Paper Group ANR 1562
Estimating Treatment Effect under Additive Hazards Models with High-dimensional Covariates. Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data. Reciprocal Translation between SAR and Optical Remote Sensing Images with Cascaded-Residual Adversarial Networks. MSD: Multi-Self-Distillation Learning …
Estimating Treatment Effect under Additive Hazards Models with High-dimensional Covariates
| Title | Estimating Treatment Effect under Additive Hazards Models with High-dimensional Covariates |
| Authors | Jue Hou, Jelena Bradic, Ronghui Xu |
| Abstract | Estimating causal effects for survival outcomes in the high-dimensional setting is an extremely important topic for many biomedical applications as well as areas of social sciences. We propose a new orthogonal score method for treatment effect estimation and inference that results in asymptotically valid confidence intervals assuming only good estimation properties of the hazard outcome model and the conditional probability of treatment. This guarantee allows us to provide valid inference for the conditional treatment effect under the high-dimensional additive hazards model under considerably more generality than existing approaches. In addition, we develop a new Hazards Difference (HDi), estimator. We showcase that our approach has double-robustness properties in high dimensions: with cross-fitting, the HDi estimate is consistent under a wide variety of treatment assignment models; the HDi estimate is also consistent when the hazards model is misspecified and instead the true data generating mechanism follows a partially linear additive hazards model. We further develop a novel sparsity doubly robust result, where either the outcome or the treatment model can be a fully dense high-dimensional model. We apply our methods to study the treatment effect of radical prostatectomy versus conservative management for prostate cancer patients using the SEER-Medicare Linked Data. |
| Tasks | |
| Published | 2019-06-29 |
| URL | https://arxiv.org/abs/1907.00287v1 |
| https://arxiv.org/pdf/1907.00287v1.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-treatment-effect-under-additive |
| Repo | |
| Framework | |
Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data
| Title | Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data |
| Authors | Yerbolat Khassanov, Haihua Xu, Van Tung Pham, Zhiping Zeng, Eng Siong Chng, Chongjia Ni, Bin Ma |
| Abstract | The lack of code-switch training data is one of the major concerns in the development of end-to-end code-switching automatic speech recognition (ASR) models. In this work, we propose a method to train an improved end-to-end code-switching ASR using only monolingual data. Our method encourages the distributions of output token embeddings of monolingual languages to be similar, and hence, promotes the ASR model to easily code-switch between languages. Specifically, we propose to use Jensen-Shannon divergence and cosine distance based constraints. The former will enforce output embeddings of monolingual languages to possess similar distributions, while the later simply brings the centroids of two distributions to be close to each other. Experimental results demonstrate high effectiveness of the proposed method, yielding up to 4.5% absolute mixed error rate improvement on Mandarin-English code-switching ASR task. |
| Tasks | Speech Recognition |
| Published | 2019-04-08 |
| URL | https://arxiv.org/abs/1904.03802v2 |
| https://arxiv.org/pdf/1904.03802v2.pdf | |
| PWC | https://paperswithcode.com/paper/constrained-output-embeddings-for-end-to-end |
| Repo | |
| Framework | |
Reciprocal Translation between SAR and Optical Remote Sensing Images with Cascaded-Residual Adversarial Networks
| Title | Reciprocal Translation between SAR and Optical Remote Sensing Images with Cascaded-Residual Adversarial Networks |
| Authors | Shilei Fu, Feng Xu, Ya-Qiu Jin |
| Abstract | Despite the advantages of all-weather and all-day high-resolution imaging, synthetic aperture radar (SAR) images are much less viewed and used by general people because human vision is not adapted to microwave scattering phenomenon. However, expert interpreters can be trained by comparing side-by-side SAR and optical images to learn the mapping rules from SAR to optical. This paper attempts to develop machine intelligence that are trainable with large-volume co-registered SAR and optical images to translate SAR image to optical version for assisted SAR image interpretation. Reciprocal SAR-Optical image translation is a challenging task because it is raw data translation between two physically very different sensing modalities. This paper proposes a novel reciprocal adversarial network scheme where cascaded residual connections and hybrid L1-GAN loss are employed. It is trained and tested on both spaceborne GF-3 and airborne UAVSAR images. Results are presented for datasets of different resolutions and polarizations and compared with other state-of-the-art methods. The FID is used to quantitatively evaluate the translation performance. The possibility of unsupervised learning with unpaired SAR and optical images is also explored. Results show that the proposed translation network works well under many scenarios and it could potentially be used for assisted SAR interpretation. |
| Tasks | |
| Published | 2019-01-24 |
| URL | https://arxiv.org/abs/1901.08236v2 |
| https://arxiv.org/pdf/1901.08236v2.pdf | |
| PWC | https://paperswithcode.com/paper/reciprocal-translation-between-sar-and |
| Repo | |
| Framework | |
MSD: Multi-Self-Distillation Learning via Multi-classifiers within Deep Neural Networks
| Title | MSD: Multi-Self-Distillation Learning via Multi-classifiers within Deep Neural Networks |
| Authors | Yunteng Luan, Hanyu Zhao, Zhi Yang, Yafei Dai |
| Abstract | As the development of neural networks, more and more deep neural networks are adopted in various tasks, such as image classification. However, as the huge computational overhead, these networks could not be applied on mobile devices or other low latency scenes. To address this dilemma, multi-classifier convolutional network is proposed to allow faster inference via early classifiers with the corresponding classifiers. These networks utilize sophisticated designing to increase the early classifier accuracy. However, naively training the multi-classifier network could hurt the performance (accuracy) of deep neural networks as early classifiers throughout interfere with the feature generation process. In this paper, we propose a general training framework named multi-self-distillation learning (MSD), which mining knowledge of different classifiers within the same network and increase every classifier accuracy. Our approach can be applied not only to multi-classifier networks, but also modern CNNs (e.g., ResNet Series) augmented with additional side branch classifiers. We use sampling-based branch augmentation technique to transform a single-classifier network into a multi-classifier network. This reduces the gap of capacity between different classifiers, and improves the effectiveness of applying MSD. Our experiments show that MSD improves the accuracy of various networks: enhancing the accuracy of every classifier significantly for existing multi-classifier network (MSDNet), improving vanilla single-classifier networks with internal classifiers with high accuracy, while also improving the final accuracy. |
| Tasks | Image Classification |
| Published | 2019-11-21 |
| URL | https://arxiv.org/abs/1911.09418v3 |
| https://arxiv.org/pdf/1911.09418v3.pdf | |
| PWC | https://paperswithcode.com/paper/msd-multi-self-distillation-learning-via |
| Repo | |
| Framework | |
Brain segmentation based on multi-atlas guided 3D fully convolutional network ensembles
| Title | Brain segmentation based on multi-atlas guided 3D fully convolutional network ensembles |
| Authors | Jiong Wu, Xiaoying Tang |
| Abstract | In this study, we proposed and validated a multi-atlas guided 3D fully convolutional network (FCN) ensemble model (M-FCN) for segmenting brain regions of interest (ROIs) from structural magnetic resonance images (MRIs). One major limitation of existing state-of-the-art 3D FCN segmentation models is that they often apply image patches of fixed size throughout training and testing, which may miss some complex tissue appearance patterns of different brain ROIs. To address this limitation, we trained a 3D FCN model for each ROI using patches of adaptive size and embedded outputs of the convolutional layers in the deconvolutional layers to further capture the local and global context patterns. In addition, with an introduction of multi-atlas based guidance in M-FCN, our segmentation was generated by combining the information of images and labels, which is highly robust. To reduce over-fitting of the FCN model on the training data, we adopted an ensemble strategy in the learning procedure. Evaluation was performed on two brain MRI datasets, aiming respectively at segmenting 14 subcortical and ventricular structures and 54 brain ROIs. The segmentation results of the proposed method were compared with those of a state-of-the-art multi-atlas based segmentation method and an existing 3D FCN segmentation model. Our results suggested that the proposed method had a superior segmentation performance. |
| Tasks | Brain Segmentation |
| Published | 2019-01-05 |
| URL | http://arxiv.org/abs/1901.01381v1 |
| http://arxiv.org/pdf/1901.01381v1.pdf | |
| PWC | https://paperswithcode.com/paper/brain-segmentation-based-on-multi-atlas |
| Repo | |
| Framework | |
Synthesizing 3D Shapes from Silhouette Image Collections using Multi-projection Generative Adversarial Networks
| Title | Synthesizing 3D Shapes from Silhouette Image Collections using Multi-projection Generative Adversarial Networks |
| Authors | Xiao Li, Yue Dong, Pieter Peers, Xin Tong |
| Abstract | We present a new weakly supervised learning-based method for generating novel category-specific 3D shapes from unoccluded image collections. Our method is weakly supervised and only requires silhouette annotations from unoccluded, category-specific objects. Our method does not require access to the object’s 3D shape, multiple observations per object from different views, intra-image pixel-correspondences, or any view annotations. Key to our method is a novel multi-projection generative adversarial network (MP-GAN) that trains a 3D shape generator to be consistent with multiple 2D projections of the 3D shapes, and without direct access to these 3D shapes. This is achieved through multiple discriminators that encode the distribution of 2D projections of the 3D shapes seen from a different views. Additionally, to determine the view information for each silhouette image, we also train a view prediction network on visualizations of 3D shapes synthesized by the generator. We iteratively alternate between training the generator and training the view prediction network. We validate our multi-projection GAN on both synthetic and real image datasets. Furthermore, we also show that multi-projection GANs can aid in learning other high-dimensional distributions from lower dimensional training datasets, such as material-class specific spatially varying reflectance properties from images. |
| Tasks | |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.03841v1 |
| https://arxiv.org/pdf/1906.03841v1.pdf | |
| PWC | https://paperswithcode.com/paper/synthesizing-3d-shapes-from-silhouette-image-1 |
| Repo | |
| Framework | |
Design of a Solver for Multi-Agent Epistemic Planning
| Title | Design of a Solver for Multi-Agent Epistemic Planning |
| Authors | Francesco Fabiano |
| Abstract | As the interest in Artificial Intelligence continues to grow it is becoming more and more important to investigate formalization and tools that allow us to exploit logic to reason about the world. In particular, given the increasing number of multi-agents systems that could benefit from techniques of automated reasoning, exploring new ways to define not only the world’s status but also the agents’ information is constantly growing in importance. This type of reasoning, i.e., about agents’ perception of the world and also about agents’ knowledge of her and others’ knowledge, is referred to as epistemic reasoning. In our work we will try to formalize this concept, expressed through epistemic logic, for dynamic domains. In particular we will attempt to define a new action-based language for multi-agent epistemic planning and to implement an epistemic planner based on it. This solver should provide a tool flexible enough to be able to reason on different domains, e.g., economy, security, justice and politics, where reasoning about others’ beliefs could lead to winning strategies or help in changing a group of agents’ view of the world. |
| Tasks | |
| Published | 2019-09-18 |
| URL | https://arxiv.org/abs/1909.08259v1 |
| https://arxiv.org/pdf/1909.08259v1.pdf | |
| PWC | https://paperswithcode.com/paper/design-of-a-solver-for-multi-agent-epistemic |
| Repo | |
| Framework | |
DA-LSTM: A Long Short-Term Memory with Depth Adaptive to Non-uniform Information Flow in Sequential Data
| Title | DA-LSTM: A Long Short-Term Memory with Depth Adaptive to Non-uniform Information Flow in Sequential Data |
| Authors | Yifeng Zhang, Ka-Ho Chow, S. -H. Gary Chan |
| Abstract | Much sequential data exhibits highly non-uniform information distribution. This cannot be correctly modeled by traditional Long Short-Term Memory (LSTM). To address that, recent works have extended LSTM by adding more activations between adjacent inputs. However, the approaches often use a fixed depth, which is at the step of the most information content. This one-size-fits-all worst-case approach is not satisfactory, because when little information is distributed to some steps, shallow structures can achieve faster convergence and consume less computation resource. In this paper, we develop a Depth-Adaptive Long Short-Term Memory (DA-LSTM) architecture, which can dynamically adjust the structure depending on information distribution without prior knowledge. Experimental results on real-world datasets show that DA-LSTM costs much less computation resource and substantially reduce convergence time by $41.78%$ and $46.01 %$, compared with Stacked LSTM and Deep Transition LSTM, respectively. |
| Tasks | |
| Published | 2019-01-18 |
| URL | http://arxiv.org/abs/1903.02082v1 |
| http://arxiv.org/pdf/1903.02082v1.pdf | |
| PWC | https://paperswithcode.com/paper/da-lstm-a-long-short-term-memory-with-depth |
| Repo | |
| Framework | |
MRI correlates of chronic symptoms in mild traumatic brain injury
| Title | MRI correlates of chronic symptoms in mild traumatic brain injury |
| Authors | Cailey I. Kerley, Kurt G. Schilling, Justin Blaber, Beth Miller, Allen Newton, Adam W. Anderson, Bennett A. Landman, Tonia S. Rex |
| Abstract | Veterans with mild traumatic brain injury (mTBI) have reported auditory and visual dysfunction that persists beyond the acute incident. The etiology behind these symptoms is difficult to characterize with current clinical imaging. These functional deficits may be caused by shear injury or micro-bleeds, which can be detected with special imaging modalities. We explore these hypotheses in a pilot study of multi-parametric MRI. We extract over 1,000 imaging and clinical metrics and project them to a low-dimensional space, where we can discriminate between healthy controls and patients with mTBI. We also show correlations between the metric representations and patient symptoms. |
| Tasks | |
| Published | 2019-12-06 |
| URL | https://arxiv.org/abs/1912.04116v1 |
| https://arxiv.org/pdf/1912.04116v1.pdf | |
| PWC | https://paperswithcode.com/paper/mri-correlates-of-chronic-symptoms-in-mild |
| Repo | |
| Framework | |
Fully Dense Neural Network for the Automatic Modulation Recognition
| Title | Fully Dense Neural Network for the Automatic Modulation Recognition |
| Authors | Miao Du, Qin Yu, Shaomin Fei, Chen Wang, Xiaofeng Gong, Ruisen Luo |
| Abstract | Nowadays, we mainly use various convolution neural network (CNN) structures to extract features from radio data or spectrogram in AMR. Based on expert experience and spectrograms, they not only increase the difficulty of preprocessing, but also consume a lot of memory. In order to directly use in-phase and quadrature (IQ) data obtained by the receiver and enhance the efficiency of network extraction features to improve the recognition rate of modulation mode, this paper proposes a new network structure called Fully Dense Neural Network (FDNN). This network uses residual blocks to extract features, dense connect to reduce model size, and adds attentions mechanism to recalibrate. Experiments on RML2016.10a show that this network has a higher recognition rate and lower model complexity. And it shows that the FDNN model with dense connections can not only extract features effectively but also greatly reduce model parameters, which also provides a significant contribution for the application of deep learning to the intelligent radio system. |
| Tasks | |
| Published | 2019-12-07 |
| URL | https://arxiv.org/abs/1912.03449v1 |
| https://arxiv.org/pdf/1912.03449v1.pdf | |
| PWC | https://paperswithcode.com/paper/fully-dense-neural-network-for-the-automatic |
| Repo | |
| Framework | |
Recovering Bandits
| Title | Recovering Bandits |
| Authors | Ciara Pike-Burke, Steffen Grünewälder |
| Abstract | We study the recovering bandits problem, a variant of the stochastic multi-armed bandit problem where the expected reward of each arm varies according to some unknown function of the time since the arm was last played. While being a natural extension of the classical bandit problem that arises in many real-world settings, this variation is accompanied by significant difficulties. In particular, methods need to plan ahead and estimate many more quantities than in the classical bandit setting. In this work, we explore the use of Gaussian processes to tackle the estimation and planing problem. We also discuss different regret definitions that let us quantify the performance of the methods. To improve computational efficiency of the methods, we provide an optimistic planning approximation. We complement these discussions with regret bounds and empirical studies. |
| Tasks | Gaussian Processes |
| Published | 2019-10-31 |
| URL | https://arxiv.org/abs/1910.14354v1 |
| https://arxiv.org/pdf/1910.14354v1.pdf | |
| PWC | https://paperswithcode.com/paper/recovering-bandits |
| Repo | |
| Framework | |
Learning a Multi-Modal Policy via Imitating Demonstrations with Mixed Behaviors
| Title | Learning a Multi-Modal Policy via Imitating Demonstrations with Mixed Behaviors |
| Authors | Fang-I Hsiao, Jui-Hsuan Kuo, Min Sun |
| Abstract | We propose a novel approach to train a multi-modal policy from mixed demonstrations without their behavior labels. We develop a method to discover the latent factors of variation in the demonstrations. Specifically, our method is based on the variational autoencoder with a categorical latent variable. The encoder infers discrete latent factors corresponding to different behaviors from demonstrations. The decoder, as a policy, performs the behaviors accordingly. Once learned, the policy is able to reproduce a specific behavior by simply conditioning on a categorical vector. We evaluate our method on three different tasks, including a challenging task with high-dimensional visual inputs. Experimental results show that our approach is better than various baseline methods and competitive with a multi-modal policy trained by ground truth behavior labels. |
| Tasks | |
| Published | 2019-03-25 |
| URL | http://arxiv.org/abs/1903.10304v1 |
| http://arxiv.org/pdf/1903.10304v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-multi-modal-policy-via-imitating |
| Repo | |
| Framework | |
Automated Pupillary Light Reflex Test on a Portable Platform
| Title | Automated Pupillary Light Reflex Test on a Portable Platform |
| Authors | Dogancan Temel, Melvin J. Mathew, Ghassan AlRegib, Yousuf M. Khalifa |
| Abstract | In this paper, we introduce a portable eye imaging device denoted as lab-on-a-headset, which can automatically perform a swinging flashlight test. We utilized this device in a clinical study to obtain high-resolution recordings of eyes while they are exposed to a varying light stimuli. Half of the participants had relative afferent pupillary defect (RAPD) while the other half was a control group. In case of positive RAPD, patients pupils constrict less or do not constrict when light stimuli swings from the unaffected eye to the affected eye. To automatically diagnose RAPD, we propose an algorithm based on pupil localization, pupil size measurement, and pupil size comparison of right and left eye during the light reflex test. We validate the algorithmic performance over a dataset obtained from 22 subjects and show that proposed algorithm can achieve a sensitivity of 93.8% and a specificity of 87.5%. |
| Tasks | |
| Published | 2019-05-21 |
| URL | https://arxiv.org/abs/1905.08886v1 |
| https://arxiv.org/pdf/1905.08886v1.pdf | |
| PWC | https://paperswithcode.com/paper/automated-pupillary-light-reflex-test-on-a |
| Repo | |
| Framework | |
Post-mortem Iris Recognition with Deep-Learning-based Image Segmentation
| Title | Post-mortem Iris Recognition with Deep-Learning-based Image Segmentation |
| Authors | Mateusz Trokielewicz, Adam Czajka, Piotr Maciejewicz |
| Abstract | This paper proposes the first known to us iris recognition methodology designed specifically for post-mortem samples. We propose to use deep learning-based iris segmentation models to extract highly irregular iris texture areas in post-mortem iris images. We show how to use segmentation masks predicted by neural networks in conventional, Gabor-based iris recognition method, which employs circular approximations of the pupillary and limbic iris boundaries. As a whole, this method allows for a significant improvement in post-mortem iris recognition accuracy over the methods designed only for ante-mortem irises, including the academic OSIRIS and commercial IriCore implementations. The proposed method reaches the EER less than 1% for samples collected up to 10 hours after death, when compared to 16.89% and 5.37% of EER observed for OSIRIS and IriCore, respectively. For samples collected up to 369 hours post-mortem, the proposed method achieves the EER 21.45%, while 33.59% and 25.38% are observed for OSIRIS and IriCore, respectively. Additionally, the method is tested on a database of iris images collected from ophthalmology clinic patients, for which it also offers an advantage over the two other algorithms. This work is the first step towards post-mortem-specific iris recognition, which increases the chances of identification of deceased subjects in forensic investigations. The new database of post-mortem iris images acquired from 42 subjects, as well as the deep learning-based segmentation models are made available along with the paper, to ensure all the results presented in this manuscript are reproducible. |
| Tasks | Iris Recognition, Iris Segmentation, Semantic Segmentation |
| Published | 2019-01-07 |
| URL | https://arxiv.org/abs/1901.01708v2 |
| https://arxiv.org/pdf/1901.01708v2.pdf | |
| PWC | https://paperswithcode.com/paper/post-mortem-iris-recognition-with-deep |
| Repo | |
| Framework | |
Considerations for the Interpretation of Bias Measures of Word Embeddings
| Title | Considerations for the Interpretation of Bias Measures of Word Embeddings |
| Authors | Inom Mirzaev, Anthony Schulte, Michael Conover, Sam Shah |
| Abstract | Word embedding spaces are powerful tools for capturing latent semantic relationships between terms in corpora, and have become widely popular for building state-of-the-art natural language processing algorithms. However, studies have shown that societal biases present in text corpora may be incorporated into the word embedding spaces learned from them. Thus, there is an ethical concern that human-like biases contained in the corpora and their derived embedding spaces might be propagated, or even amplified with the usage of the biased embedding spaces in downstream applications. In an attempt to quantify these biases so that they may be better understood and studied, several bias metrics have been proposed. We explore the statistical properties of these proposed measures in the context of their cited applications as well as their supposed utilities. We find that there are caveats to the simple interpretation of these metrics as proposed. We find that the bias metric proposed by Bolukbasi et al. 2016 is highly sensitive to embedding hyper-parameter selection, and that in many cases, the variance due to the selection of some hyper-parameters is greater than the variance in the metric due to corpus selection, while in fewer cases the bias rankings of corpora vary with hyper-parameter selection. In light of these observations, it may be the case that bias estimates should not be thought to directly measure the properties of the underlying corpus, but rather the properties of the specific embedding spaces in question, particularly in the context of hyper-parameter selections used to generate them. Hence, bias metrics of spaces generated with differing hyper-parameters should be compared only with explicit consideration of the embedding-learning algorithms particular configurations. |
| Tasks | Word Embeddings |
| Published | 2019-06-19 |
| URL | https://arxiv.org/abs/1906.08379v1 |
| https://arxiv.org/pdf/1906.08379v1.pdf | |
| PWC | https://paperswithcode.com/paper/considerations-for-the-interpretation-of-bias |
| Repo | |
| Framework | |
