Humans have a natural instinct to identify unknown object instances in their environments. The intrinsic curiosity about these unknown instances aids in learning about them, when the corresponding knowledge is eventually available. This motivates us to propose a novel computer vision problem called: `Open World Object Detection', where a model is tasked to: 1) identify objects that have not been introduced to it as `unknown', without explicit supervision to do so, and 2) incrementally learn these identified unknown categories without forgetting previously learned classes, when the corresponding labels are progressively received. We formulate the problem, introduce a strong evaluation protocol and provide a novel solution, which we call ORE: Open World Object Detector, based on contrastive clustering and energy based unknown identification. Our experimental evaluation and ablation studies analyze the efficacy of ORE in achieving Open World objectives. As an interesting by-product, we find that identifying and characterizing unknown instances helps to reduce confusion in an incremental object detection setting, where we achieve state-of-the-art performance, with no extra methodological effort. We hope that our work will attract further research into this newly identified, yet crucial research direction.

Generalization to out-of-distribution (OOD) data is a capability natural to humans yet challenging for machines to reproduce. This is because most statistical learning algorithms strongly rely on the i.i.d.~assumption while in practice the target data often come from a different distribution than the source data, known as domain shift. Domain generalization (DG) aims to achieve OOD generalization by only using source domain data for model learning. Since first introduced in 2011, research in DG has undergone a decade progress. Ten years of research in this topic have led to a broad spectrum of methodologies, e.g., based on domain alignment, meta-learning, data augmentation, or ensemble learning, just to name a few; and have covered various applications such as object recognition, segmentation, action recognition, and person re-identification. In this paper, for the first time, a comprehensive literature review is provided to summarize the ten-year development in DG. First, we cover the background by giving the problem definitions and discussing how DG is related to other fields like domain adaptation and transfer learning. Second, we conduct a thorough review into existing methods and present a taxonomy based on their methodologies and motivations. Finally, we conclude this survey with potential research directions.

This paper proposes a supervised machine learning approach for predicting the root cause of a given bug report. Knowing the root cause of a bug can help developers in the debugging process - either directly or indirectly by choosing proper tool support for the debugging task. We mined 54755 closed bug reports from the issue trackers of 103 GitHub projects and applied a set of heuristics to create a benchmark consisting of 10459 reports. A subset was manually classified into three groups (semantic, memory, and concurrency) based on the bugs' root causes. Since the types of root cause are not equally distributed, a combination of keyword search and random selection was applied. Our data set for the machine learning approach consists of 369 bug reports (122 concurrency, 121 memory, and 126 semantic bugs). The bug reports are used as input to a natural language processing algorithm. We evaluated the performance of several classifiers for predicting the root causes for the given bug reports. Linear Support Vector machines achieved the highest mean precision (0.74) and recall (0.72) scores. The created bug data set and classification are publicly available.

Fairness and explainability are two important and closely related requirements of decision making systems. While fairness and explainability of decision making systems have been extensively studied independently, only little effort has been put into studying fairness of explanations on their own. Current explanations can be unfair to an individual: an example is given by counterfactual explanations which propose different actions to change the output class to two similar individuals. In this work we formally and empirically study individual fairness and its mathematical formalization as robustness for counterfactual explanations as a prominent instance of contrasting explanations. In addition, we propose to use plausible counterfactuals instead of closest counterfactuals for improving the individual fairness of counterfactual explanations.

The key challenge of unsupervised vehicle re-identification (Re-ID) is learning discriminative features from unlabelled vehicle images. Numerous methods using domain adaptation have achieved outstanding performance, but those methods still need a labelled dataset as a source domain. This paper addresses an unsupervised vehicle Re-ID method, which no need any types of a labelled dataset, through a Self-supervised Metric Learning (SSML) based on a feature dictionary. Our method initially extracts features from vehicle images and stores them in a dictionary. Thereafter, based on the dictionary, the proposed method conducts dictionary-based positive label mining (DPLM) to search for positive labels. Pair-wise similarity, relative-rank consistency, and adjacent feature distribution similarity are jointly considered to find images that may belong to the same vehicle of a given probe image. The results of DPLM are applied to dictionary-based triplet loss (DTL) to improve the discriminativeness of learnt features and to refine the quality of the results of DPLM progressively. The iterative process with DPLM and DTL boosts the performance of unsupervised vehicle Re-ID. Experimental results demonstrate the effectiveness of the proposed method by producing promising vehicle Re-ID performance without a pre-labelled dataset. The source code for this paper is publicly available on `https://github.com/andreYoo/VeRI_SSML_FD.git'.

Since the recent study (Krichene and Rendle 2020) done by Krichene and Rendle on the sampling-based top-k evaluation metric for recommendation, there has been a lot of debates on the validity of using sampling to evaluate recommendation algorithms. Though their work and the recent work (Li et al.2020) have proposed some basic approaches for mapping the sampling-based metrics to their global counterparts which rank the entire set of items, there is still a lack of understanding and consensus on how sampling should be used for recommendation evaluation. The proposed approaches either are rather uninformative (linking sampling to metric evaluation) or can only work on simple metrics, such as Recall/Precision (Krichene and Rendle 2020; Li et al. 2020). In this paper, we introduce a new research problem on learning the empirical rank distribution, and a new approach based on the estimated rank distribution, to estimate the top-k metrics. Since this question is closely related to the underlying mechanism of sampling for recommendation, tackling it can help better understand the power of sampling and can help resolve the questions of if and how should we use sampling for evaluating recommendation. We introduce two approaches based on MLE (MaximalLikelihood Estimation) and its weighted variants, and ME(Maximal Entropy) principals to recover the empirical rank distribution, and then utilize them for metrics estimation. The experimental results show the advantages of using the new approaches for evaluating recommendation algorithms based on top-k metrics.

It is essential to understand how different Machine Learning algorithms work to succeed in your Data Science projects. I have written this story as part of the series that dives into each ML algorithm explaining its mechanics, supplemented by Python code examples and intuitive visualizations. Support Vector Machines (SVMs) are most frequently used for solving classification problems, which fall under the supervised machine learning category. The exact place of these algorithms is displayed in the diagram below. Let's assume we have a set of points that belong to two separate classes.

Welcome to another article series! This time, we are discussing XGBoost (Extreme Gradient Boosting) -- The leading and the most preferred machine learning algorithm among data scientists in the 21st century. Most people say XGBoost is a money-making algorithm because it easily outperforms any other algorithms, gives the best possible scores and helps its users to claim luxury cash prizes from data science competitions. The topic we are discussing is broad and important so that we discuss it through a series of articles. It is like a journey, maybe a long journey for newcomers.

This article is based on an in-depth study of the data science efforts in three large, private-sector Indian banks with collective assets exceeding $200 million. The study included onsite observations; semistructured interviews with 57 executives, managers, and data scientists; and the examination of archival records. The five obstacles and the solutions for overcoming them emerged from an inductive analytical process based on the qualitative data. More and more companies are embracing data science as a function and a capability. But many of them have not been able to consistently derive business value from their investments in big data, artificial intelligence, and machine learning.1 Moreover, evidence suggests that the gap is widening between organizations successfully gaining value from data science and those struggling to do so.2

At their core, data scientists have a math and statistics background. Out of this math background, they're creating advanced analytics. Just like their software engineering counterparts, data scientists will have to interact with the business side. This includes understanding the domain enough to make insights. Data scientists are often tasked with analyzing data to help the business, and this requires a level of business acumen. Finally, their results need to be given to the business in an understandable fashion. This requires the ability to verbally and visually communicate complex results and observations in a way that the business can understand and act on them. Thus, it'll be extremely valuable for any aspiring data scientists to learn data mining -- the process where one structures the raw data and formulate or recognize the various patterns in the data through the mathematical and computational algorithms. This helps to generate new information and unlock various insights. Here is a simple list of reasons on why you should study data mining? There is a heavy demand for deep analytical talent at the moment in the tech industry. You can gain a valuable skill if you want to jump into Data Science / Big Data / Predictive Analytics. Given lots of data, you'll be able to discover patterns and models that are valid, useful, unexpected, and understandable. Use some variables to predict unknown or future values of other variables (Predictive). You can activate your knowledge in CS theory, Machine Learning, and Databases. Last but not least, you'll learn a lot about algorithms, computing architectures, data scalability, and automation for handling massive datasets.