Image Stitching and Rectification for Hand-Held Cameras

/in /by

In this paper, we derive a new differential homography that can account for the scanline-varying camera poses in Rolling Shutter (RS) cameras, and demonstrate its application to carry out RS-aware image stitching and rectification at one stroke. Despite the high complexity of RS geometry, we focus in this paper on a special yet common input — two consecutive frames from a video stream, wherein the inter-frame motion is restricted from being arbitrarily large. This allows us to adopt simpler differential motion model, leading to a straightforward and practical minimal solver. To deal with non-planar scene and camera parallax in stitching, we further propose an RS-aware spatially-varying homogarphy field in the principle of As-Projective-As-Possible (APAP). We show superior performance over state-of-the-art methods both in RS image stitching and rectification, especially for images captured by hand-held shaking cameras.

Read more

Domain Adaptive Semantic Segmentation using Weak Labels

/in /by

We propose a novel framework for domain adaptation in semantic segmentation with image-level weak labels in the target domain. The weak labels may be obtained based on a model prediction for unsupervised domain adaptation (UDA), or from a human oracle in a new weakly-supervised domain adaptation (WDA) paradigm for semantic segmentation. Using weak labels is both practical and useful, since (i) collecting image-level target annotations is comparably cheap in WDA and incurs no cost in UDA, and (ii) it opens the opportunity for category-wise domain alignment. Our framework uses weak labels to enable the interplay between feature alignment and pseudo-labeling, improving both in the process of domain adaptation. Specifically, we develop a weak-label classification module to enforce the network to attend to certain categories, and then use such training signals to guide the proposed category-wise alignment method. In experiments, we show considerable improvements with respect to the existing state-of-the-arts in UDA and present a new benchmark in the WDA setting.

Read more

BAFFLE: Decentralized Blockchain based Aggregator-Free Federated Learning

/in /by

A key aspect of Federated Learning (FL) is the requirement of a centralized aggregator to maintain and update the global model. However, in many cases orchestrating a centralized aggregator might be infeasible due to numerous operational constraints. In this paper, we introduce BAFFLE, an aggregator free, blockchain driven, FL environment that is inherently decentralized. BAFFLE leverages Smart Contracts (SC) to coordinate the round delineation, model aggregation and update tasks in FL. BAFFLE boosts computational performance by decomposing the global parameter space into distinct chunks followed by a score and bid strategy. In order to characterize the performance of BAFFLE, we conduct experiments on a private Ethereum network and use the centralized and aggregator driven methods as our benchmark. We show that BAFFLE significantly reduces the gas costs for FL on the blockchain as compared to a direct adaptation of the aggregator based method. Our results also show that BAFFLE achieves high scalability and computational efficiency while delivering similar accuracy as the benchmark methods.

Read more

Stochastic Decision-Making Model for Aggregation of Residential Units with PV-Systems and Storages

/in /by

Many residential energy consumers have installed photovoltaic (PV) panels and energy storage systems. These residential users can aggregate and participate in the energy markets. A stochastic decision making model for an aggregation of these residential units for participation in two-settlement markets is proposed in this paper. Scenarios are generated using Seasonal Autoregressive Integrated Moving Average (SARIMA) model and joint probability distribution function of the forecast errors to model the uncertainties of the real-time prices, PV generations and demands. The proposed scenario generation model of this paper treats forecast errors as random variable, which allows to reflect new information observed in the real-time market into scenario generation process without retraining SARIMA or re-fitting probability distribution functions over the forecast errors. This approach significantly improves the computational time of the proposed model. A simulation study is conducted for an aggregation of 6 residential units, and the results highlights the benefits of aggregation as well as the proposed stochastic decision-making model.

Read more

Robust Graph Representation Learning via Neural Sparsification

/in /by

Graph representation learning serves as the core of important prediction tasks, ranging from product recommendation to fraud detection. Reallife graphs usually have complex information in the local neighborhood, where each node is described by a rich set of features and connects to dozens or even hundreds of neighbors. Despite the success of neighborhood aggregation in graph neural networks, task-irrelevant information is mixed into nodes’ neighborhood, making learned models suffer from sub-optimal generalization performance. In this paper, we present NeuralSparse, a supervised graph sparsification technique that improves generalization power by learning to remove potentially task-irrelevant edges from input graphs. Our method takes both structural and nonstructural information as input, utilizes deep neural networks to parameterize sparsification processes, and optimizes the parameters by feedback signals from downstream tasks. Under the NeuralSparse framework, supervised graph sparsification could seamlessly connect with existing graph neural networks for more robust performance. Experimental results on both benchmark and private datasets show that NeuralSparse can yield up to 7.2% improvement in testing accuracy when working with existing graph neural networks on node classification tasks.

Read more

Austere Flash Caching with Deduplication and Compression

/in /by

Modern storage systems leverage flash caching to boost I/O performance, and enhancing the space efficiency and endurance of flash caching remains a critical yet challenging issue in the face of ever-growing data-intensive workloads. Deduplication and compression are promising data reduction techniques for storage and I/O savings via the removal of duplicate content, yet they also incur substantial memory overhead for index management. We propose AustereCache, a new flash caching design that aims for memory-efficient indexing, while preserving the data reduction benefits of deduplication and compression. AustereCache emphasizes austere cache management and proposes different core techniques for efficient data organization and cache replacement, so as to eliminate as much indexing metadata as possible and make lightweight in-memory index structures viable. Trace-driven experiments show that our AustereCache prototype saves 69.9-97.0% of memory usage compared to the state-of-the-art flash caching design that supports deduplication and compression, while maintaining comparable read hit ratios and write reduction ratios and achieving high I/O throughput.

Read more

Improving Face Recognition by Clustering Unlabeled Faces in the Wild (arXiv)

/in /by

Read Improving Face Recognition by Clustering Unlabeled Faces in the Wild (arXiv). While deep face recognition has benefited significantly from large scale labeled data, current research is focused on leveraging unlabeled data to further boost performance, reducing the cost of human annotation. Prior work has mostly been in controlled settings, where the labeled and unlabeled data sets have no overlapping identities by construction. This is not realistic in large scale face recognition, where one must contend with such overlaps, the frequency of which increases with the volume of data. Ignoring identity overlap leads to significant labeling noise, as data from the same identity is split into multiple clusters. To address this, we propose a novel identity separation method based on extreme value theory. It is formulated as an out of distribution detection algorithm, and greatly reduces the problems caused by overlapping identity label noise. Considering cluster assignments as pseudo labels, we must also overcome the labeling noise from clustering errors. We propose a modulation of the cosine loss, where the modulation weights correspond to an estimate of clustering uncertainty. Extensive experiments on both controlled and real settings demonstrate our method’s consistent improvements over supervised baselines, e.g., 11.6% improvement on IJB A verification.

Read more

DeepTrack: Grouping RFID Tags Based on Spatio-temporal Proximity in Retail Spaces

/in /by

RFID applications for taking inventory and processing transactions in point-of-sale (POS) systems improve operational efficiency but are not designed to provide insights about customers’ interactions with products. We bridge this gap by solving the proximity grouping problem to identify groups of RFID tags that stay in close proximity to each other over time. We design DeepTrack, a framework that uses deep learning to automatically track the group of items carried by a customer during her shopping journey. This unearths hidden purchase behaviors helping retailers make better business decisions and paves the way for innovative shopping experiences such as seamless checkout (‘a la Amazon Go). DeepTrack employs a recurrent neural network (RNN) with the attention mechanism, to solve the proximity grouping problem in noisy settings without explicitly localizing tags. We tailor DeepTrack’s design to track not only mobile groups (products carried by customers) but also flexibly identify stationary tag groups (products on shelves). The key attribute of DeepTrack is that it only uses readily available tag data from commercial off-the-shelf RFID equipment. Our experiments demonstrate that, with only two hours training data, DeepTrack achieves a grouping accuracy of 98.18% (99.79%) when tracking eight mobile (stationary) groups.

Read more

Improving Disentangled Text Representation Learning with Information Theoretical Guidance

/in /by

Learning disentangled representations of natural language is essential for many NLP tasks, e.g., conditional text generation, style transfer, personalized dialogue systems, etc. Similar problems have been studied extensively for other forms of data, such as images and videos. However, the discrete nature of natural language makes the disentangling of textual representations more challenging (e.g., the manipulation over the data space cannot be easily achieved). Inspired by information theory, we propose a novel method that effectively manifests disentangled representations of text, without any supervision on semantics. A new mutual information upper bound is derived and leveraged to measure dependence between style and content. By minimizing this upper bound, the proposed method induces style and content embeddings into two independent low-dimensional spaces. Experiments on both conditional text generation and text-style transfer demonstrate the high quality of our disentangled representation in terms of content and style preservation.

Read more

On Optimal Multi-user Beam Alignment in Millimeter Wave Wireless Systems

/in /by

Directional transmission patterns (a.k.a. narrow beams) are the key to wireless communications in millimeter wave (mmWave) frequency bands which suffer from high path loss and severe shadowing. In addition, the propagation channel in mmWave frequencies incorporates only a few number of spatial clusters requiring a procedure to align the corresponding narrow beams with the angle of departure (AoD) of the channel clusters. The objective of this procedure, called beam alignment (BA) is to increase the beamforming gain for subsequent data communication. Several prior studies consider optimizing BA procedure to achieve various objectives such as reducing the BA overhead, increasing throughput, and reducing power consumption. While these studies mostly provide optimized BA schemes for scenarios with a single active user, there are often multiple active users in practical networks. Consequently, it is more efficient in terms of BA overhead and delay to design multi-user BA schemes which can perform beam management for multiple users collectively. This paper considers a class of multi-user BA schemes where the base station performs a one shot scan of the angular domain to simultaneously localize multiple users. The objective is to minimize the average of expected width of remaining uncertainty regions (UR) on the AoDs after receiving users’ feedbacks. Fundamental bounds on the optimal performance are analyzed using information theoretic tools. Furthermore, a BA optimization problem is formulated and a practical BA scheme, which provides significant gains compared to the beam sweeping used in 5G standard, is proposed.

Read more