Paper Group ANR 150
Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond. Towards Precise Intra-camera Supervised Person Re-identification. Label Noise Types and Their Effects on Deep Learning. Person Re-identification by Contour Sketch under Moderate Clothing Change. Convolutional Neural Networks based Focal Loss for Class Imbalance Probl …
Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond
| Title | Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond |
| Authors | Yu-Jhe Li, Yun-Chun Chen, Yen-Yu Lin, Yu-Chiang Frank Wang |
| Abstract | Person re-identification (re-ID) aims at matching images of the same person across camera views. Due to varying distances between cameras and persons of interest, resolution mismatch can be expected, which would degrade re-ID performance in real-world scenarios. To overcome this problem, we propose a novel generative adversarial network to address cross-resolution person re-ID, allowing query images with varying resolutions. By advancing adversarial learning techniques, our proposed model learns resolution-invariant image representations while being able to recover the missing details in low-resolution input images. The resulting features can be jointly applied for improving re-ID performance due to preserving resolution invariance and recovering re-ID oriented discriminative details. Extensive experimental results on five standard person re-ID benchmarks confirm the effectiveness of our method and the superiority over the state-of-the-art approaches, especially when the input resolutions are not seen during training. Furthermore, the experimental results on two vehicle re-ID benchmarks also confirm the generalization of our model on cross-resolution visual tasks. The extensions of semi-supervised settings further support the use of our proposed approach to real-world scenarios and applications. |
| Tasks | Person Re-Identification |
| Published | 2020-02-19 |
| URL | https://arxiv.org/abs/2002.09274v1 |
| https://arxiv.org/pdf/2002.09274v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-resolution-adversarial-dual-network-for |
| Repo | |
| Framework | |
Towards Precise Intra-camera Supervised Person Re-identification
| Title | Towards Precise Intra-camera Supervised Person Re-identification |
| Authors | Menglin Wang, Baisheng Lai, Haokun Chen, Jianqiang Huang, Xiaojin Gong, Xian-Sheng Hua |
| Abstract | Intra-camera supervision (ICS) for person re-identification (Re-ID) assumes that identity labels are independently annotated within each camera view and no inter-camera identity association is labeled. It is a new setting proposed recently to reduce the burden of annotation while expect to maintain desirable Re-ID performance. However, the lack of inter-camera labels makes the ICS Re-ID problem much more challenging than the fully supervised counterpart. By investigating the characteristics of ICS, this paper proposes camera-specific non-parametric classifiers, together with a hybrid mining quintuplet loss, to perform intra-camera learning. Then, an inter-camera learning module consisting of a graph-based ID association step and a Re-ID model updating step is conducted. Extensive experiments on three large-scale Re-ID datasets show that our approach outperforms all existing ICS works by a great margin. Our approach performs even comparable to state-of-the-art fully supervised methods in two of the datasets. |
| Tasks | Person Re-Identification |
| Published | 2020-02-12 |
| URL | https://arxiv.org/abs/2002.04932v1 |
| https://arxiv.org/pdf/2002.04932v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-precise-intra-camera-supervised |
| Repo | |
| Framework | |
Label Noise Types and Their Effects on Deep Learning
| Title | Label Noise Types and Their Effects on Deep Learning |
| Authors | Görkem Algan, İlkay Ulusoy |
| Abstract | The recent success of deep learning is mostly due to the availability of big datasets with clean annotations. However, gathering a cleanly annotated dataset is not always feasible due to practical challenges. As a result, label noise is a common problem in datasets, and numerous methods to train deep neural networks in the presence of noisy labels are proposed in the literature. These methods commonly use benchmark datasets with synthetic label noise on the training set. However, there are multiple types of label noise, and each of them has its own characteristic impact on learning. Since each work generates a different kind of label noise, it is problematic to test and compare those algorithms in the literature fairly. In this work, we provide a detailed analysis of the effects of different kinds of label noise on learning. Moreover, we propose a generic framework to generate feature-dependent label noise, which we show to be the most challenging case for learning. Our proposed method aims to emphasize similarities among data instances by sparsely distributing them in the feature domain. By this approach, samples that are more likely to be mislabeled are detected from their softmax probabilities, and their labels are flipped to the corresponding class. The proposed method can be applied to any clean dataset to synthesize feature-dependent noisy labels. For the ease of other researchers to test their algorithms with noisy labels, we share corrupted labels for the most commonly used benchmark datasets. Our code and generated noisy synthetic labels are available online. |
| Tasks | |
| Published | 2020-03-23 |
| URL | https://arxiv.org/abs/2003.10471v1 |
| https://arxiv.org/pdf/2003.10471v1.pdf | |
| PWC | https://paperswithcode.com/paper/label-noise-types-and-their-effects-on-deep |
| Repo | |
| Framework | |
Person Re-identification by Contour Sketch under Moderate Clothing Change
| Title | Person Re-identification by Contour Sketch under Moderate Clothing Change |
| Authors | Qize Yang, Ancong Wu, Wei-Shi Zheng |
| Abstract | Person re-identification (re-id), the process of matching pedestrian images across different camera views, is an important task in visual surveillance. Substantial development of re-id has recently been observed, and the majority of existing models are largely dependent on color appearance and assume that pedestrians do not change their clothes across camera views. This limitation, however, can be an issue for re-id when tracking a person at different places and at different time if that person (e.g., a criminal suspect) changes his/her clothes, causing most existing methods to fail, since they are heavily relying on color appearance and thus they are inclined to match a person to another person wearing similar clothes. In this work, we call the person re-id under clothing change the “cross-clothes person re-id”. In particular, we consider the case when a person only changes his clothes moderately as a first attempt at solving this problem based on visible light images; that is we assume that a person wears clothes of a similar thickness, and thus the shape of a person would not change significantly when the weather does not change substantially within a short period of time. We perform cross-clothes person re-id based on a contour sketch of person image to take advantage of the shape of the human body instead of color information for extracting features that are robust to moderate clothing change. Due to the lack of a large-scale dataset for cross-clothes person re-id, we contribute a new dataset that consists of 33698 images from 221 identities. Our experiments illustrate the challenges of cross-clothes person re-id and demonstrate the effectiveness of our proposed method. |
| Tasks | Person Re-Identification |
| Published | 2020-02-06 |
| URL | https://arxiv.org/abs/2002.02295v1 |
| https://arxiv.org/pdf/2002.02295v1.pdf | |
| PWC | https://paperswithcode.com/paper/person-re-identification-by-contour-sketch |
| Repo | |
| Framework | |
Convolutional Neural Networks based Focal Loss for Class Imbalance Problem: A Case Study of Canine Red Blood Cells Morphology Classification
| Title | Convolutional Neural Networks based Focal Loss for Class Imbalance Problem: A Case Study of Canine Red Blood Cells Morphology Classification |
| Authors | Kitsuchart Pasupa, Supawit Vatathanavaro, Suchat Tungjitnob |
| Abstract | Morphologies of red blood cells are normally interpreted by a pathologist. It is time-consuming and laborious. Furthermore, a misclassified red blood cell morphology will lead to false disease diagnosis and improper treatment. Thus, a decent pathologist must truly be an expert in classifying red blood cell morphology. In the past decade, many approaches have been proposed for classifying human red blood cell morphology. However, those approaches have not addressed the class imbalance problem in classification. A class imbalance problem—a problem where the numbers of samples in classes are very different—is one of the problems that can lead to a biased model towards the majority class. Due to the rarity of every type of abnormal blood cell morphology, the data from the collection process are usually imbalanced. In this study, we aimed to solve this problem specifically for classification of dog red blood cell morphology by using a Convolutional Neural Network (CNN)—a well-known deep learning technique—in conjunction with a focal loss function, adept at handling class imbalance problem. The proposed technique was conducted on a well-designed framework: two different CNNs were used to verify the effectiveness of the focal loss function and the optimal hyper-parameters were determined by 5-fold cross-validation. The experimental results show that both CNNs models augmented with the focal loss function achieved higher $F_{1}$-scores, compared to the models augmented with a conventional cross-entropy loss function that does not address class imbalance problem. In other words, the focal loss function truly enabled the CNNs models to be less biased towards the majority class than the cross-entropy did in the classification task of imbalanced dog red blood cell data. |
| Tasks | |
| Published | 2020-01-10 |
| URL | https://arxiv.org/abs/2001.03329v1 |
| https://arxiv.org/pdf/2001.03329v1.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-neural-networks-based-focal |
| Repo | |
| Framework | |
Relaxed Scheduling for Scalable Belief Propagation
| Title | Relaxed Scheduling for Scalable Belief Propagation |
| Authors | Vitaly Aksenov, Dan Alistarh, Janne H. Korhonen |
| Abstract | The ability to leverage large-scale hardware parallelism has been one of the key enablers of the accelerated recent progress in machine learning. Consequently, there has been considerable effort invested into developing efficient parallel variants of classic machine learning algorithms. However, despite the wealth of knowledge on parallelization, some classic machine learning algorithms often prove hard to parallelize efficiently while maintaining convergence. In this paper, we focus on efficient parallel algorithms for the key machine learning task of inference on graphical models, in particular on the fundamental belief propagation algorithm. We address the challenge of efficiently parallelizing this classic paradigm by showing how to leverage scalable relaxed schedulers in this context. We present an extensive empirical study, showing that our approach outperforms previous parallel belief propagation implementations both in terms of scalability and in terms of wall-clock convergence time, on a range of practical applications. |
| Tasks | |
| Published | 2020-02-25 |
| URL | https://arxiv.org/abs/2002.11505v1 |
| https://arxiv.org/pdf/2002.11505v1.pdf | |
| PWC | https://paperswithcode.com/paper/relaxed-scheduling-for-scalable-belief |
| Repo | |
| Framework | |
Gödel’s Sentence Is An Adversarial Example But Unsolvable
| Title | Gödel’s Sentence Is An Adversarial Example But Unsolvable |
| Authors | Xiaodong Qi, Lansheng Han |
| Abstract | In recent years, different types of adversarial examples from different fields have emerged endlessly, including purely natural ones without perturbations. A variety of defenses are proposed and then broken quickly. Two fundamental questions need to be asked: What’s the reason for the existence of adversarial examples and are adversarial examples unsolvable? In this paper, we will show the reason for the existence of adversarial examples is there are non-isomorphic natural explanations that can all explain data set. Specifically, for two natural explanations of being true and provable, G"odel’s sentence is an adversarial example but ineliminable. It can’t be solved by the re-accumulation of data set or the re-improvement of learning algorithm. Finally, from the perspective of computability, we will prove the incomputability for adversarial examples, which are unrecognizable. |
| Tasks | |
| Published | 2020-02-25 |
| URL | https://arxiv.org/abs/2002.10703v1 |
| https://arxiv.org/pdf/2002.10703v1.pdf | |
| PWC | https://paperswithcode.com/paper/godels-sentence-is-an-adversarial-example-but |
| Repo | |
| Framework | |
List-Decodable Subspace Recovery via Sum-of-Squares
| Title | List-Decodable Subspace Recovery via Sum-of-Squares |
| Authors | Ainesh Bakshi, Pravesh Kothari |
| Abstract | We give the first efficient algorithm for the problem of list-decodable subspace recovery. Our algorithm takes input $n$ samples $\alpha n$ ($\alpha\ll 1/2$) are generated i.i.d. from Gaussian distribution $\mathcal{N}(0,\Sigma_*)$ on $\mathbb{R}^d$ with covariance $\Sigma_*$ of rank $r$ and the rest are arbitrary, potentially adversarial outliers. It outputs a list of $O(1/\alpha)$ projection matrices guaranteed to contain a projection matrix $\Pi$ such that $\Pi-\Pi_*_F^2 = \kappa^4 \log (r) \tilde{O}(1/\alpha^2)$, where $\tilde{O}$ hides polylogarithmic factors in $1/\alpha$. Here, $\Pi_*$ is the projection matrix to the range space of $\Sigma_*$. The algorithm needs $n=d^{\log (r \kappa) \tilde{O}(1/\alpha^2)}$ samples and runs in time $n^{\log (r \kappa) \tilde{O}(1/\alpha^4)}$ time where $\kappa$ is the ratio of the largest to smallest non-zero eigenvalues of $\Sigma_*$. Our algorithm builds on the recently developed framework for list-decodable learning via the sum-of-squares (SoS) method [KKK’19, RY’20] with some key technical and conceptual advancements. Our key conceptual contribution involves showing a (SoS “certified”) lower bound on the eigenvalues of covariances of arbitrary small subsamples of an i.i.d. sample of a certifiably anti-concentrated distribution. One of our key technical contributions gives a new method that allows error reduction “within SoS” with only a logarithmic cost in the exponent in the running time (in contrast to polynomial cost in [KKK’19, RY’20]. In a concurrent and independent work, Raghavendra and Yau proved related results for list-decodable subspace recovery [RY’20]. |
| Tasks | |
| Published | 2020-02-12 |
| URL | https://arxiv.org/abs/2002.05139v1 |
| https://arxiv.org/pdf/2002.05139v1.pdf | |
| PWC | https://paperswithcode.com/paper/list-decodable-subspace-recovery-via-sum-of |
| Repo | |
| Framework | |
An Active Learning Framework for Constructing High-fidelity Mobility Maps
| Title | An Active Learning Framework for Constructing High-fidelity Mobility Maps |
| Authors | Gary R. Marple, David Gorsich, Paramsothy Jayakumar, Shravan Veerapaneni |
| Abstract | A mobility map, which provides maximum achievable speed on a given terrain, is essential for path planning of autonomous ground vehicles in off-road settings. While physics-based simulations play a central role in creating next-generation, high-fidelity mobility maps, they are cumbersome and expensive. For instance, a typical simulation can take weeks to run on a supercomputer and each map requires thousands of such simulations. Recent work at the U.S. Army CCDC Ground Vehicle Systems Center has shown that trained machine learning classifiers can greatly improve the efficiency of this process. However, deciding which simulations to run in order to train the classifier efficiently is still an open problem. According to PAC learning theory, data that can be separated by a classifier is expected to require $\mathcal{O}(1/\epsilon)$ randomly selected points (simulations) to train the classifier with error less than $\epsilon$. In this paper, building on existing algorithms, we introduce an active learning paradigm that substantially reduces the number of simulations needed to train a machine learning classifier without sacrificing accuracy. Experimental results suggest that our sampling algorithm can train a neural network, with higher accuracy, using less than half the number of simulations when compared to random sampling. |
| Tasks | Active Learning |
| Published | 2020-03-07 |
| URL | https://arxiv.org/abs/2003.03517v1 |
| https://arxiv.org/pdf/2003.03517v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-active-learning-framework-for-constructing |
| Repo | |
| Framework | |
Neuro-evolutionary Frameworks for Generalized Learning Agents
| Title | Neuro-evolutionary Frameworks for Generalized Learning Agents |
| Authors | Thommen George Karimpanal |
| Abstract | The recent successes of deep learning and deep reinforcement learning have firmly established their statuses as state-of-the-art artificial learning techniques. However, longstanding drawbacks of these approaches, such as their poor sample efficiencies and limited generalization capabilities point to a need for re-thinking the way such systems are designed and deployed. In this paper, we emphasize how the use of these learning systems, in conjunction with a specific variation of evolutionary algorithms could lead to the emergence of unique characteristics such as the automated acquisition of a variety of desirable behaviors and useful sets of behavior priors. This could pave the way for learning to occur in a generalized and continual manner, with minimal interactions with the environment. We discuss the anticipated improvements from such neuro-evolutionary frameworks, along with the associated challenges, as well as its potential for application to a number of research areas. |
| Tasks | |
| Published | 2020-02-04 |
| URL | https://arxiv.org/abs/2002.01088v1 |
| https://arxiv.org/pdf/2002.01088v1.pdf | |
| PWC | https://paperswithcode.com/paper/neuro-evolutionary-frameworks-for-generalized |
| Repo | |
| Framework | |
Explainable Active Learning (XAL): An Empirical Study of How Local Explanations Impact Annotator Experience
| Title | Explainable Active Learning (XAL): An Empirical Study of How Local Explanations Impact Annotator Experience |
| Authors | Bhavya Ghai, Q. Vera Liao, Yunfeng Zhang, Rachel Bellamy, Klaus Mueller |
| Abstract | Active Learning (AL) is a human-in-the-loop Machine Learning paradigm favored for its ability to learn with fewer labeled instances, but the model’s states and progress remain opaque to the annotators. Meanwhile, many recognize the benefits of model transparency for people interacting with ML models, as reflected by the surge of explainable AI (XAI) as a research field. However, explaining an evolving model introduces many open questions regarding its impact on the annotation quality and the annotator’s experience. In this paper, we propose a novel paradigm of explainable active learning (XAL), by explaining the learning algorithm’s prediction for the instance it wants to learn from and soliciting feedback from the annotator. We conduct an empirical study comparing the model learning outcome, human feedback content and the annotator experience with XAL, to that of traditional AL and coactive learning (providing the model’s prediction without the explanation). Our study reveals benefits–supporting trust calibration and enabling additional forms of human feedback, and potential drawbacks–anchoring effect and frustration from transparent model limitations–of providing local explanations in AL. We conclude by suggesting directions for developing explanations that better support annotator experience in AL and interactive ML settings. |
| Tasks | Active Learning, Calibration |
| Published | 2020-01-24 |
| URL | https://arxiv.org/abs/2001.09219v2 |
| https://arxiv.org/pdf/2001.09219v2.pdf | |
| PWC | https://paperswithcode.com/paper/explainable-active-learning-xal-an-empirical |
| Repo | |
| Framework | |
Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures
| Title | Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures |
| Authors | Jatin Chauhan, Deepak Nathani, Manohar Kaul |
| Abstract | We propose to study the problem of few shot graph classification in graph neural networks (GNNs) to recognize unseen classes, given limited labeled graph examples. Despite several interesting GNN variants being proposed recently for node and graph classification tasks, when faced with scarce labeled examples in the few shot setting, these GNNs exhibit significant loss in classification performance. Here, we present an approach where a probability measure is assigned to each graph based on the spectrum of the graphs normalized Laplacian. This enables us to accordingly cluster the graph base labels associated with each graph into super classes, where the Lp Wasserstein distance serves as our underlying distance metric. Subsequently, a super graph constructed based on the super classes is then fed to our proposed GNN framework which exploits the latent inter class relationships made explicit by the super graph to achieve better class label separation among the graphs. We conduct exhaustive empirical evaluations of our proposed method and show that it outperforms both the adaptation of state of the art graph classification methods to few shot scenario and our naive baseline GNNs. Additionally, we also extend and study the behavior of our method to semi supervised and active learning scenarios. |
| Tasks | Active Learning, Few-Shot Learning, Graph Classification |
| Published | 2020-02-27 |
| URL | https://arxiv.org/abs/2002.12815v1 |
| https://arxiv.org/pdf/2002.12815v1.pdf | |
| PWC | https://paperswithcode.com/paper/few-shot-learning-on-graphs-via-super-classes-1 |
| Repo | |
| Framework | |
Combining Federated and Active Learning for Communication-efficient Distributed Failure Prediction in Aeronautics
| Title | Combining Federated and Active Learning for Communication-efficient Distributed Failure Prediction in Aeronautics |
| Authors | Nicolas Aussel, Sophie Chabridon, Yohan Petetin |
| Abstract | Machine Learning has proven useful in the recent years as a way to achieve failure prediction for industrial systems. However, the high computational resources necessary to run learning algorithms are an obstacle to its widespread application. The sub-field of Distributed Learning offers a solution to this problem by enabling the use of remote resources but at the expense of introducing communication costs in the application that are not always acceptable. In this paper, we propose a distributed learning approach able to optimize the use of computational and communication resources to achieve excellent learning model performances through a centralized architecture. To achieve this, we present a new centralized distributed learning algorithm that relies on the learning paradigms of Active Learning and Federated Learning to offer a communication-efficient method that offers guarantees of model precision on both the clients and the central server. We evaluate this method on a public benchmark and show that its performances in terms of precision are very close to state-of-the-art performance level of non-distributed learning despite additional constraints. |
| Tasks | Active Learning |
| Published | 2020-01-21 |
| URL | https://arxiv.org/abs/2001.07504v1 |
| https://arxiv.org/pdf/2001.07504v1.pdf | |
| PWC | https://paperswithcode.com/paper/combining-federated-and-active-learning-for |
| Repo | |
| Framework | |
Dynamic Experience Replay
| Title | Dynamic Experience Replay |
| Authors | Jieliang Luo, Hui Li |
| Abstract | We present a novel technique called Dynamic Experience Replay (DER) that allows Reinforcement Learning (RL) algorithms to use experience replay samples not only from human demonstrations but also successful transitions generated by RL agents during training and therefore improve training efficiency. It can be combined with an arbitrary off-policy RL algorithm, such as DDPG or DQN, and their distributed versions. We build upon Ape-X DDPG and demonstrate our approach on robotic tight-fitting joint assembly tasks, based on force/torque and Cartesian pose observations. In particular, we run experiments on two different tasks: peg-in-hole and lap-joint. In each case, we compare different replay buffer structures and how DER affects them. Our ablation studies show that Dynamic Experience Replay is a crucial ingredient that either largely shortens the training time in these challenging environments or solves the tasks that the vanilla Ape-X DDPG cannot solve. We also show that our policies learned purely in simulation can be deployed successfully on the real robot. The video presenting our experiments is available at https://sites.google.com/site/dynamicexperiencereplay |
| Tasks | |
| Published | 2020-03-04 |
| URL | https://arxiv.org/abs/2003.02372v1 |
| https://arxiv.org/pdf/2003.02372v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-experience-replay |
| Repo | |
| Framework | |
A Support Detection and Root Finding Approach for Learning High-dimensional Generalized Linear Models
| Title | A Support Detection and Root Finding Approach for Learning High-dimensional Generalized Linear Models |
| Authors | Jian Huang, Yuling Jiao, Lican Kang, Jin Liu, Yanyan Liu, Xiliang Lu |
| Abstract | Feature selection is important for modeling high-dimensional data, where the number of variables can be much larger than the sample size. In this paper, we develop a support detection and root finding procedure to learn the high dimensional sparse generalized linear models and denote this method by GSDAR. Based on the KKT condition for $\ell_0$-penalized maximum likelihood estimations, GSDAR generates a sequence of estimators iteratively. Under some restricted invertibility conditions on the maximum likelihood function and sparsity assumption on the target coefficients, the errors of the proposed estimate decays exponentially to the optimal order. Moreover, the oracle estimator can be recovered if the target signal is stronger than the detectable level. We conduct simulations and real data analysis to illustrate the advantages of our proposed method over several existing methods, including Lasso and MCP. |
| Tasks | Feature Selection |
| Published | 2020-01-16 |
| URL | https://arxiv.org/abs/2001.05819v1 |
| https://arxiv.org/pdf/2001.05819v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-support-detection-and-root-finding-approach |
| Repo | |
| Framework | |
