Abstract

Alongside revenue maximization, retailers seek to offer a diverse range of items to facilitate sustainable revenue generation in the long run. Moreover, customers typically buy sets of items, i.e., itemsets, as opposed to individual items. Therefore, strategic placement of diversified and high-revenue itemsets is a priority for the retailer. Research efforts made towards the extraction and placement of high-revenue itemsets in retail stores do not consider the notion of diversification. Further, candidate itemsets generated using existing utility mining schemes usually explode; which can cause memory and retrieval- time issues. This work makes three key contributions. First, we propose an efficient framework for retrieval of high-revenue itemsets with a varying size and a varying degree of diversification. A higher degree of diversification is indicative of fewer repetitive items in the top-revenue itemsets. Second, we propose the kUI (k Utility Itemset) index for quick and efficient retrieval of diverse top-λ high-revenue itemsets. We also propose the HUDIP (High-Utility and Diversified Itemset Placement) scheme, which exploits our proposed kUI index for placement of high-revenue and diversified itemsets. Third, our extensive performance study with both real and synthetic datasets demonstrates the effectiveness of our proposed HUDIP scheme in efficiently determining high-revenue and diversified itemsets.

Abstract

Anatomical variabilities seen in longitudinal data or inter- subject data is usually described by the underlying deformation, cap- tured by non-rigid registration of these images. Stationary Velocity Field (SVF) based non-rigid registration algorithms are widely used for reg- istration. However, these methods cover only a limited degree of defor- mations. We address this limitation and define an approximate metric space for the manifold of diffeomorphisms G. We propose a method to break down the large deformation into finite set of small sequential defor- mations. This results in a broken geodesic path on G and its length now forms an approximate registration metric. We illustrate the method using a simple, intensity-based, log-demon implementation. Validation results of the proposed method show that it can capture large and complex de- formations while producing qualitatively better results than state-of-the- art methods. The results also demonstrate that the proposed registration metric is a good indicator of the degree of deformation.

Abstract

Self-supervised methods have shown promising results in denoising and dehazing tasks, where the collection of the paired dataset is challenging and expensive. However, we find that these methods fail to remove the rain streaks when applied for image deraining tasks. The method’s poor per- formance is due to the explicit assumptions: (i) the distribu- tion of noise or haze is uniform and (ii) the value of a noisy or hazy pixel is independent of its neighbors. The rainy pix- els are non-uniformly distributed, and it is not necessarily dependant on its neighboring pixels. Hence, we conclude that the self-supervised method needs to have some prior knowledge about rain distribution to perform the deraining task. To provide this knowledge, we hypothesize a network trained with minimal supervision to estimate the likelihood of rainy pixels. This leads us to our proposed method called FLUID: Few Shot Self-Supervised Image Deraining. We perform extensive experiments and comparisons with existing image deraining and few-shot image-to-image translation methods on Rain 100L and DDN-SIRR datasets containing real and synthetic rainy images. In addition, we use the Rainy Cityscapes dataset to show that our method trained in a few-shot setting can improve semantic segmen- tation and object detection in rainy conditions. Our ap- proach obtains a mIoU gain of 51.20 over the current best- performing deraining method.

Abstract

Restoring images degraded due to atmospheric turbulence is challenging as it consists of several distortions. Several deep learning methods have been proposed to minimize atmospheric distortions that consist of a single-stage deep net- work. However, we find that a single-stage deep network is insuffi- cient to remove the mixture of distortions caused by atmospheric turbulence. We propose a two-stage deep adversarial network that minimizes atmospheric turbulence to mitigate this. The first stage reduces the geometrical distortion and the second stage minimizes the image blur. We improve our network by adding channel attention and a proposed sub-pixel mechanism, which utilizes the information between the channels and further reduces the atmospheric turbulence at the finer level. Unlike previous methods, our approach neither uses any prior knowledge about atmospheric turbulence conditions at inference time nor requires the fusion of multiple images to get a single restored image. Our final restoration models DT-GAN+ and DTD-GAN+ outperform the general state-of-the-art image-to-image translation models and baseline restoration models. We synthesize turbulent image datasets to train the restoration models. Additionally, we also curate a natural turbulent dataset from YouTube to show the generalisability of the proposed model. We perform extensive experiments on restored images by utilizing them for downstream tasks such as classification, pose estimation, semantic keypoint estimation, and depth estimation. We observe that our restored images outperform turbulent images in downstream tasks by a significant margin demonstrating the restoration model’s applica- bility in real-world problems.

Abstract

Crowdsourcing is an effective method to collect data by employingdistributed human population. Researchers introduce Peer-BasedMechanisms (PBMs) in crowdsourcing settings to incentivize agentsto report accurately. We observe that with PBMs, crowdsourcingsystems may not be fair. Unfair rewards for the agents may discour-age participation. This work aims to build a general frameworkthat assures fairness for PBMs in a temporal setting, i.e., wherereports are time-sensitive. Towards this, we introduce two notionsof fairness for PBMs, namely𝛾-fairnessandqualitative fairness. Tosatisfy these notions, our framework provides trustworthy agentswith additional chances of pairing. We introduce Temporal Reputa-tion Model (TERM) to quantify agents’ trustworthiness across tasks.Having TERM, we present our iterative framework, REFORM, thatcan adopt the reward scheme of any existing PBM. We demonstrateREFORM’s significance by deploying the framework with RPTSC’sreward scheme and prove that REFORM with RPTSC considerablyimproves fairness; while incentivizing truthful and early reports.

Abstract

Some of the issues associated with the prac- tical applications of consensus of multi-agent systems (MAS) include switching topologies, attrition and inclusion of agents from an existing network, and model uncertain- ties of agents. In this paper, a single distributed dynamic state-feedback protocol referred to as the Robust Attrition- Inclusion Distributed Dynamic (RAIDD) consensus proto- col, is synthesized for achieving the consensus of MAS with attrition and inclusion of linear time-invariant higher-order uncertain homogeneous agents and switching topologies. A state consensus problem termed as the Robust Attrition- Inclusion (RAI) consensus problem is formulated to find this RAIDD consensus protocol. To solve this RAI con- sensus problem, first, the sufficient condition for the exis- tence of the RAIDD protocol is obtained using the ν-gap metric-based simultaneous stabilization approach. Next, the RAIDD consensus protocol is attained using the Glover- McFarlane robust stabilization method if the sufficient con- dition is satisfied. The performance of this RAIDD protocol is validated by numerical simulations.

Abstract

— Sparse local feature matching is pivotal for many computer vision and robotics tasks. To improve their invariance to challenging appearance conditions and viewing angles, and hence their usefulness, existing learning-based methods have primarily focused on data augmentation-based training. In this work, we propose an alternative, complementary approach that centers on inducing bias in the model architecture itself to generate ‘rotation-specific’ features using Steerable E2-CNNs, that are then group-pooled to achieve rotation-invariant local features. We demonstrate that this high performance, rotationspecific coverage from the steerable CNNs can be expanded to all rotation angles by combining it with augmentationtrained standard CNNs which have broader coverage but are often inaccurate, thus creating a state-of-the-art rotation-robust local feature matcher. We benchmark our proposed methods against existing techniques on HPatches and a newly proposed UrbanScenes3D-Air dataset for visual place recognition. Furthermore, we present a detailed analysis of the performance effects of ensembling, robust estimation, network architecture variations, and the use of rotation priors

Abstract

Modern autonomous vehicles (AVs) often rely on vision, LIDAR, and even radar-based simultaneous localization and mapping (SLAM) frameworks for precise localization and navigation. However, modern SLAM frameworks often lead to unacceptably high levels of drift (i.e., localization error) when AVs observe few visually distinct features or encounter occlusions due to dynamic obstacles. This paper argues that minimizing drift must be a key desiderata in AV motion planning, which requires an AV to take active control decisions to move towards feature-rich regions while also minimizing conventional control cost. To do so, we first introduce a novel data-driven perception module that observes LIDAR point clouds and estimates which features/regions an AV must navigate towards for drift minimization. Then, we introduce an interpretable model predictive controller (MPC) that moves an AV toward such feature-rich regions while avoiding visual occlusions and gracefully trading off drift and control cost. Our experiments on challenging, dynamic scenarios in the state-ofthe-art CARLA simulator indicate our method reduces drift up to 76.76% compared to benchmark approaches

Abstract

Automated generation and (user) authoring of the realistic virtual terrain is most sought for by the multimedia applications like VR models and gaming. The most common representation adopted for terrain is Digital Elevation Model (DEM). Existing terrain authoring and modelling techniques have addressed some of these and can be broadly categorised as: procedural modeling, simulation method, and example-based methods. In this paper, we propose a novel realistic terrain authoring framework powered by a combination of VAE and generative conditional GAN model. Our framework is an example-based method that attempt to overcome the limitations of existing methods by learning a latent space from real world terrain dataset. This latent space allows us to generate multiple variants of terrain from a single input as well as interpolate between terrains, while keeping the generated terrains close to real world data distribution. We also developed an interactive tool, that lets the user generate diverse terrains with minimalist inputs. We perform thorough qualitative and quantitative analysis and provide comparison with other SOTA methods. We intend to release our code/tool to academic community.

Abstract

Toric differential inclusions occur as key dynamical systems in the context of the Global Attractor Conjecture. We introduce the notions of minimal invariant regions and minimal globally attracting regions for toric differential inclusions. We describe a procedure for explicitly constructing the minimal invariant and minimal globally attracting regions for two-dimensional toric differential inclusions. In particular, we obtain invariant regions and globally attracting regions for two-dimensional weakly reversible or endotactic dynamical systems (even if they have time-dependent parameters).