Gradient-based explanation is the cornerstone of explainable deep networks, but it has been shown to be vulnerable to adversarial attacks. However, existing works measure the explanation robustness based on $\ell_p$-norm, which can be counter-intuitive to humans, who only pay attention to the top few salient features. We propose explanation ranking thickness as a more suitable explanation robustness metric. We then present a new practical adversarial attacking goal for manipulating explanation rankings. To mitigate the ranking-based attacks while maintaining computational feasibility, we derive surrogate bounds of the thickness that involve expensive sampling and integration. We use a multi-objective approach to analyze the convergence of a gradient-based attack to confirm that the explanation robustness can be measured by the thickness metric. We conduct experiments on various network architectures and diverse datasets to prove the superiority of the proposed methods, while the widely accepted Hessian-based curvature smoothing approaches are not as robust as our method.
LiDAR and camera are two essential sensors for 3D object detection in autonomous driving. LiDAR provides accurate and reliable 3D geometry information while the camera provides rich texture with color. Despite the increasing popularity of fusing these two complementary sensors, the challenge remains in how to effectively fuse 3D LiDAR point cloud with 2D camera images. Recent methods focus on point-level fusion which paints the LiDAR point cloud with camera features in the perspective view or bird's-eye view (BEV)-level fusion which unifies multi-modality features in the BEV representation. In this paper, we rethink these previous fusion strategies and analyze their information loss and influences on geometric and semantic features. We present SemanticBEVFusion to deeply fuse camera features with LiDAR features in a unified BEV representation while maintaining per-modality strengths for 3D object detection. Our method achieves state-of-the-art performance on the large-scale nuScenes dataset, especially for challenging distant objects. The code will be made publicly available.
Sketches make an intuitive and powerful visual expression as they are fast executed freehand drawings. We present a method for synthesizing realistic photos from scene sketches. Without the need for sketch and photo pairs, our framework directly learns from readily available large-scale photo datasets in an unsupervised manner. To this end, we introduce a standardization module that provides pseudo sketch-photo pairs during training by converting photos and sketches to a standardized domain, i.e. the edge map. The reduced domain gap between sketch and photo also allows us to disentangle them into two components: holistic scene structures and low-level visual styles such as color and texture. Taking this advantage, we synthesize a photo-realistic image by combining the structure of a sketch and the visual style of a reference photo. Extensive experimental results on perceptual similarity metrics and human perceptual studies show the proposed method could generate realistic photos with high fidelity from scene sketches and outperform state-of-the-art photo synthesis baselines. We also demonstrate that our framework facilitates a controllable manipulation of photo synthesis by editing strokes of corresponding sketches, delivering more fine-grained details than previous approaches that rely on region-level editing.
Risk assessment is a substantial problem for financial institutions that has been extensively studied both for its methodological richness and its various practical applications. With the expansion of inclusive finance, recent attentions are paid to micro and small-sized enterprises (MSEs). Compared with large companies, MSEs present a higher exposure rate to default owing to their insecure financial stability. Conventional efforts learn classifiers from historical data with elaborate feature engineering. However, the main obstacle for MSEs involves severe deficiency in credit-related information, which may degrade the performance of prediction. Besides, financial activities have diverse explicit and implicit relations, which have not been fully exploited for risk judgement in commercial banks. In particular, the observations on real data show that various relationships between company users have additional power in financial risk analysis. In this paper, we consider a graph of banking data, and propose a novel HIDAM model for the purpose. Specifically, we attempt to incorporate heterogeneous information network with rich attributes on multi-typed nodes and links for modeling the scenario of business banking service. To enhance feature representation of MSEs, we extract interactive information through meta-paths and fully exploit path information. Furthermore, we devise a hierarchical attention mechanism respectively to learn the importance of contents inside each meta-path and the importance of different metapahs. Experimental results verify that HIDAM outperforms state-of-the-art competitors on real-world banking data.
Fake reviews are prevalent on review websites such as Amazon and Yelp. GNN is the state-of-the-art method that can detect suspicious reviewers by exploiting the topologies of the graph connecting reviewers, reviews, and target products. However, the discrepancy in the detection accuracy over different groups of reviewers causes discriminative treatment of different reviewers of the websites, leading to less engagement and trustworthiness of such websites. The complex dependencies over the review graph introduce difficulties in teasing out subgroups of reviewers that are hidden within larger groups and are treated unfairly. There is no previous study that defines and discovers the subtle subgroups to improve equitable treatment of reviewers. This paper addresses the challenges of defining, discovering, and utilizing subgroup memberships for fair spam detection. We first define a subgroup membership that can lead to discrepant accuracy in the subgroups. Since the subgroup membership is usually not observable while also important to guide the GNN detector to balance the treatment, we design a model that jointly infers the hidden subgroup memberships and exploits the membership for calibrating the target GNN's detection accuracy across subgroups. Comprehensive results on two large Yelp review datasets demonstrate that the proposed model can be trained to treat the subgroups more fairly.
We present a structured graph variational autoencoder for generating the layout of indoor 3D scenes. Given the room type (e.g., living room or library) and the room layout (e.g., room elements such as floor and walls), our architecture generates a collection of objects (e.g., furniture items such as sofa, table and chairs) that is consistent with the room type and layout. This is a challenging problem because the generated scene should satisfy multiple constrains, e.g., each object must lie inside the room and two objects cannot occupy the same volume. To address these challenges, we propose a deep generative model that encodes these relationships as soft constraints on an attributed graph (e.g., the nodes capture attributes of room and furniture elements, such as class, pose and size, and the edges capture geometric relationships such as relative orientation). The architecture consists of a graph encoder that maps the input graph to a structured latent space, and a graph decoder that generates a furniture graph, given a latent code and the room graph. The latent space is modeled with auto-regressive priors, which facilitates the generation of highly structured scenes. We also propose an efficient training procedure that combines matching and constrained learning. Experiments on the 3D-FRONT dataset show that our method produces scenes that are diverse and are adapted to the room layout.
To enrich the functionalities of traditional cameras, light field cameras record both the intensity and direction of light rays, so that images can be rendered with user-defined camera parameters via computations. The added capability and flexibility are gained at the cost of gathering typically more than $100\times$ greater amount of information than conventional images. To cope with this issue, several light field compression schemes have been introduced. However, their ways of exploiting correlations of multidimensional light field data are complex and are hence not suited for inexpensive light field cameras. In this work, we propose a novel $\ell_\infty$-constrained light-field image compression system that has a very low-complexity DPCM encoder and a CNN-based deep decoder. Targeting high-fidelity reconstruction, the CNN decoder capitalizes on the $\ell_\infty$-constraint and light field properties to remove the compression artifacts and achieves significantly better performance than existing state-of-the-art $\ell_2$-based light field compression methods.
Social networks are polluted by rumors, which can be detected by machine learning models. However, the models are fragile and understanding the vulnerabilities is critical to rumor detection. Certain vulnerabilities are due to dependencies on the graphs and suspiciousness ranking and are difficult for end-to-end methods to learn from limited noisy data. With a black-box detector, we design features capturing the dependencies to allow a reinforcement learning to learn an effective and interpretable attack policy based on the detector output. To speed up learning, we devise: (i) a credit assignment method that decomposes delayed rewards to individual attacking steps proportional to their effects; (ii) a time-dependent control variate to reduce variance due to large graphs and many attacking steps. On two social rumor datasets, we demonstrate: (i) the effectiveness of the attacks compared to rule-based attacks and end-to-end approaches; (ii) the usefulness of the proposed credit assignment strategy and control variate; (iii) interpretability of the policy when generating strong attacks.