervised subspace learning with L2graph

Subspace learning aims to learn a projection matrix from a given training set so that a transformation of raw data to a low-dimensional representation can be obtained. In practice, the labels of some training samples are available, which can be used to improve the discrimination of low-dimensional representation. In this paper, we propose a semi-supervised learning method which is inspired by the biological observation of similar inputs having similar codes (SISC), i.e., the same collection of cortical columns of the mammals visual cortex is always activated by the similar stimuli. More specifically, we propose a mathematical formulation of SISC which minimizes the distance among the data points with the same label while maximizing the separability between different subjects in the projection space. The proposed method, namely, semi-supervised L2graph (SeL2graph) has two advantages: (1) unlike the classical dimension reduction methods such as principle component analysis, SeL2graph can automatically determine the dimension of feature space. This remarkably reduces the effort to find an optimal feature dimension for a good performance; and (2) it fully exploits the prior knowledge carried by the labeled samples and thus the obtained features are with higher discrimination and compactness. Extensive experiments show that the proposed method outperforms 7 subspace learning algorithms on 15 data sets with respect to classification accuracy, computational efficiency, and robustness to noises and disguises. HighlightsA semi-supervised subspace learning method is proposed.The method is inspired by similar inputs having similar code.The method can automatically determine the feature dimension.

Structured Hough Voting for Vision-Based Highway Border Detection

We propose a vision-based highway border detection algorithm using structured Hough voting. Our approach takes advantage of the geometric relationship between highway road borders and highway lane markings. It uses a strategy where a number of trained road border and lane marking detectors are triggered, followed by Hough voting to generate corresponding detection of the border and lane marking. Since the initially triggered detectors usually result in large number of positives, conventional frame-wise Hough voting is not able to always generate robust border and lane marking results. Therefore, we formulate this problem as a joint detection-and-tracking problem under the structured Hough voting model, where tracking refers to exploiting inter-frame structural information to stabilize the detection results. Both qualitative and quantitative evaluations show the superiority of the proposed structured Hough voting model over a number of baseline methods.

Efficient autism spectrum disorder prediction with eye movement: A machine learning framework

We propose an autism spectrum disorder (ASD) prediction system based on machine learning techniques. Our work features the novel development and application of machine learning methods over traditional ASD evaluation protocols. Specifically, we are interested in discovering the latent patterns that possibly indicate the symptom of ASD underneath the observations of eye movement. A group of subjects (either ASD or non-ASD) are shown with a set of aligned human face images, with eye gaze locations on each image recorded sequentially. An image-level feature is then extracted from the recorded eye gaze locations on each face image. Such feature extraction process is expected to capture discriminative eye movement patterns related to ASD. In this work, we propose a variety of feature extraction methods, seeking to evaluate their prediction performance comprehensively. We further propose an ASD prediction framework in which the prediction model is learned on the labeled features. At testing stage, a test subject is also asked to view the face images with eye gaze locations recorded. The learned model predicts the image-level labels and a threshold is set to determine whether the test subject potentially has ASD or not. Despite the inherent difficulty of ASD prediction, experimental results indicates statistical significance of the predicted results, showing promising perspective of this framework.