Paper Group ANR 47
An analysis of observation length requirements for machine understanding of human behaviors in spoken language. Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors. Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topology. Target Language-Aware Constrained Inference for Cross-lingual …
An analysis of observation length requirements for machine understanding of human behaviors in spoken language
| Title | An analysis of observation length requirements for machine understanding of human behaviors in spoken language |
| Authors | Sandeep Nallan Chakravarthula, Brian Baucom, Shrikanth Narayanan, Panayiotis Georgiou |
| Abstract | Machine learning-based human behavior modeling, often at the level of characterizing an entire clinical encounter such as a therapy session, has been shown to be useful across a range of domains in psychological research and practice from relationship and family studies to cancer care. Existing approaches typically first quantify the target behavior construct based on cues in an observation window, such as a fixed number of words, and then aggregate it over all the windows in that session. During this process, a sufficiently long window is employed so that adequate information is gathered to accurately estimate the construct. The link between behavior modeling and the observation length, however, has not been well studied, especially for spoken language. In this paper, we analyze the effect of observation window length on the quality of behavior quantification and present a framework for determining appropriate windows for a wide range of behaviors. Our analysis method employs two levels of evaluations: (a) extrinsic similarity between machine predictions and human expert annotations, and (b) intrinsic consistency between intra-machine and intra-human behavior relations. We apply our analysis on a dataset of real-life married couple interactions that are annotated for a large and diverse set of behavior codes and test the robustness of our findings to different machine learning models. We find that negative constructs such as blame can be accurately identified from short expressions while those pertaining to positive affect such as satisfaction tend to require slightly longer observation windows. Behaviors that describe more complex personality traits such as negotiation and avoidance are found to require very long observations and are difficult to quantify from language alone. Our findings are in agreement with similar work on acoustic cues, thin slices and human emotion perception. |
| Tasks | |
| Published | 2019-11-21 |
| URL | https://arxiv.org/abs/1911.09515v2 |
| https://arxiv.org/pdf/1911.09515v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-analysis-of-observation-length |
| Repo | |
| Framework | |
Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors
| Title | Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors |
| Authors | Mohammad Mahdi Derakhshani, Saeed Masoudnia, Amir Hossein Shaker, Omid Mersa, Mohammad Amin Sadeghi, Mohammad Rastegari, Babak N. Araabi |
| Abstract | We present a simple and effective learning technique that significantly improves mAP of YOLO object detectors without compromising their speed. During network training, we carefully feed in localization information. We excite certain activations in order to help the network learn to better localize. In the later stages of training, we gradually reduce our assisted excitation to zero. We reached a new state-of-the-art in the speed-accuracy trade-off. Our technique improves the mAP of YOLOv2 by 3.8% and mAP of YOLOv3 by 2.2% on MSCOCO dataset.This technique is inspired from curriculum learning. It is simple and effective and it is applicable to most single-stage object detectors. |
| Tasks | |
| Published | 2019-06-12 |
| URL | https://arxiv.org/abs/1906.05388v1 |
| https://arxiv.org/pdf/1906.05388v1.pdf | |
| PWC | https://paperswithcode.com/paper/assisted-excitation-of-activations-a-learning-1 |
| Repo | |
| Framework | |
Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topology
| Title | Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topology |
| Authors | Chen Zhao, Jiaqi Yang, Xin Xiong, Angfan Zhu, Zhiguo Cao, Xin Li |
| Abstract | Point cloud analysis is a fundamental task in 3D computer vision. Most previous works have conducted experiments on synthetic datasets with well-aligned data; while real-world point clouds are often not pre-aligned. How to achieve rotation invariance remains an open problem in point cloud analysis. To meet this challenge, we propose a novel approach toward achieving rotation-invariant (RI) representations by combining local geometry with global topology. In our local-global-representation (LGR)-Net, we have designed a two-branch network where one stream encodes local geometric RI features and the other encodes global topology-preserving RI features. Motivated by the observation that local geometry and global topology have different yet complementary RI responses in varying regions, two-branch RI features are fused by an innovative multi-layer perceptron (MLP) based attention module. To the best of our knowledge, this work is the first principled approach toward adaptively combining global and local information under the context of RI point cloud analysis. Extensive experiments have demonstrated that our LGR-Net achieves the state-of-the-art performance on various rotation-augmented versions of ModelNet40, ShapeNet, and ScanObjectNN (a real-world dataset). |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://arxiv.org/abs/1911.00195v2 |
| https://arxiv.org/pdf/1911.00195v2.pdf | |
| PWC | https://paperswithcode.com/paper/rotation-invariant-point-cloud-classification |
| Repo | |
| Framework | |
Target Language-Aware Constrained Inference for Cross-lingual Dependency Parsing
| Title | Target Language-Aware Constrained Inference for Cross-lingual Dependency Parsing |
| Authors | Tao Meng, Nanyun Peng, Kai-Wei Chang |
| Abstract | Prior work on cross-lingual dependency parsing often focuses on capturing the commonalities between source and target languages and overlooks the potential of leveraging linguistic properties of the languages to facilitate the transfer. In this paper, we show that weak supervisions of linguistic knowledge for the target languages can improve a cross-lingual graph-based dependency parser substantially. Specifically, we explore several types of corpus linguistic statistics and compile them into corpus-wise constraints to guide the inference process during the test time. We adapt two techniques, Lagrangian relaxation and posterior regularization, to conduct inference with corpus-statistics constraints. Experiments show that the Lagrangian relaxation and posterior regularization inference improve the performances on 15 and 17 out of 19 target languages, respectively. The improvements are especially significant for target languages that have different word order features from the source language. |
| Tasks | Dependency Parsing |
| Published | 2019-09-03 |
| URL | https://arxiv.org/abs/1909.01482v1 |
| https://arxiv.org/pdf/1909.01482v1.pdf | |
| PWC | https://paperswithcode.com/paper/target-language-aware-constrained-inference |
| Repo | |
| Framework | |
Inference with Deep Generative Priors in High Dimensions
| Title | Inference with Deep Generative Priors in High Dimensions |
| Authors | Parthe Pandit, Mojtaba Sahraee-Ardakan, Sundeep Rangan, Philip Schniter, Alyson K. Fletcher |
| Abstract | Deep generative priors offer powerful models for complex-structured data, such as images, audio, and text. Using these priors in inverse problems typically requires estimating the input and/or hidden signals in a multi-layer deep neural network from observation of its output. While these approaches have been successful in practice, rigorous performance analysis is complicated by the non-convex nature of the underlying optimization problems. This paper presents a novel algorithm, Multi-Layer Vector Approximate Message Passing (ML-VAMP), for inference in multi-layer stochastic neural networks. ML-VAMP can be configured to compute maximum a priori (MAP) or approximate minimum mean-squared error (MMSE) estimates for these networks. We show that the performance of ML-VAMP can be exactly predicted in a certain high-dimensional random limit. Furthermore, under certain conditions, ML-VAMP yields estimates that achieve the minimum (i.e., Bayes-optimal) MSE as predicted by the replica method. In this way, ML-VAMP provides a computationally efficient method for multi-layer inference with an exact performance characterization and testable conditions for optimality in the large-system limit. |
| Tasks | |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.03409v1 |
| https://arxiv.org/pdf/1911.03409v1.pdf | |
| PWC | https://paperswithcode.com/paper/inference-with-deep-generative-priors-in-high |
| Repo | |
| Framework | |
Collage Inference: Using Coded Redundancy for Low Variance Distributed Image Classification
| Title | Collage Inference: Using Coded Redundancy for Low Variance Distributed Image Classification |
| Authors | Krishna Giri Narra, Zhifeng Lin, Ganesh Ananthanarayanan, Salman Avestimehr, Murali Annavaram |
| Abstract | MLaaS (ML-as-a-Service) offerings by cloud computing platforms are becoming increasingly popular. Hosting pre-trained machine learning models in the cloud enables elastic scalability as the demand grows. But providing low latency and reducing the latency variance is a key requirement. Variance is harder to control in a cloud deployment due to uncertainties in resource allocations across many virtual instances. We propose the collage inference technique which uses a novel convolutional neural network model, collage-cnn, to provide low-cost redundancy. A collage-cnn model takes a collage image formed by combining multiple images and performs multi-image classification in one shot, albeit at slightly lower accuracy. We augment a collection of traditional single image classifier models with a single collage-cnn classifier which acts as their low-cost redundant backup. Collage-cnn provides backup classification results if any single image classification requests experience slowdown. Deploying the collage-cnn models in the cloud, we demonstrate that the 99th percentile tail latency of inference can be reduced by 1.2x to 2x compared to replication based approaches while providing high accuracy. Variation in inference latency can be reduced by 1.8x to 15x. |
| Tasks | Image Classification, Object Detection |
| Published | 2019-04-27 |
| URL | https://arxiv.org/abs/1904.12222v2 |
| https://arxiv.org/pdf/1904.12222v2.pdf | |
| PWC | https://paperswithcode.com/paper/collage-inference-tolerating-stragglers-in |
| Repo | |
| Framework | |
Attesting Biases and Discrimination using Language Semantics
| Title | Attesting Biases and Discrimination using Language Semantics |
| Authors | Xavier Ferrer Aran, Jose M. Such, Natalia Criado |
| Abstract | AI agents are increasingly deployed and used to make automated decisions that affect our lives on a daily basis. It is imperative to ensure that these systems embed ethical principles and respect human values. We focus on how we can attest to whether AI agents treat users fairly without discriminating against particular individuals or groups through biases in language. In particular, we discuss human unconscious biases, how they are embedded in language, and how AI systems inherit those biases by learning from and processing human language. Then, we outline a roadmap for future research to better understand and attest problematic AI biases derived from language. |
| Tasks | |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04386v1 |
| https://arxiv.org/pdf/1909.04386v1.pdf | |
| PWC | https://paperswithcode.com/paper/attesting-biases-and-discrimination-using |
| Repo | |
| Framework | |
Task-Driven Data Verification via Gradient Descent
| Title | Task-Driven Data Verification via Gradient Descent |
| Authors | Siavash Golkar, Kyunghyun Cho |
| Abstract | We introduce a novel algorithm for the detection of possible sample corruption such as mislabeled samples in a training dataset given a small clean validation set. We use a set of inclusion variables which determine whether or not any element of the noisy training set should be included in the training of a network. We compute these inclusion variables by optimizing the performance of the network on the clean validation set via “gradient descent on gradient descent” based learning. The inclusion variables as well as the network trained in such a way form the basis of our methods, which we call Corruption Detection via Gradient Descent (CDGD). This algorithm can be applied to any supervised machine learning task and is not limited to classification problems. We provide a quantitative comparison of these methods on synthetic and real world datasets. |
| Tasks | |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.05843v1 |
| https://arxiv.org/pdf/1905.05843v1.pdf | |
| PWC | https://paperswithcode.com/paper/task-driven-data-verification-via-gradient |
| Repo | |
| Framework | |
Support Recovery in the Phase Retrieval Model: Information-Theoretic Fundamental Limits
| Title | Support Recovery in the Phase Retrieval Model: Information-Theoretic Fundamental Limits |
| Authors | Lan V. Truong, Jonathan Scarlett |
| Abstract | The support recovery problem consists of determining a sparse subset of variables that is relevant in generating a set of observations. In this paper, we study the support recovery problem in the phase retrieval model consisting of noisy phaseless measurements, which arises in a diverse range of settings such as optical detection, X-ray crystallography, electron microscopy, and coherent diffractive imaging. Our focus is on information-theoretic fundamental limits under an approximate recovery criterion, considering both discrete and Gaussian models for the sparse non-zero entries. In both cases, our bounds provide sharp thresholds with near-matching constant factors in several scaling regimes on the sparsity and signal-to-noise ratio. As a key step towards obtaining these results, we develop new concentration bounds for the conditional information content of log-concave random variables, which may be of independent interest. |
| Tasks | |
| Published | 2019-01-30 |
| URL | http://arxiv.org/abs/1901.10647v1 |
| http://arxiv.org/pdf/1901.10647v1.pdf | |
| PWC | https://paperswithcode.com/paper/support-recovery-in-the-phase-retrieval-model |
| Repo | |
| Framework | |
Talk2Car: Taking Control of Your Self-Driving Car
| Title | Talk2Car: Taking Control of Your Self-Driving Car |
| Authors | Thierry Deruyttere, Simon Vandenhende, Dusan Grujicic, Luc Van Gool, Marie-Francine Moens |
| Abstract | A long-term goal of artificial intelligence is to have an agent execute commands communicated through natural language. In many cases the commands are grounded in a visual environment shared by the human who gives the command and the agent. Execution of the command then requires mapping the command into the physical visual space, after which the appropriate action can be taken. In this paper we consider the former. Or more specifically, we consider the problem in an autonomous driving setting, where a passenger requests an action that can be associated with an object found in a street scene. Our work presents the Talk2Car dataset, which is the first object referral dataset that contains commands written in natural language for self-driving cars. We provide a detailed comparison with related datasets such as ReferIt, RefCOCO, RefCOCO+, RefCOCOg, Cityscape-Ref and CLEVR-Ref. Additionally, we include a performance analysis using strong state-of-the-art models. The results show that the proposed object referral task is a challenging one for which the models show promising results but still require additional research in natural language processing, computer vision and the intersection of these fields. The dataset can be found on our website: http://macchina-ai.eu/ |
| Tasks | Autonomous Driving, Self-Driving Cars |
| Published | 2019-09-24 |
| URL | https://arxiv.org/abs/1909.10838v1 |
| https://arxiv.org/pdf/1909.10838v1.pdf | |
| PWC | https://paperswithcode.com/paper/talk2car-taking-control-of-your-self-driving |
| Repo | |
| Framework | |
UTFPR at SemEval-2019 Task 5: Hate Speech Identification with Recurrent Neural Networks
| Title | UTFPR at SemEval-2019 Task 5: Hate Speech Identification with Recurrent Neural Networks |
| Authors | Gustavo Henrique Paetzold, Shervin Malmasi, Marcos Zampieri |
| Abstract | In this paper we revisit the problem of automatically identifying hate speech in posts from social media. We approach the task using a system based on minimalistic compositional Recurrent Neural Networks (RNN). We tested our approach on the SemEval-2019 Task 5: Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter (HatEval) shared task dataset. The dataset made available by the HatEval organizers contained English and Spanish posts retrieved from Twitter annotated with respect to the presence of hateful content and its target. In this paper we present the results obtained by our system in comparison to the other entries in the shared task. Our system achieved competitive performance ranking 7th in sub-task A out of 62 systems in the English track. |
| Tasks | |
| Published | 2019-04-16 |
| URL | http://arxiv.org/abs/1904.07839v1 |
| http://arxiv.org/pdf/1904.07839v1.pdf | |
| PWC | https://paperswithcode.com/paper/utfpr-at-semeval-2019-task-5-hate-speech |
| Repo | |
| Framework | |
Adaptive Granularity in Tensors: A Quest for Interpretable Structure
| Title | Adaptive Granularity in Tensors: A Quest for Interpretable Structure |
| Authors | Ravdeep Pasricha, Ekta Gujral, Evangelos E. Papalexakis |
| Abstract | Data collected at very frequent intervals is usually extremely sparse and has no structure that is exploitable by modern tensor decomposition algorithms. Thus the utility of such tensors is low, in terms of the amount of interpretable and exploitable structure that one can extract from them. In this paper, we introduce the problem of finding a tensor of adaptive aggregated granularity that can be decomposed to reveal meaningful latent concepts (structures) from datasets that, in their original form, are not amenable to tensor analysis. Such datasets fall under the broad category of sparse point processes that evolve over space and/or time. To the best of our knowledge, this is the first work that explores adaptive granularity aggregation in tensors. Furthermore, we formally define the problem and discuss what different definitions of “good structure” can be in practice, and show that optimal solution is of prohibitive combinatorial complexity. Subsequently, we propose an efficient and effective greedy algorithm which follows a number of intuitive decision criteria that locally maximize the “goodness of structure”, resulting in high-quality tensors. We evaluate our method on both semi-synthetic data where ground truth is known and real datasets for which we do not have any ground truth. In both cases, our proposed method constructs tensors that have very high structure quality. Finally, our proposed method is able to discover different natural resolutions of a multi-aspect dataset, which can lead to multi-resolution analysis. |
| Tasks | Point Processes |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.09009v1 |
| https://arxiv.org/pdf/1912.09009v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-granularity-in-tensors-a-quest-for |
| Repo | |
| Framework | |
Regularized Weighted Low Rank Approximation
| Title | Regularized Weighted Low Rank Approximation |
| Authors | Frank Ban, David Woodruff, Qiuyi Zhang |
| Abstract | The classical low rank approximation problem is to find a rank $k$ matrix $UV$ (where $U$ has $k$ columns and $V$ has $k$ rows) that minimizes the Frobenius norm of $A - UV$. Although this problem can be solved efficiently, we study an NP-hard variant of this problem that involves weights and regularization. A previous paper of [Razenshteyn et al. ‘16] derived a polynomial time algorithm for weighted low rank approximation with constant rank. We derive provably sharper guarantees for the regularized version by obtaining parameterized complexity bounds in terms of the statistical dimension rather than the rank, allowing for a rank-independent runtime that can be significantly faster. Our improvement comes from applying sharper matrix concentration bounds, using a novel conditioning technique, and proving structural theorems for regularized low rank problems. |
| Tasks | |
| Published | 2019-11-16 |
| URL | https://arxiv.org/abs/1911.06958v2 |
| https://arxiv.org/pdf/1911.06958v2.pdf | |
| PWC | https://paperswithcode.com/paper/regularized-weighted-low-rank-approximation-1 |
| Repo | |
| Framework | |
Semantic Graph Parsing with Recurrent Neural Network DAG Grammars
| Title | Semantic Graph Parsing with Recurrent Neural Network DAG Grammars |
| Authors | Federico Fancellu, Sorcha Gilroy, Adam Lopez, Mirella Lapata |
| Abstract | Semantic parses are directed acyclic graphs (DAGs), so semantic parsing should be modeled as graph prediction. But predicting graphs presents difficult technical challenges, so it is simpler and more common to predict the linearized graphs found in semantic parsing datasets using well-understood sequence models. The cost of this simplicity is that the predicted strings may not be well-formed graphs. We present recurrent neural network DAG grammars, a graph-aware sequence model that ensures only well-formed graphs while sidestepping many difficulties in graph prediction. We test our model on the Parallel Meaning Bank—a multilingual semantic graphbank. Our approach yields competitive results in English and establishes the first results for German, Italian and Dutch. |
| Tasks | Semantic Parsing |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1910.00051v2 |
| https://arxiv.org/pdf/1910.00051v2.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-graph-parsing-with-recurrent-neural |
| Repo | |
| Framework | |
Representational Capacity of Deep Neural Networks – A Computing Study
| Title | Representational Capacity of Deep Neural Networks – A Computing Study |
| Authors | Bernhard Bermeitinger, Tomas Hrycej, Siegfried Handschuh |
| Abstract | There is some theoretical evidence that deep neural networks with multiple hidden layers have a potential for more efficient representation of multidimensional mappings than shallow networks with a single hidden layer. The question is whether it is possible to exploit this theoretical advantage for finding such representations with help of numerical training methods. Tests using prototypical problems with a known mean square minimum did not confirm this hypothesis. Minima found with the help of deep networks have always been worse than those found using shallow networks. This does not directly contradict the theoretical findings—it is possible that the superior representational capacity of deep networks is genuine while finding the mean square minimum of such deep networks is a substantially harder problem than with shallow ones. |
| Tasks | |
| Published | 2019-07-19 |
| URL | https://arxiv.org/abs/1907.08475v1 |
| https://arxiv.org/pdf/1907.08475v1.pdf | |
| PWC | https://paperswithcode.com/paper/representational-capacity-of-deep-neural |
| Repo | |
| Framework | |
