arXiv subjects

Zhe Lin

Publications and source records attributed to Zhe Lin.

192 records · Page 11Linked to original sources

arXiv2016

Salient Object Subitizing

We study the problem of Salient Object Subitizing, i.e. predicting the existence and the number of salient objects in an image using holistic cues. This task is inspired by the ability of people to quickly and accurately identify the number of items within the subitizing range (1-4). To this end, we present a salient object subitizing image dataset of about 14K everyday images which are annotated using an online crowdsourcing marketplace. We show that using an end-to-end trained Convolutional Neural Network (CNN) model, we achieve prediction accuracy comparable to human performance in identifying images with zero or one salient object. For images with multiple salient objects, our model also provides significantly better than chance performance without requiring any localization process. Moreover, we propose a method to improve the training of the CNN subitizing model by leveraging synthetic images. In experiments, we demonstrate the accuracy and generalizability of our CNN subitizing model and its applications in salient object detection and image retrieval.

cs.CV↗

arXiv2015

Multi-Instance Visual-Semantic Embedding

Visual-semantic embedding models have been recently proposed and shown to be effective for image classification and zero-shot learning, by mapping images into a continuous semantic label space. Although several approaches have been proposed for single-label embedding tasks, handling images with multiple labels (which is a more general setting) still remains an open problem, mainly due to the complex underlying corresponding relationship between image and its labels. In this work, we present Multi-Instance visual-semantic Embedding model (MIE) for embedding images associated with either single or multiple labels. Our model discovers and maps semantically-meaningful image subregions to their corresponding labels. And we demonstrate the superiority of our method over the state-of-the-art on two tasks, including multi-label image annotation and zero-shot learning.

cs.CV↗

arXiv2015

Automatic Content-Aware Color and Tone Stylization

We introduce a new technique that automatically generates diverse, visually compelling stylizations for a photograph in an unsupervised manner. We achieve this by learning style ranking for a given input using a large photo collection and selecting a diverse subset of matching styles for final style transfer. We also propose a novel technique that transfers the global color and tone of the chosen exemplars to the input photograph while avoiding the common visual artifacts produced by the existing style transfer methods. Together, our style selection and transfer techniques produce compelling, artifact-free results on a wide range of input photographs, and a user study shows that our results are preferred over other techniques.

cs.CV↗

arXiv2015

LCNN: Low-level Feature Embedded CNN for Salient Object Detection

In this paper, we propose a novel deep neural network framework embedded with low-level features (LCNN) for salient object detection in complex images. We utilise the advantage of convolutional neural networks to automatically learn the high-level features that capture the structured information and semantic context in the image. In order to better adapt a CNN model into the saliency task, we redesign the network architecture based on the small-scale datasets. Several low-level features are extracted, which can effectively capture contrast and spatial information in the salient regions, and incorporated to compensate with the learned high-level features at the output of the last fully connected layer. The concatenated feature vector is further fed into a hinge-loss SVM detector in a joint discriminative learning manner and the final saliency score of each region within the bounding box is obtained by the linear combination of the detector's weights. Experiments on three challenging benchmark (MSRA-5000, PASCAL-S, ECCSD) demonstrate our algorithm to be effective and superior than most low-level oriented state-of-the-arts in terms of P-R curves, F-measure and mean absolute errors.

cs.CV↗

arXiv2015

Inner and Inter Label Propagation: Salient Object Detection in the Wild

In this paper, we propose a novel label propagation based method for saliency detection. A key observation is that saliency in an image can be estimated by propagating the labels extracted from the most certain background and object regions. For most natural images, some boundary superpixels serve as the background labels and the saliency of other superpixels are determined by ranking their similarities to the boundary labels based on an inner propagation scheme. For images of complex scenes, we further deploy a 3-cue-center-biased objectness measure to pick out and propagate foreground labels. A co-transduction algorithm is devised to fuse both boundary and objectness labels based on an inter propagation scheme. The compactness criterion decides whether the incorporation of objectness labels is necessary, thus greatly enhancing computational efficiency. Results on five benchmark datasets with pixel-wise accurate annotations show that the proposed method achieves superior performance compared with the newest state-of-the-arts in terms of different evaluation metrics.

cs.CV↗

arXiv2015

Joint Object and Part Segmentation using Deep Learned Potentials

Segmenting semantic objects from images and parsing them into their respective semantic parts are fundamental steps towards detailed object understanding in computer vision. In this paper, we propose a joint solution that tackles semantic object and part segmentation simultaneously, in which higher object-level context is provided to guide part segmentation, and more detailed part-level localization is utilized to refine object segmentation. Specifically, we first introduce the concept of semantic compositional parts (SCP) in which similar semantic parts are grouped and shared among different objects. A two-channel fully convolutional network (FCN) is then trained to provide the SCP and object potentials at each pixel. At the same time, a compact set of segments can also be obtained from the SCP predictions of the network. Given the potentials and the generated segments, in order to explore long-range context, we finally construct an efficient fully connected conditional random field (FCRF) to jointly predict the final object and part labels. Extensive evaluation on three different datasets shows that our approach can mutually enhance the performance of object and part segmentation, and outperforms the current state-of-the-art on both tasks.

cs.CV↗

arXiv2015

Collaborative Feature Learning from Social Media

Image feature representation plays an essential role in image recognition and related tasks. The current state-of-the-art feature learning paradigm is supervised learning from labeled data. However, this paradigm requires large-scale category labels, which limits its applicability to domains where labels are hard to obtain. In this paper, we propose a new data-driven feature learning paradigm which does not rely on category labels. Instead, we learn from user behavior data collected on social media. Concretely, we use the image relationship discovered in the latent space from the user behavior data to guide the image feature learning. We collect a large-scale image and user behavior dataset from Behance.net. The dataset consists of 1.9 million images and over 300 million view records from 1.9 million users. We validate our feature learning paradigm on this dataset and find that the learned feature significantly outperforms the state-of-the-art image features in learning better image similarities. We also show that the learned feature performs competitively on various recognition benchmarks.

cs.CV↗

arXiv2014

Scalable Similarity Learning using Large Margin Neighborhood Embedding

Classifying large-scale image data into object categories is an important problem that has received increasing research attention. Given the huge amount of data, non-parametric approaches such as nearest neighbor classifiers have shown promising results, especially when they are underpinned by a learned distance or similarity measurement. Although metric learning has been well studied in the past decades, most existing algorithms are impractical to handle large-scale data sets. In this paper, we present an image similarity learning method that can scale well in both the number of images and the dimensionality of image descriptors. To this end, similarity comparison is restricted to each sample's local neighbors and a discriminative similarity measure is induced from large margin neighborhood embedding. We also exploit the ensemble of projections so that high-dimensional features can be processed in a set of lower-dimensional subspaces in parallel without much performance compromise. The similarity function is learned online using a stochastic gradient descent algorithm in which the triplet sampling strategy is customized for quick convergence of classification performance. The effectiveness of our proposed model is validated on several data sets with scales varying from tens of thousands to one million images. Recognition accuracies competitive with the state-of-the-art performance are achieved with much higher efficiency and scalability.

cs.CV↗

arXiv2014

The Computational Compexity of Decision Problem in Additive Extensions of Nonassociative Lambek Calculus

We analyze the complexity of decision problems for Boolean Nonassociative Lambek Calculus admitting empty antecedent of sequents ($\mathsf{BFNL^*}$), and the consequence relation of Distributive Full Nonassociative Lambek Calculus ($\mathsf{DFNL}$). We construct a polynomial reduction from modal logic $\mathsf{K}$ into $\mathsf{BFNL^*}$. As a consequence, we prove that the decision problem for $\mathsf{BFNL^*}$ is PSPACE-hard. We also prove that the same result holds for the consequence relation of DFNL, by reducing $\mathsf{BFNL^*}$ in polynomial time to DFNL enriched with finite set of assumptions. Finally, we prove analogous results for variants of $\mathsf{BFNL^*}$, including $\mathsf{BFNL^*e}$ ($\mathsf{BFNL^*}$ with exchange), modal extensions of $\mathsf{BFNL^*_i}$ and $\mathsf{BFNL^*_{ei}}$ for $i \in \{\mathsf{K}, \mathsf{T}, \mathsf{K4}, \mathsf{S4}, \mathsf{S5}\}$.

cs.LO↗

arXiv2014

Residuated Basic Logic I

We study the residuated basic logic ($\mathsf{RBL}$) of residuated basic algebra in which the basic implication of Visser's basic propositional logic ($\mathsf{BPL}$) is interpreted as the right residual of a non-associative binary operator $\cdot$ (product). We develop an algebraic system $\mathsf{S_{RBL}}$ of residuated basic algebra by which we show that $\mathsf{RBL}$ is a conservative extension of $\mathsf{BPL}$. We present the sequent formalization $\mathsf{L_{RBL}}$ of $\mathsf{S_{RBL}}$ which is an extension of distributive full non-associative Lambek calculus ($\mathsf{DFNL}$), and show that the cut elimination and subformula property hold for it.

math.LO↗

arXiv2014

Residuated Basic Logic II. Interpolation, Decidability and Embedding

We prove that the sequent calculus $\mathsf{L_{RBL}}$ for residuated basic logic $\mathsf{RBL}$ has strong finite model property, and that intuitionistic logic can be embedded into basic propositional logic $\mathsf{BPL}$. Thus $\mathsf{RBL}$ is decidable. Moreover, it follows that the class of residuated basic algebras has the finite embeddability property, and that $\mathsf{BPL}$ is PSPACE-complete, and that intuitionistic logic can be embedded into the modal logic $\mathsf{K4}$.

math.LO↗

arXiv2013

GPU Asynchronous Stochastic Gradient Descent to Speed Up Neural Network Training

The ability to train large-scale neural networks has resulted in state-of-the-art performance in many areas of computer vision. These results have largely come from computational break throughs of two forms: model parallelism, e.g. GPU accelerated training, which has seen quick adoption in computer vision circles, and data parallelism, e.g. A-SGD, whose large scale has been used mostly in industry. We report early experiments with a system that makes use of both model parallelism and data parallelism, we call GPU A-SGD. We show using GPU A-SGD it is possible to speed up training of large convolutional neural networks useful for computer vision. We believe GPU A-SGD will make it possible to train larger networks on larger training sets in a reasonable amount of time.

cs.CV↗