A novel contrast enhancement algorithm is proposed The proposed approach enhances the contrast without losing the original histogram characteristics, which is based on the histogram specification technique It is expected to eliminate the annoying side effects effectively by using the differential information from the input histogram The experimental results show that the proposed dynamic histogram specification (DHS) algorithm not only keeps the original histogram shape features but also enhances the contrast effectively Moreover, the DHS algorithm can be applied by simple hardware and processed in real-time system due to its simplicity

Dynamic contrast enhancement based on histogram specification

This paper is a statistical analysis of hybrid expert system approaches and their applications but more specifically connectionist and neuro-fuzzy system oriented articles are considered. The current survey of hybrid expert systems is based on the classification of articles from 1988 to 2010. Present analysis includes 91 articles from related academic journals, conference proceedings and literature reviews. Our results show an increase in the number of recent publications which is an indication of gaining popularity on the part of hybrid expert systems. This increase in the articles is mainly in neuro-fuzzy and rough neural expert systems' areas. We also observe that many new industrial applications are developed using hybrid expert systems recently.

Review: Hybrid expert systems: A survey of current approaches and applications

Universal domain adaptation (UniDA) transfers knowledge between domains without any constraint on the label sets, extending the applicability of domain adaptation in the wild. In UniDA, both the source and target label sets may hold individual labels not shared by the other domain. A de facto challenge of UniDA is to classify the target examples in the shared classes against the domain shift. A more prominent challenge of UniDA is to mark the target examples in the target-individual label set (open classes) as “unknown”. These two entangled challenges make UniDA a highly under-explored problem. Previous work on UniDA focuses on the classification of data in the shared classes and uses per-class accuracy as the evaluation metric, which is badly biased to the accuracy of shared classes. However, accurately detecting open classes is the mission-critical task to enable real universal domain adaptation. It further turns UniDA problem into a well-established close-set domain adaptation problem. Towards accurate open class detection, we propose Calibrated Multiple Uncertainties (CMU) with a novel transferability measure estimated by a mixture of uncertainty quantities in complementation: entropy, confidence and consistency, defined on conditional probabilities calibrated by a multi-classifier ensemble model. The new transferability measure accurately quantifies the inclination of a target example to the open classes. We also propose a novel evaluation metric called H-score, which emphasizes the importance of both accuracies of the shared classes and the “unknown” class. Empirical results under the UniDA setting show that CMU outperforms the state-of-the-art domain adaptation methods on all the evaluation metrics, especially by a large margin on the H-score.

Learning to Detect Open Classes for Universal Domain Adaptation

In packet-based video transmissions, packets loss due to channel errors may result in the loss of the whole video frame. Recently, many error concealment algorithms have been proposed in order to combat channel errors; however, most of the existing algorithms can only deal with the loss of macroblocks and are not able to conceal the whole missing frame. In order to resolve this problem, in this paper, we have proposed a new hybrid motion vector extrapolation (HMVE) algorithm to recover the whole missing frame, and it is able to provide more accurate estimation for the motion vectors of the missing frame than other conventional methods. Simulation results show that it is highly effective and significantly outperforms other existing frame recovery methods.

A Hybrid Frame Concealment Algorithm for H.264/AVC

/pdf/a-hybrid-frame-concealment-algorithm-for-h-264-avc-nist-w6y0rburk2.pdf

A Hybrid Frame Concealment Algorithm for H.264/AVC | NIST

Domain adaptation (DA) has been a fundamental building block for Transfer Learning (TL) which assumes that source and target domain share the same label space. A more general and realistic setting is that the label space of target domain is a subset of the source domain, as termed by Partial domain adaptation (PDA). Previous methods typically match the whole source domain to target domain, which causes negative transfer due to the source-negative classes in source domain that does not exist in target domain. In this paper, a novel Discriminative Partial Domain Adversarial Network (DPDAN) is developed. We first propose to use hard binary weighting to differentiate the source-positive and source-negative samples in the source domain. The source-positive samples are those with labels shared by two domains, while the rest in the source domain are treated as source-negative samples. Based on the above binary relabeling strategy, our algorithm maximizes the distribution divergence between source-negative samples and all the others (source-positive and target samples), meanwhile minimizes domain shift between source-positive samples and target domain to obtain discriminative domain-invariant features. We empirically verify DPDAN can effectively reduce the negative transfer caused by source-negative classes, and also theoretically show it decreases negative transfer caused by domain shift. Experiments on four benchmark domain adaptation datasets show DPDAN consistently outperforms state-of-the-art methods.

Discriminative Partial Domain Adversarial Network

In this paper, a new method is described to construct rough neural networks. On the base of rough set model, we present a method to develop rough neural network of variable precision and train it using Levenberg–Marquart algorithm. The method is particularly attractive because it combines the advantages of both rough logic networks and neural networks. In our system, weak generalization in rough sets theory and complexity in neural network are avoided while anti-jamming performance is highly improved and the network structure is also simplified. In experiments, the network is applied to classification of remote sensing images. The results show that our method is more effective and successful than application of rough sets and neural network separately.

Rough Neural Network of Variable Precision

Multisensor image registration is a difficult problem In this paper, we give a new registration method using direct histogram specification technique We find that after using histogram specification, the resulting images with the same view look more similar, though the original images gained by different sensors differ much in intensity Based on this property, a novel approach to find matching block pairs is proposed The centers of the block pairs are used as control points (cps) We also use the cluster method of the nearest function criterion to test the correctness of the cps and discard wrong ones The algorithm has been tested by many aerial images of different sensors The effectiveness is illustrated by the experimental results

Multisensor aerial image registration using direct histogram specification

Domain shift is a major challenge for object detectors to generalize well to real world applications. Emerging techniques of domain adaptation for two-stage detectors help to tackle this problem. However, two-stage detectors are not the first choice for industrial applications due to its long time consumption. In this paper, a novel Domain Adaptive YOLO (DA-YOLO) is proposed to improve cross-domain performance for one-stage detectors. Image level features alignment is used to strictly match for local features like texture, and loosely match for global features like illumination. Multi-scale instance level features alignment is presented to reduce instance domain shift effectively , such as variations in object appearance and viewpoint. A consensus regularization to these domain classifiers is employed to help the network generate domain-invariant detections. We evaluate our proposed method on popular datasets like Cityscapes, KITTI, SIM10K and etc.. The results demonstrate significant improvement when tested under different cross-domain scenarios.

Domain Adaptive YOLO for One-Stage Cross-Domain Detection.

Domain adaptation (DA) plays an important role in transfer learning. However, when target label space is a subset of source label space, standard DA cannot tackle this issue. Partial domain adaptation focuses on how to transfer knowledge from massive labelled dataset to unlabelled miniature one, which attracts extensive research interest. In this paper, we propose a Multi-Weight Partial Domain Adaptation (MWPDA) to solve the problem. We divide the source domain into two parts: shared classes and outlier classes. MWPDA aims to reduce negative transfer caused by outlier classes when transferring knowledge between domains. Based on OTSU-Algorithm, hard shared-class labels are obtained to decrease weights of outlier classes and increase ones of shared classes. A novel shared-sample classifier is trained for shared-sample weights to distinguish outlier samples. Shared-class weights and shared-sample weights are acted on source classifier and domain discriminator to jointly distinguish outlier classes and samples. This kind of multiweight mechanism can avoid misalignment to outlier classes and promote classification accuracy. Furthermore, our universal network framework is utilized for both partial domain adaptation and standard domain adaptation issues. Extensive experiments on three benchmark domain adaptation datasets illustrate our method achieves state-of-the-art results.

Hongya Tuo

Papers

Discriminative Partial Domain Adversarial Network

Rough Neural Network of Variable Precision

Multisensor aerial image registration using direct histogram specification

Domain Adaptive YOLO for One-Stage Cross-Domain Detection.

Multi-Weight Partial Domain Adaptation.