Paper Group ANR 1515
Learning to Forget for Meta-Learning. Cross-Modal Image Fusion Theory Guided by Subjective Visual Attention. Slow Feature Analysis for Human Action Recognition. SALT: Subspace Alignment as an Auxiliary Learning Task for Domain Adaptation. Wyner VAE: Joint and Conditional Generation with Succinct Common Representation Learning. Power Gradient Descen …
Learning to Forget for Meta-Learning
| Title | Learning to Forget for Meta-Learning |
| Authors | Sungyong Baik, Seokil Hong, Kyoung Mu Lee |
| Abstract | Few-shot learning is a challenging problem where the system is required to achieve generalization from only few examples. Meta-learning tackles the problem by learning prior knowledge shared across a distribution of tasks, which is then used to quickly adapt to unseen tasks. Model-agnostic meta-learning (MAML) algorithm formulates prior knowledge as a common initialization across tasks. However, forcibly sharing an initialization brings about conflicts between tasks and thus compromises the quality of the initialization. In this work, by observing that the extent of compromise differs among tasks and between layers of a neural network, we propose a new initialization idea that employs task-dependent layer-wise attenuation, which we call selective forgetting. The proposed attenuation scheme dynamically controls how much of prior knowledge each layer will exploit for a given task. The experimental results demonstrate that the proposed method mitigates the conflicts and provides outstanding performance as a result. We further show that the proposed method, named L2F, can be applied and improve other state-of-the-art MAML-based frameworks, illustrating its generalizability. |
| Tasks | Few-Shot Learning, Meta-Learning |
| Published | 2019-06-13 |
| URL | https://arxiv.org/abs/1906.05895v1 |
| https://arxiv.org/pdf/1906.05895v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-forget-for-meta-learning |
| Repo | |
| Framework | |
Cross-Modal Image Fusion Theory Guided by Subjective Visual Attention
| Title | Cross-Modal Image Fusion Theory Guided by Subjective Visual Attention |
| Authors | Aiqing Fang, Xinbo Zhao, Yanning Zhang |
| Abstract | The human visual perception system has very strong robustness and contextual awareness in a variety of image processing tasks. This robustness and the perception ability of contextual awareness is closely related to the characteristics of multi-task auxiliary learning and subjective attention of the human visual perception system. In order to improve the robustness and contextual awareness of image fusion tasks, we proposed a multi-task auxiliary learning image fusion theory guided by subjective attention. The image fusion theory effectively unifies the subjective task intention and prior knowledge of human brain. In order to achieve our proposed image fusion theory, we first analyze the mechanism of multi-task auxiliary learning, build a multi-task auxiliary learning network. Secondly, based on the human visual attention perception mechanism, we introduce the human visual attention network guided by subjective tasks on the basis of the multi-task auxiliary learning network. The subjective intention is introduced by the subjective attention task model, so that the network can fuse images according to the subjective intention. Finally, in order to verify the superiority of our image fusion theory, we carried out experiments on the combined vision system image data set, and the infrared and visible image data set for experimental verification. The experimental results demonstrate the superiority of our fusion theory over state-of-arts in contextual awareness and robustness. |
| Tasks | Auxiliary Learning |
| Published | 2019-12-23 |
| URL | https://arxiv.org/abs/1912.10718v1 |
| https://arxiv.org/pdf/1912.10718v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-modal-image-fusion-theory-guided-by |
| Repo | |
| Framework | |
Slow Feature Analysis for Human Action Recognition
| Title | Slow Feature Analysis for Human Action Recognition |
| Authors | Zhang Zhang, Dacheng Tao |
| Abstract | Slow Feature Analysis (SFA) extracts slowly varying features from a quickly varying input signal. It has been successfully applied to modeling the visual receptive fields of the cortical neurons. Sufficient experimental results in neuroscience suggest that the temporal slowness principle is a general learning principle in visual perception. In this paper, we introduce the SFA framework to the problem of human action recognition by incorporating the discriminative information with SFA learning and considering the spatial relationship of body parts. In particular, we consider four kinds of SFA learning strategies, including the original unsupervised SFA (U-SFA), the supervised SFA (S-SFA), the discriminative SFA (D-SFA), and the spatial discriminative SFA (SD-SFA), to extract slow feature functions from a large amount of training cuboids which are obtained by random sampling in motion boundaries. Afterward, to represent action sequences, the squared first order temporal derivatives are accumulated over all transformed cuboids into one feature vector, which is termed the Accumulated Squared Derivative (ASD) feature. The ASD feature encodes the statistical distribution of slow features in an action sequence. Finally, a linear support vector machine (SVM) is trained to classify actions represented by ASD features. We conduct extensive experiments, including two sets of control experiments, two sets of large scale experiments on the KTH and Weizmann databases, and two sets of experiments on the CASIA and UT-interaction databases, to demonstrate the effectiveness of SFA for human action recognition. |
| Tasks | Temporal Action Localization |
| Published | 2019-07-15 |
| URL | https://arxiv.org/abs/1907.06670v1 |
| https://arxiv.org/pdf/1907.06670v1.pdf | |
| PWC | https://paperswithcode.com/paper/slow-feature-analysis-for-human-action |
| Repo | |
| Framework | |
SALT: Subspace Alignment as an Auxiliary Learning Task for Domain Adaptation
| Title | SALT: Subspace Alignment as an Auxiliary Learning Task for Domain Adaptation |
| Authors | Kowshik Thopalli, Jayaraman J. Thiagarajan, Rushil Anirudh, Pavan Turaga |
| Abstract | Unsupervised domain adaptation aims to transfer and adapt knowledge learned from a labeled source domain to an unlabeled target domain. Key components of unsupervised domain adaptation include: (a) maximizing performance on the target, and (b) aligning the source and target domains. Traditionally, these tasks have either been considered as separate, or assumed to be implicitly addressed together with high-capacity feature extractors. When considered separately, alignment is usually viewed as a problem of aligning data distributions, either through geometric approaches such as subspace alignment or through distributional alignment such as optimal transport. This paper represents a hybrid approach, where we assume simplified data geometry in the form of subspaces, and consider alignment as an auxiliary task to the primary task of maximizing performance on the source. The alignment is made rather simple by leveraging tractable data geometry in the form of subspaces. We synergistically allow certain parameters derived from the closed-form auxiliary solution, to be affected by gradients from the primary task. The proposed approach represents a unique fusion of geometric and model-based alignment with gradients from a data-driven primary task. Our approach termed SALT, is a simple framework that achieves comparable or sometimes outperforms state-of-the-art on multiple standard benchmarks. |
| Tasks | Auxiliary Learning, Domain Adaptation, Unsupervised Domain Adaptation |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04338v2 |
| https://arxiv.org/pdf/1906.04338v2.pdf | |
| PWC | https://paperswithcode.com/paper/salt-subspace-alignment-as-an-auxiliary |
| Repo | |
| Framework | |
Wyner VAE: Joint and Conditional Generation with Succinct Common Representation Learning
| Title | Wyner VAE: Joint and Conditional Generation with Succinct Common Representation Learning |
| Authors | J. Jon Ryu, Yoojin Choi, Young-Han Kim, Mostafa El-Khamy, Jungwon Lee |
| Abstract | A new variational autoencoder (VAE) model is proposed that learns a succinct common representation of two correlated data variables for conditional and joint generation tasks. The proposed Wyner VAE model is based on two information theoretic problems—distributed simulation and channel synthesis—in which Wyner’s common information arises as the fundamental limit of the succinctness of the common representation. The Wyner VAE decomposes a pair of correlated data variables into their common representation (e.g., a shared concept) and local representations that capture the remaining randomness (e.g., texture and style) in respective data variables by imposing the mutual information between the data variables and the common representation as a regularization term. The utility of the proposed approach is demonstrated through experiments for joint and conditional generation with and without style control using synthetic data and real images. Experimental results show that learning a succinct common representation achieves better generative performance and that the proposed model outperforms existing VAE variants and the variational information bottleneck method. |
| Tasks | Representation Learning |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.10945v1 |
| https://arxiv.org/pdf/1905.10945v1.pdf | |
| PWC | https://paperswithcode.com/paper/wyner-vae-joint-and-conditional-generation |
| Repo | |
| Framework | |
Power Gradient Descent
| Title | Power Gradient Descent |
| Authors | Marco Baiesi |
| Abstract | The development of machine learning is promoting the search for fast and stable minimization algorithms. To this end, we suggest a change in the current gradient descent methods that should speed up the motion in flat regions and slow it down in steep directions of the function to minimize. It is based on a “power gradient”, in which each component of the gradient is replaced by its versus-preserving $H$-th power, with $0<H<1$. We test three modern gradient descent methods fed by such variant and by standard gradients, finding the new version to achieve significantly better performances for the Nesterov accelerated gradient and AMSGrad. We also propose an effective new take on the ADAM algorithm, which includes power gradients with varying $H$. |
| Tasks | |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04787v1 |
| https://arxiv.org/pdf/1906.04787v1.pdf | |
| PWC | https://paperswithcode.com/paper/power-gradient-descent |
| Repo | |
| Framework | |
Hierarchical Auxiliary Learning
| Title | Hierarchical Auxiliary Learning |
| Authors | Jaehoon Cha, Kyeong Soo Kim, Sanghyuk Lee |
| Abstract | Conventional application of convolutional neural networks (CNNs) for image classification and recognition is based on the assumption that all target classes are equal(i.e., no hierarchy) and exclusive of one another (i.e., no overlap). CNN-based image classifiers built on this assumption, therefore, cannot take into account an innate hierarchy among target classes (e.g., cats and dogs in animal image classification) or additional information that can be easily derived from the data (e.g.,numbers larger than five in the recognition of handwritten digits), thereby resulting in scalability issues when the number of target classes is large. Combining two related but slightly different ideas of hierarchical classification and logical learning by auxiliary inputs, we propose a new learning framework called hierarchical auxiliary learning, which not only address the scalability issues with a large number of classes but also could further reduce the classification/recognition errors with a reasonable number of classes. In the hierarchical auxiliary learning, target classes are semantically or non-semantically grouped into superclasses, which turns the original problem of mapping between an image and its target class into a new problem of mapping between a pair of an image and its superclass and the target class. To take the advantage of superclasses, we introduce an auxiliary block into a neural network, which generates auxiliary scores used as additional information for final classification/recognition; in this paper, we add the auxiliary block between the last residual block and the fully-connected output layer of the ResNet. Experimental results demonstrate that the proposed hierarchical auxiliary learning can reduce classification errors up to 0.56, 1.6 and 3.56 percent with MNIST, SVHN and CIFAR-10 datasets, respectively. |
| Tasks | Auxiliary Learning, Image Classification |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.00852v1 |
| https://arxiv.org/pdf/1906.00852v1.pdf | |
| PWC | https://paperswithcode.com/paper/190600852 |
| Repo | |
| Framework | |
Supervised feature selection with orthogonal regression and feature weighting
| Title | Supervised feature selection with orthogonal regression and feature weighting |
| Authors | Xia Wu, Xueyuan Xu, Jianhong Liu, Hailing Wang, Bin Hu, Feiping Nie |
| Abstract | Effective features can improve the performance of a model, which can thus help us understand the characteristics and underlying structure of complex data. Previous feature selection methods usually cannot keep more local structure information. To address the defects previously mentioned, we propose a novel supervised orthogonal least square regression model with feature weighting for feature selection. The optimization problem of the objection function can be solved by employing generalized power iteration (GPI) and augmented Lagrangian multiplier (ALM) methods. Experimental results show that the proposed method can more effectively reduce the feature dimensionality and obtain better classification results than traditional feature selection methods. The convergence of our iterative method is proved as well. Consequently, the effectiveness and superiority of the proposed method are verified both theoretically and experimentally. |
| Tasks | Feature Selection |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.03787v1 |
| https://arxiv.org/pdf/1910.03787v1.pdf | |
| PWC | https://paperswithcode.com/paper/supervised-feature-selection-with-orthogonal |
| Repo | |
| Framework | |
Image Cropping with Composition and Saliency Aware Aesthetic Score Map
| Title | Image Cropping with Composition and Saliency Aware Aesthetic Score Map |
| Authors | Yi Tu, Li Niu, Weijie Zhao, Dawei Cheng, Liqing Zhang |
| Abstract | Aesthetic image cropping is a practical but challenging task which aims at finding the best crops with the highest aesthetic quality in an image. Recently, many deep learning methods have been proposed to address this problem, but they did not reveal the intrinsic mechanism of aesthetic evaluation. In this paper, we propose an interpretable image cropping model to unveil the mystery. For each image, we use a fully convolutional network to produce an aesthetic score map, which is shared among all candidate crops during crop-level aesthetic evaluation. Then, we require the aesthetic score map to be both composition-aware and saliency-aware. In particular, the same region is assigned with different aesthetic scores based on its relative positions in different crops. Moreover, a visually salient region is supposed to have more sensitive aesthetic scores so that our network can learn to place salient objects at more proper positions. Such an aesthetic score map can be used to localize aesthetically important regions in an image, which sheds light on the composition rules learned by our model. We show the competitive performance of our model in the image cropping task on several benchmark datasets, and also demonstrate its generality in real-world applications. |
| Tasks | Image Cropping |
| Published | 2019-11-24 |
| URL | https://arxiv.org/abs/1911.10492v1 |
| https://arxiv.org/pdf/1911.10492v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-cropping-with-composition-and-saliency |
| Repo | |
| Framework | |
Norm-based generalisation bounds for multi-class convolutional neural networks
| Title | Norm-based generalisation bounds for multi-class convolutional neural networks |
| Authors | Antoine Ledent, Yunwen Lei, Marius Kloft |
| Abstract | We show generalisation error bounds for deep learning with two main improvements over the state of the art. (1) Our bounds have no explicit dependence on the number of classes except for logarithmic factors. This holds even when formulating the bounds in terms of the $L^2$-norm of the weight matrices, where previous bounds exhibit at least a square-root dependence on the number of classes. (2) We adapt the classic Rademacher analysis of DNNs to incorporate weight sharing—a task of fundamental theoretical importance which was previously attempted only under very restrictive assumptions. In our results, each convolutional filter contributes only once to the bound, regardless of how many times it is applied. Further improvements exploiting pooling and sparse connections are provided. The presented bounds scale as the norms of the parameter matrices, rather than the number of parameters. In particular, contrary to bounds based on parameter counting, they are asymptotically tight (up to log factors) when the weights approach initialisation, making them suitable as a basic ingredient in bounds sensitive to the optimisation procedure. We also show how to adapt the recent technique of loss function augmentation to our situation to replace spectral norms by empirical analogues whilst maintaining the advantages of our approach. |
| Tasks | |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12430v3 |
| https://arxiv.org/pdf/1905.12430v3.pdf | |
| PWC | https://paperswithcode.com/paper/improved-generalisation-bounds-for-deep |
| Repo | |
| Framework | |
Deep Minimax Probability Machine
| Title | Deep Minimax Probability Machine |
| Authors | Lirong He, Ziyi Guo, Kaizhu Huang, Zenglin Xu |
| Abstract | Deep neural networks enjoy a powerful representation and have proven effective in a number of applications. However, recent advances show that deep neural networks are vulnerable to adversarial attacks incurred by the so-called adversarial examples. Although the adversarial example is only slightly different from the input sample, the neural network classifies it as the wrong class. In order to alleviate this problem, we propose the Deep Minimax Probability Machine (DeepMPM), which applies MPM to deep neural networks in an end-to-end fashion. In a worst-case scenario, MPM tries to minimize an upper bound of misclassification probabilities, considering the global information (i.e., mean and covariance information of each class). DeepMPM can be more robust since it learns the worst-case bound on the probability of misclassification of future data. Experiments on two real-world datasets can achieve comparable classification performance with CNN, while can be more robust on adversarial attacks. |
| Tasks | |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.08723v1 |
| https://arxiv.org/pdf/1911.08723v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-minimax-probability-machine |
| Repo | |
| Framework | |
Model selection for deep audio source separation via clustering analysis
| Title | Model selection for deep audio source separation via clustering analysis |
| Authors | Alisa Liu, Prem Seetharaman, Bryan Pardo |
| Abstract | Audio source separation is the process of separating a mixture (e.g. a pop band recording) into isolated sounds from individual sources (e.g. just the lead vocals). Deep learning models are the state-of-the-art in source separation, given that the mixture to be separated is similar to the mixtures the deep model was trained on. This requires the end user to know enough about each model’s training to select the correct model for a given audio mixture. In this work, we automate selection of the appropriate model for an audio mixture. We present a confidence measure that does not require ground truth to estimate separation quality, given a deep model and audio mixture. We use this confidence measure to automatically select the model output with the best predicted separation quality. We compare our confidence-based ensemble approach to using individual models with no selection, to an oracle that always selects the best model and to a random model selector. Results show our confidence-based ensemble significantly outperforms the random ensemble over general mixtures and approaches oracle performance for music mixtures. |
| Tasks | Model Selection |
| Published | 2019-10-23 |
| URL | https://arxiv.org/abs/1910.12626v1 |
| https://arxiv.org/pdf/1910.12626v1.pdf | |
| PWC | https://paperswithcode.com/paper/model-selection-for-deep-audio-source |
| Repo | |
| Framework | |
FairSearch: A Tool For Fairness in Ranked Search Results
| Title | FairSearch: A Tool For Fairness in Ranked Search Results |
| Authors | Meike Zehlike, Tom Sühr, Carlos Castillo, Ivan Kitanovski |
| Abstract | Ranked search results and recommendations have become the main mechanism by which we find content, products, places, and people online. With hiring, selecting, purchasing, and dating being increasingly mediated by algorithms, rankings may determine career and business opportunities, educational placement, access to benefits, and even social and reproductive success. It is therefore of societal and ethical importance to ask whether search results can demote, marginalize, or exclude individuals of unprivileged groups or promote products with undesired features. In this paper we present FairSearch, the first fair open source search API to provide fairness notions in ranked search results. We implement two algorithms from the fair ranking literature, namely FAIR (Zehlike et al., 2017) and DELTR (Zehlike and Castillo, 2018) and provide them as stand-alone libraries in Python and Java. Additionally we implement interfaces to Elasticsearch for both algorithms, that use the aforementioned Java libraries and are then provided as Elasticsearch plugins. Elasticsearch is a well-known search engine API based on Apache Lucene. With our plugins we enable search engine developers who wish to ensure fair search results of different styles to easily integrate DELTR and FAIR into their existing Elasticsearch environment. |
| Tasks | |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.13134v1 |
| https://arxiv.org/pdf/1905.13134v1.pdf | |
| PWC | https://paperswithcode.com/paper/fairsearch-a-tool-for-fairness-in-ranked |
| Repo | |
| Framework | |
A tale of two toolkits, report the first: benchmarking time series classification algorithms for correctness and efficiency
| Title | A tale of two toolkits, report the first: benchmarking time series classification algorithms for correctness and efficiency |
| Authors | Anthony Bagnall, Franz Király, Markus Löning, Matthew Middlehurst, George Oastler |
| Abstract | sktime is an open source, Python based, sklearn compatible toolkit for time series analysis developed by researchers at the University of East Anglia (UEA), University College London and the Alan Turing Institute. A key initial goal for sktime was to provide time series classification functionality equivalent to that available in a related java package, tsml, also developed at UEA. We describe the implementation of six such classifiers in sktime and compare them to their tsml equivalents. We demonstrate correctness through equivalence of accuracy on a range of standard test problems and compare the build time of the different implementations. We find that there is significant difference in accuracy on only one of the six algorithms we look at (Proximity Forest). This difference is causing us some pain in debugging. We found a much wider range of difference in efficiency. Again, this was not unexpected, but it does highlight ways both toolkits could be improved. |
| Tasks | Time Series, Time Series Analysis, Time Series Classification |
| Published | 2019-09-12 |
| URL | https://arxiv.org/abs/1909.05738v3 |
| https://arxiv.org/pdf/1909.05738v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-tale-of-two-toolkits-report-the-first |
| Repo | |
| Framework | |
Photometric light curves classification with machine learning
| Title | Photometric light curves classification with machine learning |
| Authors | Tatiana Gabruseva, Sergey Zlobin, Peter Wang |
| Abstract | The Large Synoptic Survey Telescope will complete its survey in 2022 and produce terabytes of imaging data each night. To work with this massive onset of data, automated algorithms to classify astronomical light curves are crucial. Here, we present a method for automated classification of photometric light curves for a range of astronomical objects. Our approach is based on the gradient boosting of decision trees, feature extraction and selection, and augmentation. The solution was developed in the context of The Photometric LSST Astronomical Time Series Classification Challenge (PLAsTiCC) and achieved one of the top results in the challenge. |
| Tasks | Time Series, Time Series Classification |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.05032v1 |
| https://arxiv.org/pdf/1909.05032v1.pdf | |
| PWC | https://paperswithcode.com/paper/photometric-light-curves-classification-with |
| Repo | |
| Framework | |
