Global-Local Dynamic Feature Alignment Network for Person Re-Identification

The misalignment of human images caused by pedestrian detection bounding box errors or partial occlusions is one of the main challenges in person Re-Identification (Re-ID) tasks. Previous local-based methods mainly focus on learning local features in predefined semantic regions of pedestrians, usually use local hard alignment methods or introduce auxiliary information such as key human pose points to match local features. These methods are often not applicable when large scene differences are encountered. Targeting to solve these problems, we propose a simple and efficient Local Sliding Alignment (LSA) strategy to dynamically align the local features of two images by setting a sliding window on the local stripes of the pedestrian. LSA can effectively suppress spatial misalignment and does not need to introduce extra supervision information. Then, we design a Global-Local Dynamic Feature Alignment Network (GLDFA-Net) framework, which contains both global and local branches. We introduce LSA into the local branch of GLDFA-Net to guide the computation of distance metrics, which can further improve the accuracy of the testing phase. Evaluation experiments on several mainstream evaluation datasets including Market-1501, DukeMTMC-reID, and CUHK03 show that our method has competitive accuracy over the several state-of-the-art person Re-ID methods. Additionally, it achieves 86.1% mAP and 94.8% Rank-1 accuracy on Market1501.

Learning with Multiclass AUC: Theory and Algorithms

The Area under the ROC curve (AUC) is a well-known ranking metric for problems such as imbalanced learning and recommender systems. The vast majority of existing AUC-optimization-based machine learning methods only focus on binary-class cases, while leaving the multiclass cases unconsidered. In this paper, we start an early trial to consider the problem of learning multiclass scoring functions via optimizing multiclass AUC metrics. Our foundation is based on the M metric, which is a well-known multiclass extension of AUC. We first pay a revisit to this metric, showing that it could eliminate the imbalance issue from the minority class pairs. Motivated by this, we propose an empirical surrogate risk minimization framework to approximately optimize the M metric. Theoretically, we show that: (i) optimizing most of the popular differentiable surrogate losses suffices to reach the Bayes optimal scoring function asymptotically; (ii) the training framework enjoys an imbalance-aware generalization error bound, which pays more attention to the bottleneck samples of minority classes compared with the traditional $O(sqrt{1/N})$ result. Practically, to deal with the low scalability of the computational operations, we propose acceleration methods for three popular surrogate loss functions, including the exponential loss, squared loss, and hinge loss, to speed up loss and gradient evaluations. Finally, experimental results on 11 real-world datasets demonstrate the effectiveness of our proposed framework.

A note on extrapolation of compactness

This note is devoted to the study of Hyt{o}nens extrapolation theorem of compactness on weighted Lebesgue spaces. Two criteria of compactness of linear operators in the two-weight setting are obtained. As applications, we obtain two-weight compactness of commutators of Calder{o}n--Zygmund operators, fractional integrals and bilinear Calder{o}n--Zygmund operators.

Two results on character codegrees

Let $G$ be a finite group and $mathrm{Irr}(G)$ be the set of irreducible characters of $G$. The codegree of an irreducible character $chi$ of the group $G$ is defined as $mathrm{cod}(chi)=|G:mathrm{ker}(chi)|/chi(1)$. In this paper, we study two topics related to the character codegrees. Let $sigma^c(G)$ be the maximal integer $m$ such that there is a member in $mathrm{cod}(G)$ having $m$ distinct prime divisors, where $mathrm{cod}(G)={mathrm{cod}(chi)|chiin mathrm{Irr}(G)}$. One is related to the codegree version of the Hupperts $rho$-$sigma$ conjecture and we obtain the best possible bound for $|pi(G)|$ under the condition $sigma^c(G) = 2,3,$ and $4$ respectively. The other is related to the prime graph of character codegrees and we show that the codegree prime graphs of several classes of groups can be characterized only by graph theoretical terms.

Fully Automated Noncoplanar Radiation Therapy Treatment Planning

Noncoplanar radiation therapy treatment planning has the potential to improve dosimetric quality as compared to traditional coplanar techniques. Likewise, automated treatment planning algorithms can reduce a planners active treatment planning time and remove inter-planner variability. To address the limitations of traditional treatment planning, we have been developing a suite of algorithms called station parameter optimized radiation therapy (SPORT). Within the SPORT suite of algorithms, we propose a method called NC-POPS to produce noncoplanar (NC) plans using the fully automated Pareto Optimal Projection Search (POPS) algorithm. Our NC-POPS algorithm extends the original POPS algorithm to the noncoplanar setting with potential applications to both IMRT and VMAT. The proposed algorithm consists of two main parts: 1) noncoplanar beam angle optimization (BAO) and 2) fully automated inverse planning using the POPS algorithm. We evaluate the performance of NC-POPS by comparing between various noncoplanar and coplanar configurations. To evaluate plan quality, we compute the homogeneity index (HI), conformity index (CI), and dose-volume histogram (DVH) statistics for various organs-at-risk (OARs). As compared to the evaluated coplanar baseline methods, the proposed NC-POPS method achieves significantly better OAR sparing, comparable or better dose conformity, and similar dose homogeneity. Our proposed NC-POPS algorithm provides a modular approach for fully automated treatment planning of noncoplanar IMRT cases with the potential to substantially improve treatment planning workflow and plan quality.

Explore User Neighborhood for Real-time E-commerce Recommendation

Recommender systems play a vital role in modern online services, such as Amazon and Taobao. Traditional personalized methods, which focus on user-item (UI) relations, have been widely applied in industrial settings, owing to their efficiency and effectiveness. Despite their success, we argue that these approaches ignore local information hidden in similar users. To tackle this problem, user-based methods exploit similar user relations to make recommendations in a local perspective. Nevertheless, traditional user-based methods, like userKNN and matrix factorization, are intractable to be deployed in the real-time applications since such transductive models have to be recomputed or retrained with any new interaction. To overcome this challenge, we propose a framework called self-complementary collaborative filtering~(SCCF) which can make recommendations with both global and local information in real time. On the one hand, it utilizes UI relations and user neighborhood to capture both global and local information. On the other hand, it can identify similar users for each user in real time by inferring user representations on the fly with an inductive model. The proposed framework can be seamlessly incorporated into existing inductive UI approach and benefit from user neighborhood with little additional computation. It is also the first attempt to apply user-based methods in real-time settings. The effectiveness and efficiency of SCCF are demonstrated through extensive offline experiments on four public datasets, as well as a large scale online A/B test in Taobao.

On p-parts of character degrees

In this paper, we get the sharp bound for $|G/O_p(G)|_p$ under the assumption that either $p^2 mid chi(1)$ for all $chi in {rm Irr}(G)$ or $p^2 mid phi(1)$ for all $phi in {rm IBr}_p(G)$. This would settle two conjectures raised by Lewis, Navarro, Tiep, and Tong-Viet.

Matrix weighted Kolmogorov-Rieszs compactness theorem

In this paper, sever

Attribution Preservation in Network Compression for Reliable Network Interpretation

Neural networks embedded in safety-sensitive applications such as self-driving cars and wearable health monitors rely on two important techniques: input attribution for hindsight analysis and network compression to reduce its size for edge-computing. In this paper, we show that these seemingly unrelated techniques conflict with each other as network compression deforms the produced attributions, which could lead to dire consequences for mission-critical applications. This phenomenon arises due to the fact that conventional network compression methods only preserve the predictions of the network while ignoring the quality of the attributions. To combat the attribution inconsistency problem, we present a framework that can preserve the attributions while compressing a network. By employing the Weighted Collapsed Attribution Matching regularizer, we match the attribution maps of the network being compressed to its pre-compression former self. We demonstrate the effectiveness of our algorithm both quantitatively and qualitatively on diverse compression methods.

Commonsense knowledge adversarial dataset that challenges ELECTRA

Commonsense knowledge is critical in human reading comprehension. While machine comprehension has made significant progress in recent years, the ability in handling commonsense knowledge remains limited. Synonyms are one of the most widely used commonsense knowledge. Constructing adversarial dataset is an important approach to find weak points of machine comprehension models and support the design of solutions. To investigate machine comprehension models ability in handling the commonsense knowledge, we created a Question and Answer Dataset with common knowledge of Synonyms (QADS). QADS are questions generated based on SQuAD 2.0 by applying commonsense knowledge of synonyms. The synonyms are extracted from WordNet. Words often have multiple meanings and synonyms. We used an enhanced Lesk algorithm to perform word sense disambiguation to identify synonyms for the context. ELECTRA achieves the state-of-art result on the SQuAD 2.0 dataset in 2019. With scale, ELECTRA can achieve similar performance as BERT does. However, QADS shows that ELECTRA has little ability to handle commonsense knowledge of synonyms. In our experiment, ELECTRA-small can achieve 70% accuracy on SQuAD 2.0, but only 20% on QADS. ELECTRA-large did not perform much better. Its accuracy on SQuAD 2.0 is 88% but dropped significantly to 26% on QADS. In our earlier experiments, BERT, although also failed badly on QADS, was not as bad as ELECTRA. The result shows that even top-performing NLP models have little ability to handle commonsense knowledge which is essential in reading comprehension.