Unifying Fourteen Post-Hoc Attribution Methods With Taylor Interactions.

Various attribution methods have been developed to explain deep neural networks (DNNs) by inferring the attribution/importance/contribution score of each input variable to the final output. However, existing attribution methods are often built upon different heuristics. There remains a lack of a unified theoretical understanding of why these methods are effective and how they are related. Furthermore, there is still no universally accepted criterion to compare whether one attribution method is preferable over another. In this paper, we resort to Taylor interactions and for the first time, we discover that fourteen existing attribution methods, which define attributions based on fully different heuristics, actually share the same core mechanism. Specifically, we prove that attribution scores of input variables estimated by the fourteen attribution methods can all be mathematically reformulated as a weighted allocation of two typical types of effects, i.e., independent effects of each input variable and interaction effects between input variables. The essential difference among these attribution methods lies in the weights of allocating different effects. Inspired by these insights, we propose three principles for fairly allocating the effects, which serve as new criteria to evaluate the faithfulness of attribution methods. In summary, this study can be considered as a new unified perspective to revisit fourteen attribution methods, which theoretically clarifies essential similarities and differences among these methods. Besides, the proposed new principles enable people to make a direct and fair comparison among different methods under the unified perspective.

A convenient polyculture system that controls a shrimp viral disease with a high transmission rate.

Developing ecological approaches for disease control is critical for future sustainable aquaculture development. White spot syndrome (WSS), caused by white spot syndrome virus (WSSV), is the most severe disease in cultured shrimp production. Culturing specific pathogen-free (SPF) broodstock is an effective and widely used strategy for controlling WSS. However, most small-scale farmers, who predominate shrimp aquaculture in developing countries, cannot cultivate SPF shrimp, as they do not have the required infrastructure and skills. Thus, these producers are more vulnerable to WSS outbreaks than industrial farms. Here we developed a shrimp polyculture system that prevents WSS outbreaks by introducing specific fish species. The system is easy to implement and requires no special biosecurity measures. The promotion of this system in China demonstrated that it allowed small-scale farmers to improve their livelihood through shrimp cultivation by controlling WSS outbreaks and increasing the production of ponds.

An Algorithm of l 1-Norm and l 0-Norm Regularization Algorithm for CT Image Reconstruction from Limited Projection.

The l 1-norm regularization has attracted attention for image reconstruction in computed tomography. The l 0-norm of the gradients of an image provides a measure of the sparsity of gradients of the image. In this paper, we present a new combined l 1-norm and l 0-norm regularization model for image reconstruction from limited projection data in computed tomography. We also propose an algorithm in the algebraic framework to solve the optimization effectively using the nonmonotone alternating direction algorithm with hard thresholding method. Numerical experiments indicate that this new algorithm makes much improvement by involving l 0-norm regularization.

A self-tuned graph-based framework for localization and grading prostate cancer lesions: An initial evaluation based on multiparametric magnetic resonance imaging.

Multiparametric magnetic resonance imaging (mpMRI) has been established as the state-of-the-art examination for the detection and localization of prostate cancer lesions. Prostate Imaging-Reporting and Data System (PI-RADS) has been established as a scheme to standardize the reporting of mpMRI findings. Although lesion delineation and PI-RADS ratings could be performed manually, human delineation and ratings are subjective and time-consuming. In this article, we developed and validated a self-tuned graph-based model for PI-RADS rating prediction. 34 features were obtained at the pixel level from T2-weighted (T2W), apparent diffusion coefficient (ADC) and dynamic contrast enhanced (DCE) images, from which PI-RADS scores were predicted. Two major innovations were involved in this self-tuned graph-based model. First, graph-based approaches are sensitive to the choice of the edge weight. The proposed model tuned the edge weights automatically based on the structure of the data, thereby obviating empirical edge weight selection. Second, the feature weights were tuned automatically to give heavier weights to features important for PI-RADS rating estimation. The proposed framework was evaluated for its lesion localization performance in mpMRI datasets of 12 patients. In the evaluation, the PI-RADS score distribution map generated by the algorithm and from the observers' ratings were binarized by thresholds of 3 and 4. The sensitivity, specificity and accuracy obtained in these two threshold settings ranged from 65 to 77%, 86 to 93% and 85 to 88% respectively, which are comparable to results obtained in previous studies in which non-clinical T2 maps were available. The proposed algorithm took 10s to estimate the PI-RADS score distribution in an axial image. The efficiency achievable suggests that this technique can be developed into a prostate MR analysis system suitable for clinical use after a thorough validation involving more patients.

Learning Low-Rank Class-Specific Dictionary and Sparse Intra-Class Variant Dictionary for Face Recognition.

Face recognition is challenging especially when the images from different persons are similar to each other due to variations in illumination, expression, and occlusion. If we have sufficient training images of each person which can span the facial variations of that person under testing conditions, sparse representation based classification (SRC) achieves very promising results. However, in many applications, face recognition often encounters the small sample size problem arising from the small number of available training images for each person. In this paper, we present a novel face recognition framework by utilizing low-rank and sparse error matrix decomposition, and sparse coding techniques (LRSE+SC). Firstly, the low-rank matrix recovery technique is applied to decompose the face images per class into a low-rank matrix and a sparse error matrix. The low-rank matrix of each individual is a class-specific dictionary and it captures the discriminative feature of this individual. The sparse error matrix represents the intra-class variations, such as illumination, expression changes. Secondly, we combine the low-rank part (representative basis) of each person into a supervised dictionary and integrate all the sparse error matrix of each individual into a within-individual variant dictionary which can be applied to represent the possible variations between the testing and training images. Then these two dictionaries are used to code the query image. The within-individual variant dictionary can be shared by all the subjects and only contribute to explain the lighting conditions, expressions, and occlusions of the query image rather than discrimination. At last, a reconstruction-based scheme is adopted for face recognition. Since the within-individual dictionary is introduced, LRSE+SC can handle the problem of the corrupted training data and the situation that not all subjects have enough samples for training. Experimental results show that our method achieves the state-of-the-art results on AR, FERET, FRGC and LFW databases.

[The application of multi-slice CT and MRI on maxillofacial region soft tissue measurement].

PURPOSE: To evaluate the value of multi-slice CT and MRI on maxillofacial region soft tissue measurement. METHODS: A total of 12 cases of dentofacial orthodontic underwent X-ray photograph, multi-slice CT and MRI scanning. The angle and distance of maxillofacial region soft tissue were measured respectively. All data were analyzed statistically for ANOVA with SPSS11.0 software package. RESULTS: There was no significant difference among the three measurement methods: X-ray photograph, multi-slice CT and MRI(P>0.05). MRI had advantages on depicting hierarchical structure of maxillofacial region, especially soft tissues, while multi-slice CT had advantages on depicting structure of maxillofacial region, both hard and soft tissues. CONCLUSIONS: Multi-slice CT and MRI are useful on maxillofacial region soft tissues measurement. MRI is superior to multi-slice CT and X-ray photograph on maxillofacial region soft tissue measurement.