Abstract Most recent learning algorithms for single image dehazing are designed to train with paired hazy and corresponding ground truth images, typically synthesized images. Real paired datasets can help to improve performance, but are tough to acquire. This paper proposes an unsupervised dehazing algorithm based on GAN to alleviate this issue. An end-to-end network based on GAN architecture is established and fed with unpaired clean and hazy images, signifying that the estimation of atmospheric light and transmission is not required. The proposed network consists of three parts: a generator, a global test discriminator, and a local context discriminator. Moreover, a dark channel prior based attention mechanism is applied to handle inconsistency haze. We conduct experiments on RESIDE datasets. Extensive experiments demonstrated the effectiveness of the proposed approach which outperformed previous state-of-the-art unsupervised methods by a large margin.

Few-Shot Image Classification aims to identify unseen categories by a limited number of instances. Recently, some metric-based methods have attempted to generate more discriminative task-specific embeddings by embedding adaptation strategies. However, the generated embeddings are either query-agnostic or ignore local relations between instances in each category, resulting in limited performance improvement. To address the above issues, in this letter, we propose QS-CAN, a Query-Specific embedding Co-Adaptation Network, which generates task- and query-specific embeddings by fusing inter-class and intra-class information. The core modules of QS-CAN are Inter-Class Adapter(Inter-A) and Intra-Class Adapter(Intra-A). The Inter-Class Adapter encodes the global relationship within the task, pushing the different categories away from each other. At the same time, the Intra-Class Adapter focuses on modeling the local relationship within each category, pulling the instances within a category closer. Moreover, an Adaptive Fusion Module(AFM) is proposed to integrate two co-adapted embeddings to get a more discriminative space. Experiments show that our method performs comparably to other advanced methods on three widely used datasets.

Recent years person re-identification (ReID) has been developed rapidly due to its broad practical applications. Most existing benchmarks assume that the same person wears the same clothes across captured images, while, in real-world scenarios, person may change his/her clothes frequently. Thus the Clothes-Changing person ReID (CC-ReID) problem is introduced and several related benchmarks are established. CC-ReID is a very difficult task as the main visual characteristics of a human body, clothes, are different between query and gallery, and clothes-irrelevant features are relatively weak. To promote the research and applications of person ReID in clothes-changing scenarios, in this paper, we introduce a new task called Clothes Template based Clothes-Changing person ReID (CTCC-ReID), where the query image is enhanced by a clothes template which shares similar visual patterns with the clothes of the target person image in the gallery. So, ReID methods are encouraged to jointly consider the original query image and the given clothes template for retrieval in the proposed CTCC-ReID setting. To facilitate research works on CTCC-ReID, we construct a novel large-scale ReID dataset named ClOthes ChAnging person Set Plus (COCAS+), which contains both realistic and synthetic clothes-changing person images with manually collected clothes templates. Furthermore, we propose a novel Dual-Attention Biometric-Clothes Transfusion Network (DualBCT-Net) for CTCC-ReID, which can effectively learn to extract biometric features from the original query person image and clothes features from the given clothes template and then fuse them through a Dual-Attention Fusion Module. Extensive experimental results show that the proposed CTCC-ReID setting and COCAS+ dataset can help greatly push the performance of clothes-changing ReID toward practical applications, and synthetic data is impressively effective for CTCC-ReID. What’s more, the proposed DualBCT-Net shows significant improvements over state-of-the-art methods on the CTCC-ReID task. COCAS+ and code of DualBCT-Net will be released inhttps://github.com/Chenhaobin/COCAS-plus.

Few-shot image classification (FSIC) is the task of generalizing a model to unknown categories by learning from a small number of labeled samples of some given categories. Recently, metric-based approaches have received lots of attention for their simplicity and effectiveness, but they often only use support set to generate inaccurate prototypes matching query set, ignoring the rich information contained in queries and the reversibility of the matching relationship between the two. In this letter, we propose a new simple and effective metric-based method called Bidirectional Matching Prototypical Network (BMPN), which has three innovations:1)It has an additional reverse matching process. This process uses queries to generate more accurate prototypes to improve the model’s performance while also forcing the model to learn features far from the decision boundary to enhance generalization capabilities; 2)It has a lightweight coordinate attention feature extractor (CAFE). This module not only captures long-term dependence along one spatial direction but also saving the accurate position information of the other spatial direction, helping the model to locate the region of interest more accurately; 3)It has a joint loss function, including forward matching loss and reverse matching loss, and a progressive weighting strategy is used in the training process to balance the importance of the two. Our model is trained end-to-end, and the experimental results show that we have reached the most advanced performance on the two benchmark datasets.

Unsupervised domain adaptation (UDA) in person re-identification (re-ID) is a challenging task, aiming to learn a model with labeled source data and unlabeled target data to recognize the same person in the target domain across different cameras. Recently, a lot of popular and promising methods based on clustering are proposed for this task and achieve a sizable progress. However, in those methods, without target labels, the clustering algorithms will inevitably produce noisy pseudo-labels. Overfitting on these noisy labels is severely harmful to the performance and generalization of models. In order to address the above issues, we propose a novel framework, Adaptive Deep Clustering (AdaDC), to reduce the negative impact of noisy pseudo-labels. On one hand, the proposed approach employs different clustering methods adaptively and alternately to fully exploit their complementary information and avoid overfitting noisy pseudo-labels. On the other hand, there is a progressive sample selection strategy for reducing noisy label ratio in pseudo-labels, which is achieved by integrating different clustering results. Experiments present that the proposed approach can achieve state-of-the-art performance compared to the other recent UDA person re-ID methods on widely-used datasets. Moreover, there are some other analysis experiments conducted for verifying the effectiveness of the proposed approach.

RS-LDPC codes, constructed based on the codewords of Reed-Solomon (RS) codes with two information symbols, are an important class of LDPC codes. In this paper, we present two representations, namely, quasi-cyclic (QC) representation and vector representation, for RS-LDPC codes. Under the first representation, most part of the parity-check matrix of a full-length RS-LDPC code consists of circulant permutation matrices and zero matrices. As a result, the class of codes can enjoy the advantages in hardware implementation as QC-LDPC codes. In addition, the base matrix under the QC representation of an RS-LDPC code can be explicitly given such that the rank of its parity-check matrix can be analyzed combinatorially. Under the second representation, each permutation matrix in the parity-check matrix of an RS-LDPC code is defined by a nonbinary vector, whose entries are a permutation of entries in the field from which the RS code is constructed. Then, the “affine invariance” property is proved for full-length RS-LDPC codes, which can facilitate the structural analysis of the codes.

Absorbing sets, a class of combinatorial structures of the Tanner graph representation of a low-density parity-check (LDPC) code, are known to influence the performance of the code under message passing iterative decoding. In this paper, we study the smallest absorbing sets of LDPC codes constructed from projective planes and Euclidean planes. The lower bounds on the parameters of smallest absorbing sets given by Dolecek are proven to be tight for these two families of LDPC codes. We also analyze the combinatorial properties of the smallest absorbing sets and give conditions necessary and sufficient for a set of bit nodes in the Tanner graph to be a smallest absorbing set. For LDPC codes from projective planes, we further give a condition necessary and sufficient for a smallest absorbing set to be a fully absorbing set. In addition, we show that these smallest absorbing sets are asymptotically not stable, which may explain to some extent the good performance as well as the low error floor expectation of these two families of LDPC codes.

In this paper, we focus on solving the linear programming (LP) problem that arises in the decoding of low-density parity-check (LDPC) codes by means of the revised simplex method. In order to take advantage of the structure of the LP problem, we reformulate the dual LP and apply the idea of Dantzig-Wolfe (D-W) decomposition method to solve the problem. Each subproblem in the D-W decomposition method is an LP over a convex polyhedral cone. We define the convex polyhedral cone as local parity-check cone and discuss its special structures. Then, we enumerate its extreme rays and use these extreme rays to design an efficient method for the general LP decoding problem. The proposed method exhibits advantages in reducing both the storage and computational requirements.

A programmable parallel digital signal processor (DSP) core for embedded applications is presented which combines the concepts of single instruction stream over multiple data streams (SIMD) and reconfigurable architecture. Equipped with eight SIMD-controlled 16-bit datapaths which can also be reconfigured as two 32-bit datapaths, the DSP core can process both 16-bit and 32-bit data in parallel, showing high performance, especially in the applications preferring parallel data flow computations, such as image processing. The SIMD scheme is extended with the instant-scalability of datapaths (ISSIMD), which offers the DSP a capability of dimension-controllable vector processing, so that to provide flexibility for different embedded applications. A first prototype in 0.18-/spl mu/m CMOS technology has been fabricated, which achieves IGMACS performance at the clock of 125 MHz.

Abstract In recent years, a new quasi‐synchronous CDMA (QS‐CDMA) system based on complete complementary codes with zero correlation zones (ZCZ), named ZCZ‐CDMA system, has been proposed. In a ZCZ‐CDMA system, data transmission efficiency can be greatly improved by accurately detecting the multi‐path properties of the communication channel utilizing the unique correlation features of the ZCZ sequence. As for the despreading operation and the code acquisition, the ZCZ‐CDMA system however is more complicated and difficult than the conventional DS‐CDMA systems. In this paper, we discuss the issues of the code acquisition in ZCZ‐CDMA systems, and propose an efficient code acquisition scheme, called two‐stage search (TSS) scheme. In the first stage of the TSS code acquisition scheme, a predictive code phase is coarsely searched, and then a fine search utilizing the unique features of the ZCZ‐sequences is carried out in the second stage. Simulation results show that the proposed scheme achieves better performance in terms of search time and hardware complexity than conventional code acquisition schemes. Copyright © 2003 John Wiley & Sons, Ltd.