Paper Group ANR 310
A review on ranking problems in statistical learning. Cognitive Analysis of 360 degree Surround Photos. Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Multi-Modal Conditional Learning. Visual interpretation of the robustness of Non-Negative Associative Gradient Projection Points over function minimizers in mini-batch …
A review on ranking problems in statistical learning
| Title | A review on ranking problems in statistical learning |
| Authors | Tino Werner |
| Abstract | Ranking problems define a widely spread class of statistical learning problems with many applications, including fraud detection, document ranking, medicine, credit risk screening, image ranking or media memorability. In this article, we systematically describe different types of non-probabilistic supervised ranking problems, i.e., ranking problems that require the prediction of an order of the response variables, and the corresponding loss functions resp. goodness criteria. We discuss the difficulties when trying to optimize those criteria. As for a detailed and comprehensive overview of existing machine learning techniques to solve such ranking problems, we group the suitable techniques into SVM-, tree-, Boosting and Neural Network-type approaches and recapitulate the corresponding optimization problems in a unified notation. We also discuss to which of the ranking problems the respective algorithms are tailored and identify their strengths and limitations. Computational aspects and open research problems are also considered. |
| Tasks | Document Ranking, Fraud Detection |
| Published | 2019-09-06 |
| URL | https://arxiv.org/abs/1909.02998v2 |
| https://arxiv.org/pdf/1909.02998v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-review-on-ranking-problems-in-statistical |
| Repo | |
| Framework | |
Cognitive Analysis of 360 degree Surround Photos
| Title | Cognitive Analysis of 360 degree Surround Photos |
| Authors | Madhawa Vidanapathirana, Lakmal Meegahapola, Indika Perera |
| Abstract | 360 degrees surround photography or photospheres have taken the world by storm as the new media for content creation providing viewers rich, immersive experience compared to conventional photography. With the emergence of Virtual Reality as a mainstream trend, the 360 degrees photography is increasingly important to offer a practical approach to the general public to capture virtual reality ready content from their mobile phones without explicit tool support or knowledge. Even though the amount of 360-degree surround content being uploaded to the Internet continues to grow, there is no proper way to index them or to process them for further information. This is because of the difficulty in image processing the photospheres due to the distorted nature of objects embedded. This challenge lies in the way 360-degree panoramic photospheres are saved. This paper presents a unique, and innovative technique named Photosphere to Cognition Engine (P2CE), which allows cognitive analysis on 360-degree surround photos using existing image cognitive analysis algorithms and APIs designed for conventional photos. We have optimized the system using a wide variety of indoor and outdoor samples and extensive evaluation approaches. On average, P2CE provides up-to 100% growth in accuracy on image cognitive analysis of Photospheres over direct use of conventional non-photosphere based Image Cognition Systems. |
| Tasks | |
| Published | 2019-01-17 |
| URL | http://arxiv.org/abs/1901.05634v1 |
| http://arxiv.org/pdf/1901.05634v1.pdf | |
| PWC | https://paperswithcode.com/paper/cognitive-analysis-of-360-degree-surround |
| Repo | |
| Framework | |
Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Multi-Modal Conditional Learning
| Title | Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Multi-Modal Conditional Learning |
| Authors | Jianwen Xie, Zilong Zheng, Xiaolin Fang, Song-Chun Zhu, Ying Nian Wu |
| Abstract | This paper studies the supervised learning of the conditional distribution of a high-dimensional output given an input, where the output and input may belong to two different modalities, e.g., the output is an photo image and the input is a sketch image. We solve this problem by cooperative training of a fast thinking initializer and slow thinking solver. The initializer generates the output directly by a non-linear transformation of the input as well as a noise vector that accounts for latent variability in the output. The slow thinking solver learns an objective function in the form of a conditional energy function, so that the output can be generated by optimizing the objective function, or more rigorously by sampling from the conditional energy-based model. We propose to learn the two models jointly, where the fast thinking initializer serves to initialize the sampling of the slow thinking solver, and the solver refines the initial output by an iterative algorithm. The solver learns from the difference between the refined output and the observed output, while the initializer learns from how the solver refines its initial output. We demonstrate the effectiveness of the proposed method on various multi-modal conditional learning tasks, e.g., class-to-image generation, image-to-image translation, and image recovery. |
| Tasks | Image Generation, Image-to-Image Translation |
| Published | 2019-02-07 |
| URL | https://arxiv.org/abs/1902.02812v2 |
| https://arxiv.org/pdf/1902.02812v2.pdf | |
| PWC | https://paperswithcode.com/paper/multimodal-conditional-learning-with-fast |
| Repo | |
| Framework | |
Visual interpretation of the robustness of Non-Negative Associative Gradient Projection Points over function minimizers in mini-batch sampled loss functions
| Title | Visual interpretation of the robustness of Non-Negative Associative Gradient Projection Points over function minimizers in mini-batch sampled loss functions |
| Authors | Dominic Kafka, Daniel Wilke |
| Abstract | Mini-batch sub-sampling is likely here to stay, due to growing data demands, memory-limited computational resources such as graphical processing units (GPUs), and the dynamics of on-line learning. Sampling a new mini-batch at every loss evaluation brings a number of benefits, but also one significant drawback: The loss function becomes discontinuous. These discontinuities are generally not problematic when using fixed learning rates or learning rate schedules typical of subgradient methods. However, they hinder attempts to directly minimize the loss function by solving for critical points, since function minimizers find spurious minima induced by discontinuities, while critical points may not even exist. Therefore, finding function minimizers and critical points in stochastic optimization is ineffective. As a result, attention has been given to reducing the effect of these discontinuities by means such as gradient averaging or adaptive and dynamic sampling. This paper offers an alternative paradigm: Recasting the optimization problem to rather find Non-Negative Associated Gradient Projection Points (NN-GPPs). In this paper, we demonstrate the NN-GPP interpretation of gradient information is more robust than critical points or minimizers, being less susceptible to sub-sampling induced variance and eliminating spurious function minimizers. We conduct a visual investigation, where we compare function value and gradient information for a variety of popular activation functions as applied to a simple neural network training problem. Based on the improved description offered by NN-GPPs over minimizers to identify true optima, in particular when using smooth activation functions with high curvature characteristics, we postulate that locating NN-GPPs can contribute significantly to automating neural network training. |
| Tasks | Stochastic Optimization |
| Published | 2019-03-20 |
| URL | http://arxiv.org/abs/1903.08552v1 |
| http://arxiv.org/pdf/1903.08552v1.pdf | |
| PWC | https://paperswithcode.com/paper/visual-interpretation-of-the-robustness-of |
| Repo | |
| Framework | |
Markov Decision Process for MOOC users behavioral inference
| Title | Markov Decision Process for MOOC users behavioral inference |
| Authors | Firas Jarboui, Célya Gruson-daniel, Alain Durmus, Vincent Rocchisani, Sophie-helene Goulet Ebongue, Anneliese Depoux, Wilfried Kirschenmann, Vianney Perchet |
| Abstract | Studies on massive open online courses (MOOCs) users discuss the existence of typical profiles and their impact on the learning process of the students. However defining the typical behaviors as well as classifying the users accordingly is a difficult task. In this paper we suggest two methods to model MOOC users behaviour given their log data. We mold their behavior into a Markov Decision Process framework. We associate the user’s intentions with the MDP reward and argue that this allows us to classify them. |
| Tasks | |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04723v1 |
| https://arxiv.org/pdf/1907.04723v1.pdf | |
| PWC | https://paperswithcode.com/paper/markov-decision-process-for-mooc-users |
| Repo | |
| Framework | |
Unbiased Evaluation of Deep Metric Learning Algorithms
| Title | Unbiased Evaluation of Deep Metric Learning Algorithms |
| Authors | Istvan Fehervari, Avinash Ravichandran, Srikar Appalaraju |
| Abstract | Deep metric learning (DML) is a popular approach for images retrieval, solving verification (same or not) problems and addressing open set classification. Arguably, the most common DML approach is with triplet loss, despite significant advances in the area of DML. Triplet loss suffers from several issues such as collapse of the embeddings, high sensitivity to sampling schemes and more importantly a lack of performance when compared to more modern methods. We attribute this adoption to a lack of fair comparisons between various methods and the difficulty in adopting them for novel problem statements. In this paper, we perform an unbiased comparison of the most popular DML baseline methods under same conditions and more importantly, not obfuscating any hyper parameter tuning or adjustment needed to favor a particular method. We find, that under equal conditions several older methods perform significantly better than previously believed. In fact, our unified implementation of 12 recently introduced DML algorithms achieve state-of-the art performance on CUB200, CAR196, and Stanford Online products datasets which establishes a new set of baselines for future DML research. The codebase and all tuned hyperparameters will be open-sourced for reproducibility and to serve as a source of benchmark. |
| Tasks | Metric Learning |
| Published | 2019-11-28 |
| URL | https://arxiv.org/abs/1911.12528v1 |
| https://arxiv.org/pdf/1911.12528v1.pdf | |
| PWC | https://paperswithcode.com/paper/unbiased-evaluation-of-deep-metric-learning |
| Repo | |
| Framework | |
Imitation Learning from Imperfect Demonstration
| Title | Imitation Learning from Imperfect Demonstration |
| Authors | Yueh-Hua Wu, Nontawat Charoenphakdee, Han Bao, Voot Tangkaratt, Masashi Sugiyama |
| Abstract | Imitation learning (IL) aims to learn an optimal policy from demonstrations. However, such demonstrations are often imperfect since collecting optimal ones is costly. To effectively learn from imperfect demonstrations, we propose a novel approach that utilizes confidence scores, which describe the quality of demonstrations. More specifically, we propose two confidence-based IL methods, namely two-step importance weighting IL (2IWIL) and generative adversarial IL with imperfect demonstration and confidence (IC-GAIL). We show that confidence scores given only to a small portion of sub-optimal demonstrations significantly improve the performance of IL both theoretically and empirically. |
| Tasks | Imitation Learning |
| Published | 2019-01-27 |
| URL | http://arxiv.org/abs/1901.09387v3 |
| http://arxiv.org/pdf/1901.09387v3.pdf | |
| PWC | https://paperswithcode.com/paper/imitation-learning-from-imperfect |
| Repo | |
| Framework | |
Iterative Budgeted Exponential Search
| Title | Iterative Budgeted Exponential Search |
| Authors | Malte Helmert, Tor Lattimore, Levi H. S. Lelis, Laurent Orseau, Nathan R. Sturtevant |
| Abstract | We tackle two long-standing problems related to re-expansions in heuristic search algorithms. For graph search, A* can require $\Omega(2^{n})$ expansions, where $n$ is the number of states within the final $f$ bound. Existing algorithms that address this problem like B and B’ improve this bound to $\Omega(n^2)$. For tree search, IDA* can also require $\Omega(n^2)$ expansions. We describe a new algorithmic framework that iteratively controls an expansion budget and solution cost limit, giving rise to new graph and tree search algorithms for which the number of expansions is $O(n \log C)$, where $C$ is the optimal solution cost. Our experiments show that the new algorithms are robust in scenarios where existing algorithms fail. In the case of tree search, our new algorithms have no overhead over IDA* in scenarios to which IDA* is well suited and can therefore be recommended as a general replacement for IDA*. |
| Tasks | |
| Published | 2019-07-30 |
| URL | https://arxiv.org/abs/1907.13062v1 |
| https://arxiv.org/pdf/1907.13062v1.pdf | |
| PWC | https://paperswithcode.com/paper/iterative-budgeted-exponential-search |
| Repo | |
| Framework | |
Active Learning with Weak Supervision for Cost-Effective Panicle Detection in Cereal Crops
| Title | Active Learning with Weak Supervision for Cost-Effective Panicle Detection in Cereal Crops |
| Authors | Akshay L Chandra, Sai Vikas Desai, Vineeth N Balasubramanian, Seishi Ninomiya, Wei Guo |
| Abstract | Panicle density of cereal crops such as wheat and sorghum is one of the main components for plant breeders and agronomists in understanding the yield of their crops. To phenotype the panicle density effectively, researchers agree there is a significant need for computer vision-based object detection techniques. Especially in recent times, research in deep learning-based object detection shows promising results in various agricultural studies. However, training such systems usually requires a lot of bounding-box labeled data. Since crops vary by both environmental and genetic conditions, acquisition of huge amount of labeled image datasets for each crop is expensive and time-consuming. Thus, to catalyze the widespread usage of automatic object detection for crop phenotyping, a cost-effective method to develop such automated systems is essential. We propose a weak supervision based active learning approach for panicle detection in cereal crops. In our approach, the model constantly interacts with a human annotator by iteratively querying the labels for only the most informative images, as opposed to all images in a dataset. Our query method is specifically designed for cereal crops which usually tend to have panicles with low variance in appearance. Our method reduces labeling costs by intelligently leveraging low-cost weak labels (object centers) for picking the most informative images for which strong labels (bounding boxes) are required. We show promising results on two publicly available cereal crop datasets - Sorghum and Wheat. On Sorghum, 6 variants of our proposed method outperform the best baseline method with more than 55% savings in labeling time. Similarly, on Wheat, 3 variants of our proposed methods outperform the best baseline method with more than 50% of savings in labeling time. |
| Tasks | Active Learning, Object Detection |
| Published | 2019-10-04 |
| URL | https://arxiv.org/abs/1910.01789v2 |
| https://arxiv.org/pdf/1910.01789v2.pdf | |
| PWC | https://paperswithcode.com/paper/active-learning-with-weak-supervision-for |
| Repo | |
| Framework | |
Learning User Preferences via Reinforcement Learning with Spatial Interface Valuing
| Title | Learning User Preferences via Reinforcement Learning with Spatial Interface Valuing |
| Authors | Miguel Alonso Jr |
| Abstract | Interactive Machine Learning is concerned with creating systems that operate in environments alongside humans to achieve a task. A typical use is to extend or amplify the capabilities of a human in cognitive or physical ways, requiring the machine to adapt to the users’ intentions and preferences. Often, this takes the form of a human operator providing some type of feedback to the user, which can be explicit feedback, implicit feedback, or a combination of both. Explicit feedback, such as through a mouse click, carries a high cognitive load. The focus of this study is to extend the current state of the art in interactive machine learning by demonstrating that agents can learn a human user’s behavior and adapt to preferences with a reduced amount of explicit human feedback in a mixed feedback setting. The learning agent perceives a value of its own behavior from hand gestures given via a spatial interface. This feedback mechanism is termed Spatial Interface Valuing. This method is evaluated experimentally in a simulated environment for a grasping task using a robotic arm with variable grip settings. Preliminary results indicate that learning agents using spatial interface valuing can learn a value function mapping spatial gestures to expected future rewards much more quickly as compared to those same agents just receiving explicit feedback, demonstrating that an agent perceiving feedback from a human user via a spatial interface can serve as an effective complement to existing approaches. |
| Tasks | |
| Published | 2019-02-02 |
| URL | http://arxiv.org/abs/1902.00719v1 |
| http://arxiv.org/pdf/1902.00719v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-user-preferences-via-reinforcement |
| Repo | |
| Framework | |
CascadeML: An Automatic Neural Network Architecture Evolution and Training Algorithm for Multi-label Classification
| Title | CascadeML: An Automatic Neural Network Architecture Evolution and Training Algorithm for Multi-label Classification |
| Authors | Arjun Pakrashi, Brian Mac Namee |
| Abstract | Multi-label classification is an approach which allows a datapoint to be labelled with more than one class at the same time. A common but trivial approach is to train individual binary classifiers per label, but the performance can be improved by considering associations within the labels. Like with any machine learning algorithm, hyperparameter tuning is important to train a good multi-label classifier model. The task of selecting the best hyperparameter settings for an algorithm is an optimisation problem. Very limited work has been done on automatic hyperparameter tuning and AutoML in the multi-label domain. This paper attempts to fill this gap by proposing a neural network algorithm, CascadeML, to train multi-label neural network based on cascade neural networks. This method requires minimal or no hyperparameter tuning and also considers pairwise label associations. The cascade algorithm grows the network architecture incrementally in a two phase process as it learns the weights using adaptive first order gradient algorithm, therefore omitting the requirement of preselecting the number of hidden layers, nodes and the learning rate. The method was tested on 10 multi-label datasets and compared with other multi-label classification algorithms. Results show that CascadeML performs very well without hyperparameter tuning. |
| Tasks | AutoML, Multi-Label Classification |
| Published | 2019-04-23 |
| URL | http://arxiv.org/abs/1904.10551v1 |
| http://arxiv.org/pdf/1904.10551v1.pdf | |
| PWC | https://paperswithcode.com/paper/cascademl-an-automatic-neural-network |
| Repo | |
| Framework | |
Datamorphic Testing: A Methodology for Testing AI Applications
| Title | Datamorphic Testing: A Methodology for Testing AI Applications |
| Authors | Hong Zhu, Dongmei Liu, Ian Bayley, Rachel Harrison, Fabio Cuzzolin |
| Abstract | With the rapid growth of the applications of machine learning (ML) and other artificial intelligence (AI) techniques, adequate testing has become a necessity to ensure their quality. This paper identifies the characteristics of AI applications that distinguish them from traditional software, and analyses the main difficulties in applying existing testing methods. Based on this analysis, we propose a new method called datamorphic testing and illustrate the method with an example of testing face recognition applications. We also report an experiment with four real industrial application systems of face recognition to validate the proposed approach. |
| Tasks | Face Recognition |
| Published | 2019-12-10 |
| URL | https://arxiv.org/abs/1912.04900v1 |
| https://arxiv.org/pdf/1912.04900v1.pdf | |
| PWC | https://paperswithcode.com/paper/datamorphic-testing-a-methodology-for-testing |
| Repo | |
| Framework | |
Robust Online Learning for Resource Allocation – Beyond Euclidean Projection and Dynamic Fit
| Title | Robust Online Learning for Resource Allocation – Beyond Euclidean Projection and Dynamic Fit |
| Authors | Ezra Tampubolon, Holger Boche |
| Abstract | Online-learning literature has focused on designing algorithms that ensure sub-linear growth of the cumulative long-term constraint violations. The drawback of this guarantee is that strictly feasible actions may cancel out constraint violations on other time slots. For this reason, we introduce a new performance measure called $\hCFit$, whose particular instance is the cumulative positive part of the constraint violations. We propose a class of non-causal algorithms for online-decision making, which guarantees, in slowly changing environments, sub-linear growth of this quantity despite noisy first-order feedback. Furthermore, we demonstrate by numerical experiments the performance gain of our method relative to the state of art. |
| Tasks | Decision Making |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.09282v1 |
| https://arxiv.org/pdf/1910.09282v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-online-learning-for-resource |
| Repo | |
| Framework | |
AIM 2019 Challenge on Image Demoireing: Dataset and Study
| Title | AIM 2019 Challenge on Image Demoireing: Dataset and Study |
| Authors | Shanxin Yuan, Radu Timofte, Gregory Slabaugh, Ales Leonardis |
| Abstract | This paper introduces a novel dataset, called LCDMoire, which was created for the first-ever image demoireing challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ICCV 2019. The dataset comprises 10,200 synthetically generated image pairs (consisting of an image degraded by moire and a clean ground truth image). In addition to describing the dataset and its creation, this paper also reviews the challenge tracks, competition, and results, the latter summarizing the current state-of-the-art on this dataset. |
| Tasks | |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.02498v1 |
| https://arxiv.org/pdf/1911.02498v1.pdf | |
| PWC | https://paperswithcode.com/paper/aim-2019-challenge-on-image-demoireing |
| Repo | |
| Framework | |
Non-Asymptotic Pure Exploration by Solving Games
| Title | Non-Asymptotic Pure Exploration by Solving Games |
| Authors | Rémy Degenne, Wouter M. Koolen, Pierre Ménard |
| Abstract | Pure exploration (aka active testing) is the fundamental task of sequentially gathering information to answer a query about a stochastic environment. Good algorithms make few mistakes and take few samples. Lower bounds (for multi-armed bandit models with arms in an exponential family) reveal that the sample complexity is determined by the solution to an optimisation problem. The existing state of the art algorithms achieve asymptotic optimality by solving a plug-in estimate of that optimisation problem at each step. We interpret the optimisation problem as an unknown game, and propose sampling rules based on iterative strategies to estimate and converge to its saddle point. We apply no-regret learners to obtain the first finite confidence guarantees that are adapted to the exponential family and which apply to any pure exploration query and bandit structure. Moreover, our algorithms only use a best response oracle instead of fully solving the optimisation problem. |
| Tasks | |
| Published | 2019-06-25 |
| URL | https://arxiv.org/abs/1906.10431v1 |
| https://arxiv.org/pdf/1906.10431v1.pdf | |
| PWC | https://paperswithcode.com/paper/non-asymptotic-pure-exploration-by-solving |
| Repo | |
| Framework | |
