Paper Group ANR 600
FUNN: Flexible Unsupervised Neural Network. Confidence Inference for Focused Learning in Stereo Matching. Who is Killed by Police: Introducing Supervised Attention for Hierarchical LSTMs. Correlation Propagation Networks for Scene Text Detection. Embedding Learning Through Multilingual Concept Induction. QADiver: Interactive Framework for Diagnosin …
FUNN: Flexible Unsupervised Neural Network
| Title | FUNN: Flexible Unsupervised Neural Network |
| Authors | David Vigouroux, Sylvain Picard |
| Abstract | Deep neural networks have demonstrated high accuracy in image classification tasks. However, they were shown to be weak against adversarial examples: a small perturbation in the image which changes the classification output dramatically. In recent years, several defenses have been proposed to solve this issue in supervised classification tasks. We propose a method to obtain robust features in unsupervised learning tasks against adversarial attacks. Our method differs from existing solutions by directly learning the robust features without the need to project the adversarial examples in the original examples distribution space. A first auto-encoder A1 is in charge of perturbing the input image to fool another auto-encoder A2 which is in charge of regenerating the original image. A1 tries to find the less perturbed image under the constraint that the error in the output of A2 should be at least equal to a threshold. Thanks to this training, the encoder of A2 will be robust against adversarial attacks and could be used in different tasks like classification. Using state-of-art network architectures, we demonstrate the robustness of the features obtained thanks to this method in classification tasks. |
| Tasks | Image Classification |
| Published | 2018-11-05 |
| URL | http://arxiv.org/abs/1811.01749v1 |
| http://arxiv.org/pdf/1811.01749v1.pdf | |
| PWC | https://paperswithcode.com/paper/funn-flexible-unsupervised-neural-network |
| Repo | |
| Framework | |
Confidence Inference for Focused Learning in Stereo Matching
| Title | Confidence Inference for Focused Learning in Stereo Matching |
| Authors | Ruichao Xiao, Wenxiu Sun, Chengxi Yang |
| Abstract | In this paper, we present confidence inference approachin an unsupervised way in stereo matching. Deep Neu-ral Networks (DNNs) have recently been achieving state-of-the-art performance. However, it is often hard to tellwhether the trained model was making sensible predictionsor just guessing at random. To address this problem, westart from a probabilistic interpretation of theL1loss usedin stereo matching, which inherently assumes an indepen-dent and identical (aka i.i.d.) Laplacian distribution. Weshow that with the newly introduced dense confidence map,the identical assumption is relaxed. Intuitively, the vari-ance in the Laplacian distribution is large for low confidentpixels while small for high-confidence pixels. In practice,the network learns toattenuatelow-confidence pixels (e.g.,noisy input, occlusions, featureless regions) andfocusonhigh-confidence pixels. Moreover, it can be observed fromexperiments that the focused learning is very helpful in find-ing a better convergence state of the trained model, reduc-ing over-fitting on a given dataset. |
| Tasks | Stereo Matching, Stereo Matching Hand |
| Published | 2018-09-25 |
| URL | http://arxiv.org/abs/1809.09758v1 |
| http://arxiv.org/pdf/1809.09758v1.pdf | |
| PWC | https://paperswithcode.com/paper/confidence-inference-for-focused-learning-in |
| Repo | |
| Framework | |
Who is Killed by Police: Introducing Supervised Attention for Hierarchical LSTMs
| Title | Who is Killed by Police: Introducing Supervised Attention for Hierarchical LSTMs |
| Authors | Minh Nguyen, Thien Huu Nguyen |
| Abstract | Finding names of people killed by police has become increasingly important as police shootings get more and more public attention (police killing detection). Unfortunately, there has been not much work in the literature addressing this problem. The early work in this field \cite{keith2017identifying} proposed a distant supervision framework based on Expectation Maximization (EM) to deal with the multiple appearances of the names in documents. However, such EM-based framework cannot take full advantages of deep learning models, necessitating the use of hand-designed features to improve the detection performance. In this work, we present a novel deep learning method to solve the problem of police killing recognition. The proposed method relies on hierarchical LSTMs to model the multiple sentences that contain the person names of interests, and introduce supervised attention mechanisms based on semantical word lists and dependency trees to upweight the important contextual words. Our experiments demonstrate the benefits of the proposed model and yield the state-of-the-art performance for police killing detection. |
| Tasks | |
| Published | 2018-07-09 |
| URL | http://arxiv.org/abs/1807.03409v1 |
| http://arxiv.org/pdf/1807.03409v1.pdf | |
| PWC | https://paperswithcode.com/paper/who-is-killed-by-police-introducing |
| Repo | |
| Framework | |
Correlation Propagation Networks for Scene Text Detection
| Title | Correlation Propagation Networks for Scene Text Detection |
| Authors | Zichuan Liu, Guosheng Lin, Wang Ling Goh, Fayao Liu, Chunhua Shen, Xiaokang Yang |
| Abstract | In this work, we propose a novel hybrid method for scene text detection namely Correlation Propagation Network (CPN). It is an end-to-end trainable framework engined by advanced Convolutional Neural Networks. Our CPN predicts text objects according to both top-down observations and the bottom-up cues. Multiple candidate boxes are assembled by a spatial communication mechanism call Correlation Propagation (CP). The extracted spatial features by CNN are regarded as node features in a latticed graph and Correlation Propagation algorithm runs distributively on each node to update the hypothesis of corresponding object centers. The CP process can flexibly handle scale-varying and rotated text objects without using predefined bounding box templates. Benefit from its distributive nature, CPN is computationally efficient and enjoys a high level of parallelism. Moreover, we introduce deformable convolution to the backbone network to enhance the adaptability to long texts. The evaluation on public benchmarks shows that the proposed method achieves state-of-art performance, and it significantly outperforms the existing methods for handling multi-scale and multi-oriented text objects with much lower computation cost. |
| Tasks | Scene Text Detection |
| Published | 2018-09-30 |
| URL | http://arxiv.org/abs/1810.00304v1 |
| http://arxiv.org/pdf/1810.00304v1.pdf | |
| PWC | https://paperswithcode.com/paper/correlation-propagation-networks-for-scene |
| Repo | |
| Framework | |
Embedding Learning Through Multilingual Concept Induction
| Title | Embedding Learning Through Multilingual Concept Induction |
| Authors | Philipp Dufter, Mengjie Zhao, Martin Schmitt, Alexander Fraser, Hinrich Schütze |
| Abstract | We present a new method for estimating vector space representations of words: embedding learning by concept induction. We test this method on a highly parallel corpus and learn semantic representations of words in 1259 different languages in a single common space. An extensive experimental evaluation on crosslingual word similarity and sentiment analysis indicates that concept-based multilingual embedding learning performs better than previous approaches. |
| Tasks | Sentiment Analysis |
| Published | 2018-01-21 |
| URL | http://arxiv.org/abs/1801.06807v3 |
| http://arxiv.org/pdf/1801.06807v3.pdf | |
| PWC | https://paperswithcode.com/paper/embedding-learning-through-multilingual |
| Repo | |
| Framework | |
QADiver: Interactive Framework for Diagnosing QA Models
| Title | QADiver: Interactive Framework for Diagnosing QA Models |
| Authors | Gyeongbok Lee, Sungdong Kim, Seung-won Hwang |
| Abstract | Question answering (QA) extracting answers from text to the given question in natural language, has been actively studied and existing models have shown a promise of outperforming human performance when trained and evaluated with SQuAD dataset. However, such performance may not be replicated in the actual setting, for which we need to diagnose the cause, which is non-trivial due to the complexity of model. We thus propose a web-based UI that provides how each model contributes to QA performances, by integrating visualization and analysis tools for model explanation. We expect this framework can help QA model researchers to refine and improve their models. |
| Tasks | Question Answering |
| Published | 2018-12-01 |
| URL | http://arxiv.org/abs/1812.00161v1 |
| http://arxiv.org/pdf/1812.00161v1.pdf | |
| PWC | https://paperswithcode.com/paper/qadiver-interactive-framework-for-diagnosing |
| Repo | |
| Framework | |
TextContourNet: a Flexible and Effective Framework for Improving Scene Text Detection Architecture with a Multi-task Cascade
| Title | TextContourNet: a Flexible and Effective Framework for Improving Scene Text Detection Architecture with a Multi-task Cascade |
| Authors | Dafang He, Xiao Yang, Daniel Kifer, C. Lee Giles |
| Abstract | We study the problem of extracting text instance contour information from images and use it to assist scene text detection. We propose a novel and effective framework for this and experimentally demonstrate that: (1) A CNN that can be effectively used to extract instance-level text contour from natural images. (2) The extracted contour information can be used for better scene text detection. We propose two ways for learning the contour task together with the scene text detection: (1) as an auxiliary task and (2) as multi-task cascade. Extensive experiments with different benchmark datasets demonstrate that both designs improve the performance of a state-of-the-art scene text detector and that a multi-task cascade design achieves the best performance. |
| Tasks | Scene Text Detection |
| Published | 2018-09-09 |
| URL | http://arxiv.org/abs/1809.03050v2 |
| http://arxiv.org/pdf/1809.03050v2.pdf | |
| PWC | https://paperswithcode.com/paper/textcontournet-a-flexible-and-effective |
| Repo | |
| Framework | |
Contextual Hourglass Networks for Segmentation and Density Estimation
| Title | Contextual Hourglass Networks for Segmentation and Density Estimation |
| Authors | Daniel Oñoro-Rubio, Mathias Niepert |
| Abstract | Hourglass networks such as the U-Net and V-Net are popular neural architectures for medical image segmentation and counting problems. Typical instances of hourglass networks contain shortcut connections between mirroring layers. These shortcut connections improve the performance and it is hypothesized that this is due to mitigating effects on the vanishing gradient problem and the ability of the model to combine feature maps from earlier and later layers. We propose a method for not only combining feature maps of mirroring layers but also feature maps of layers with different spatial dimensions. For instance, the method enables the integration of the bottleneck feature map with those of the reconstruction layers. The proposed approach is applicable to any hourglass architecture. We evaluated the contextual hourglass networks on image segmentation and object counting problems in the medical domain. We achieve competitive results outperforming popular hourglass networks by up to 17 percentage points. |
| Tasks | Density Estimation, Medical Image Segmentation, Object Counting, Semantic Segmentation |
| Published | 2018-06-08 |
| URL | http://arxiv.org/abs/1806.04009v1 |
| http://arxiv.org/pdf/1806.04009v1.pdf | |
| PWC | https://paperswithcode.com/paper/contextual-hourglass-networks-for |
| Repo | |
| Framework | |
Adaptive Adversarial Attack on Scene Text Recognition
| Title | Adaptive Adversarial Attack on Scene Text Recognition |
| Authors | Xiaoyong Yuan, Pan He, Xiaolin Andy Li, Dapeng Oliver Wu |
| Abstract | Recent studies have shown that state-of-the-art deep learning models are vulnerable to the inputs with small perturbations (adversarial examples). We observe two critical obstacles in adversarial examples: (i) Strong adversarial attacks (e.g., C&W attack) require manually tuning hyper-parameters and take a long time to construct an adversarial example, making it impractical to attack real-time systems; (ii) Most of the studies focus on non-sequential tasks, such as image classification, yet only a few consider sequential tasks. In this work, we speed up adversarial attacks, especially on sequential learning tasks. By leveraging the uncertainty of each task, we directly learn the adaptive multi-task weightings, without manually searching hyper-parameters. A unified architecture is developed and evaluated for both non-sequential tasks and sequential ones. To validate the effectiveness, we take the scene text recognition task as a case study. To our best knowledge, our proposed method is the first attempt to adversarial attack for scene text recognition. Adaptive Attack achieves over 99.9% success rate with 3-6X speedup compared to state-of-the-art adversarial attacks. |
| Tasks | Adversarial Attack, Image Classification, Object Detection, Scene Text Detection, Scene Text Recognition |
| Published | 2018-07-09 |
| URL | https://arxiv.org/abs/1807.03326v3 |
| https://arxiv.org/pdf/1807.03326v3.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-adversarial-attack-on-scene-text |
| Repo | |
| Framework | |
Good Initializations of Variational Bayes for Deep Models
| Title | Good Initializations of Variational Bayes for Deep Models |
| Authors | Simone Rossi, Pietro Michiardi, Maurizio Filippone |
| Abstract | Stochastic variational inference is an established way to carry out approximate Bayesian inference for deep models. While there have been effective proposals for good initializations for loss minimization in deep learning, far less attention has been devoted to the issue of initialization of stochastic variational inference. We address this by proposing a novel layer-wise initialization strategy based on Bayesian linear models. The proposed method is extensively validated on regression and classification tasks, including Bayesian DeepNets and ConvNets, showing faster and better convergence compared to alternatives inspired by the literature on initializations for loss minimization. |
| Tasks | Bayesian Inference |
| Published | 2018-10-18 |
| URL | http://arxiv.org/abs/1810.08083v2 |
| http://arxiv.org/pdf/1810.08083v2.pdf | |
| PWC | https://paperswithcode.com/paper/good-initializations-of-variational-bayes-for |
| Repo | |
| Framework | |
Spatiotemporal Data Fusion for Precipitation Nowcasting
| Title | Spatiotemporal Data Fusion for Precipitation Nowcasting |
| Authors | Vladimir Ivashkin, Vadim Lebedev |
| Abstract | Precipitation nowcasting using neural networks and ground-based radars has become one of the key components of modern weather prediction services, but it is limited to the regions covered by ground-based radars. Truly global precipitation nowcasting requires fusion of radar and satellite observations. We propose the data fusion pipeline based on computer vision techniques, including novel inpainting algorithm with soft masking. |
| Tasks | |
| Published | 2018-12-28 |
| URL | http://arxiv.org/abs/1812.10915v1 |
| http://arxiv.org/pdf/1812.10915v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatiotemporal-data-fusion-for-precipitation |
| Repo | |
| Framework | |
A simple parameter-free and adaptive approach to optimization under a minimal local smoothness assumption
| Title | A simple parameter-free and adaptive approach to optimization under a minimal local smoothness assumption |
| Authors | Peter L. Bartlett, Victor Gabillon, Michal Valko |
| Abstract | We study the problem of optimizing a function under a \emph{budgeted number of evaluations}. We only assume that the function is \emph{locally} smooth around one of its global optima. The difficulty of optimization is measured in terms of 1) the amount of \emph{noise} $b$ of the function evaluation and 2) the local smoothness, $d$, of the function. A smaller $d$ results in smaller optimization error. We come with a new, simple, and parameter-free approach. First, for all values of $b$ and $d$, this approach recovers at least the state-of-the-art regret guarantees. Second, our approach additionally obtains these results while being \textit{agnostic} to the values of both $b$ and $d$. This leads to the first algorithm that naturally adapts to an \textit{unknown} range of noise $b$ and leads to significant improvements in a moderate and low-noise regime. Third, our approach also obtains a remarkable improvement over the state-of-the-art SOO algorithm when the noise is very low which includes the case of optimization under deterministic feedback ($b=0$). There, under our minimal local smoothness assumption, this improvement is of exponential magnitude and holds for a class of functions that covers the vast majority of functions that practitioners optimize ($d=0$). We show that our algorithmic improvement is borne out in experiments as we empirically show faster convergence on common benchmarks. |
| Tasks | |
| Published | 2018-10-01 |
| URL | http://arxiv.org/abs/1810.00997v2 |
| http://arxiv.org/pdf/1810.00997v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-simple-parameter-free-and-adaptive-approach |
| Repo | |
| Framework | |
Chemical-protein relation extraction with ensembles of SVM, CNN, and RNN models
| Title | Chemical-protein relation extraction with ensembles of SVM, CNN, and RNN models |
| Authors | Yifan Peng, Anthony Rios, Ramakanth Kavuluru, Zhiyong Lu |
| Abstract | Text mining the relations between chemicals and proteins is an increasingly important task. The CHEMPROT track at BioCreative VI aims to promote the development and evaluation of systems that can automatically detect the chemical-protein relations in running text (PubMed abstracts). This manuscript describes our submission, which is an ensemble of three systems, including a Support Vector Machine, a Convolutional Neural Network, and a Recurrent Neural Network. Their output is combined using a decision based on majority voting or stacking. Our CHEMPROT system obtained 0.7266 in precision and 0.5735 in recall for an f-score of 0.6410, demonstrating the effectiveness of machine learning-based approaches for automatic relation extraction from biomedical literature. Our submission achieved the highest performance in the task during the 2017 challenge. |
| Tasks | Relation Extraction |
| Published | 2018-02-05 |
| URL | http://arxiv.org/abs/1802.01255v1 |
| http://arxiv.org/pdf/1802.01255v1.pdf | |
| PWC | https://paperswithcode.com/paper/chemical-protein-relation-extraction-with |
| Repo | |
| Framework | |
Recurrent knowledge distillation
| Title | Recurrent knowledge distillation |
| Authors | Silvia L. Pintea, Yue Liu, Jan C. van Gemert |
| Abstract | Knowledge distillation compacts deep networks by letting a small student network learn from a large teacher network. The accuracy of knowledge distillation recently benefited from adding residual layers. We propose to reduce the size of the student network even further by recasting multiple residual layers in the teacher network into a single recurrent student layer. We propose three variants of adding recurrent connections into the student network, and show experimentally on CIFAR-10, Scenes and MiniPlaces, that we can reduce the number of parameters at little loss in accuracy. |
| Tasks | |
| Published | 2018-05-18 |
| URL | http://arxiv.org/abs/1805.07170v1 |
| http://arxiv.org/pdf/1805.07170v1.pdf | |
| PWC | https://paperswithcode.com/paper/recurrent-knowledge-distillation |
| Repo | |
| Framework | |
Learning Markov Clustering Networks for Scene Text Detection
| Title | Learning Markov Clustering Networks for Scene Text Detection |
| Authors | Zichuan Liu, Guosheng Lin, Sheng Yang, Jiashi Feng, Weisi Lin, Wang Ling Goh |
| Abstract | A novel framework named Markov Clustering Network (MCN) is proposed for fast and robust scene text detection. MCN predicts instance-level bounding boxes by firstly converting an image into a Stochastic Flow Graph (SFG) and then performing Markov Clustering on this graph. Our method can detect text objects with arbitrary size and orientation without prior knowledge of object size. The stochastic flow graph encode objects’ local correlation and semantic information. An object is modeled as strongly connected nodes, which allows flexible bottom-up detection for scale-varying and rotated objects. MCN generates bounding boxes without using Non-Maximum Suppression, and it can be fully parallelized on GPUs. The evaluation on public benchmarks shows that our method outperforms the existing methods by a large margin in detecting multioriented text objects. MCN achieves new state-of-art performance on challenging MSRA-TD500 dataset with precision of 0.88, recall of 0.79 and F-score of 0.83. Also, MCN achieves realtime inference with frame rate of 34 FPS, which is $1.5\times$ speedup when compared with the fastest scene text detection algorithm. |
| Tasks | Scene Text Detection |
| Published | 2018-05-22 |
| URL | http://arxiv.org/abs/1805.08365v1 |
| http://arxiv.org/pdf/1805.08365v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-markov-clustering-networks-for-scene |
| Repo | |
| Framework | |
