arXiv subjects

Mingsheng Long

Publications and source records attributed to Mingsheng Long.

134 records · Page 8Linked to original sources

arXiv2017

Correlation Hashing Network for Efficient Cross-Modal Retrieval

Hashing is widely applied to approximate nearest neighbor search for large-scale multimodal retrieval with storage and computation efficiency. Cross-modal hashing improves the quality of hash coding by exploiting semantic correlations across different modalities. Existing cross-modal hashing methods first transform data into low-dimensional feature vectors, and then generate binary codes by another separate quantization step. However, suboptimal hash codes may be generated since the quantization error is not explicitly minimized and the feature representation is not jointly optimized with the binary codes. This paper presents a Correlation Hashing Network (CHN) approach to cross-modal hashing, which jointly learns good data representation tailored to hash coding and formally controls the quantization error. The proposed CHN is a hybrid deep architecture that constitutes a convolutional neural network for learning good image representations, a multilayer perception for learning good text representations, two hashing layers for generating compact binary codes, and a structured max-margin loss that integrates all things together to enable learning similarity-preserving and high-quality hash codes. Extensive empirical study shows that CHN yields state of the art cross-modal retrieval performance on standard benchmarks.

cs.CV↗

arXiv2017

Unsupervised Domain Adaptation with Residual Transfer Networks

The recent success of deep neural networks relies on massive amounts of labeled data. For a target task where labeled data is unavailable, domain adaptation can transfer a learner from a different source domain. In this paper, we propose a new approach to domain adaptation in deep networks that can jointly learn adaptive classifiers and transferable features from labeled data in the source domain and unlabeled data in the target domain. We relax a shared-classifier assumption made by previous methods and assume that the source classifier and target classifier differ by a residual function. We enable classifier adaptation by plugging several layers into deep network to explicitly learn the residual function with reference to the target classifier. We fuse features of multiple layers with tensor product and embed them into reproducing kernel Hilbert spaces to match distributions for feature adaptation. The adaptation can be achieved in most feed-forward models by extending them with new residual layers and loss functions, which can be trained efficiently via back-propagation. Empirical evidence shows that the new approach outperforms state of the art methods on standard domain adaptation benchmarks.

cs.LG↗

arXiv2016

Transitive Hashing Network for Heterogeneous Multimedia Retrieval

Hashing has been widely applied to large-scale multimedia retrieval due to the storage and retrieval efficiency. Cross-modal hashing enables efficient retrieval from database of one modality in response to a query of another modality. Existing work on cross-modal hashing assumes heterogeneous relationship across modalities for hash function learning. In this paper, we relax the strong assumption by only requiring such heterogeneous relationship in an auxiliary dataset different from the query/database domain. We craft a hybrid deep architecture to simultaneously learn the cross-modal correlation from the auxiliary dataset, and align the dataset distributions between the auxiliary dataset and the query/database domain, which generates transitive hash codes for heterogeneous multimedia retrieval. Extensive experiments exhibit that the proposed approach yields state of the art multimedia retrieval performance on public datasets, i.e. NUS-WIDE, ImageNet-YahooQA.

cs.CV↗

arXiv2016

Composite Correlation Quantization for Efficient Multimodal Retrieval

Efficient similarity retrieval from large-scale multimodal database is pervasive in modern search engines and social networks. To support queries across content modalities, the system should enable cross-modal correlation and computation-efficient indexing. While hashing methods have shown great potential in achieving this goal, current attempts generally fail to learn isomorphic hash codes in a seamless scheme, that is, they embed multiple modalities in a continuous isomorphic space and separately threshold embeddings into binary codes, which incurs substantial loss of retrieval accuracy. In this paper, we approach seamless multimodal hashing by proposing a novel Composite Correlation Quantization (CCQ) model. Specifically, CCQ jointly finds correlation-maximal mappings that transform different modalities into isomorphic latent space, and learns composite quantizers that convert the isomorphic latent features into compact binary codes. An optimization framework is devised to preserve both intra-modal similarity and inter-modal correlation through minimizing both reconstruction and quantization errors, which can be trained from both paired and partially paired data in linear time. A comprehensive set of experiments clearly show the superior effectiveness and efficiency of CCQ against the state of the art hashing methods for both unimodal and cross-modal retrieval.

cs.IR↗

arXiv2016

Broadband Photovoltaic Detectors based on an Atomically Thin Heterostructure

Van der Waals junctions of two-dimensional materials with an atomically sharp interface open up unprecedented opportunities to design and study functional heterostructures. Semiconducting transition metal dichalcogenides have shown tremendous potential for future applications due to their unique electronic properties and strong light-matter interaction. However, many important optoelectronic applications, such as broadband photodetection, are severely hindered by their limited spectral range and reduced light absorption. Here, we present a p-g-n heterostructure formed by sandwiching graphene with a gapless bandstructure and wide absorption spectrum in an atomically thin p-n junction to overcome these major limitations. We have successfully demonstrated a MoS2-graphene-WSe2 heterostructure for broadband photodetection in the visible to short-wavelength infrared range at room temperature that exhibits competitive device performance, including a specific detectivity of up to 1011 Jones in the near-infrared region. Our results pave the way toward the implementation of atomically thin heterostructures for broadband and sensitive optoelectronic applications.

cond-mat.mtrl-sci↗

arXiv2015

High responsivity phototransistors based on few-layer ReS2 for weak signal detection

Two-dimensional transition metal dichalcogenides are emerging with tremendous potential in many optoelectronic applications due to their strong light-matter interactions. To fully explore their potential in photoconductive detectors, high responsivity and weak signal detection are required. Here, we present high responsivity phototransistors based on few-layer rhenium disulfide (ReS2). Depending on the back gate voltage, source drain bias and incident optical light intensity, the maximum attainable photoresponsivity can reach as high as 88,600 A W-1, which is a record value compared to other two-dimensional materials with similar device structures and two orders of magnitude higher than that of monolayer MoS2. Such high photoresponsivity is attributed to the increased light absorption as well as the gain enhancement due to the existence of trap states in the few-layer ReS2 flakes. It further enables the detection of weak signals, as successfully demonstrated with weak light sources including a lighter and limited fluorescent lighting. Our studies underscore ReS2 as a promising material for future sensitive optoelectronic applications.

cond-mat.mtrl-sci↗

arXiv2015

Learning Transferable Features with Deep Adaptation Networks

Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation. However, as deep features eventually transition from general to specific along the network, the feature transferability drops significantly in higher layers with increasing domain discrepancy. Hence, it is important to formally reduce the dataset bias and enhance the transferability in task-specific layers. In this paper, we propose a new Deep Adaptation Network (DAN) architecture, which generalizes deep convolutional neural network to the domain adaptation scenario. In DAN, hidden representations of all task-specific layers are embedded in a reproducing kernel Hilbert space where the mean embeddings of different domain distributions can be explicitly matched. The domain discrepancy is further reduced using an optimal multi-kernel selection method for mean embedding matching. DAN can learn transferable features with statistical guarantees, and can scale linearly by unbiased estimate of kernel embedding. Extensive empirical evidence shows that the proposed architecture yields state-of-the-art image classification error rates on standard domain adaptation benchmarks.

cs.LG↗

arXiv2010

Spin density wave in oxypnictide superconductors in a three-band model

The spin density wave and its temperature dependence in oxypnictide are studied in a three-band model. The spin susceptibilities with various interactions are calculated in the random phase approximation(PPA). It is found that the spin susceptibility peaks around the M point show a spin density wave(SDW) with momentum (0, $π$) and a clear stripe-like spin configuration. The intra-band Coulomb repulsion enhances remarkably the SDW but the Hund's coupling weakens it. It is shown that a new resonance appears at higher temperatures at the $Γ$ point indicating the formation of a paramagnetic phase. There is a clear transition from the SDW phase to the paramagnetic phase.

cond-mat.supr-con↗