PyTorchKR Papers

최신 논문

총 716편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2011.08877공식 코드 · Papers with Code

Towards Improved and Interpretable Deep Metric Learning via Attentive Grouping

Grouping has been commonly used in deep metric learning for computing diverse features. However, current methods are prone to overfitting and lack interpretability. In this work, we propose an improved and interpretable grouping method to be integrated flexibly with any metric learning framework. Our method is based on the attention mechanism with a learnable query for each group. The query is fully trainable and can capture group-specific information when combined with the diversity loss. An appealing property of our method is that it naturally lends itself interpretability. The attention scores between the learnable query and each spatial position can be interpreted as the importance of that position. We formally show that our proposed grouping method is invariant to spatial permutations of features. When used as a module in convolutional neural networks, our method leads to translational invariance. We conduct comprehensive experiments to evaluate our method. Our quantitative results indicate that the proposed method outperforms prior methods consistently and significantly across different datasets, evaluation metrics, base models, and loss functions. For the first time to the best of our knowledge, our interpretation results clearly demonstrate that the proposed method enables the learning of distinct and diverse features across groups. The code is available on https://github.com/XinyiXuXD/DGML-master.

arXiv:2011.06132공식 코드 · Papers with Code

Incorporating a Local Translation Mechanism into Non-autoregressive Translation

In this work, we introduce a novel local autoregressive translation (LAT) mechanism into non-autoregressive translation (NAT) models so as to capture local dependencies among tar-get outputs. Specifically, for each target decoding position, instead of only one token, we predict a short sequence of tokens in an autoregressive way. We further design an efficient merging algorithm to align and merge the out-put pieces into one final output sequence. We integrate LAT into the conditional masked language model (CMLM; Ghazvininejad et al.,2019) and similarly adopt iterative decoding. Empirical results on five translation tasks show that compared with CMLM, our method achieves comparable or better performance with fewer decoding iterations, bringing a 2.5xspeedup. Further analysis indicates that our method reduces repeated translations and performs better at longer sentences.

arXiv:2011.05511공식 코드 · Papers with Code

A Quantum-Inspired Probabilistic Model for the Inverse Design of Meta-Structures

In quantum mechanics, a norm squared wave function can be interpreted as the probability density that describes the likelihood of a particle to be measured in a given position or momentum. This statistical property is at the core of the microcosmos. Meanwhile, machine learning inverse design of materials raised intensive attention, resulting in various intelligent systems for matter engineering. Here, inspired by quantum theory, we propose a probabilistic deep learning paradigm for the inverse design of functional meta-structures. Our probability-density-based neural network (PDN) can accurately capture all plausible meta-structures to meet the desired performances. Local maxima in probability density distribution correspond to the most likely candidates. We verify this approach by designing multiple meta-structures for each targeted transmission spectrum to enrich design choices.

arXiv:2011.05782공식 코드 · Papers with Code

Reinforcement Learning Experiments and Benchmark for Solving Robotic Reaching Tasks

Reinforcement learning has shown great promise in robotics thanks to its ability to develop efficient robotic control procedures through self-training. In particular, reinforcement learning has been successfully applied to solving the reaching task with robotic arms. In this paper, we define a robust, reproducible and systematic experimental procedure to compare the performance of various model-free algorithms at solving this task. The policies are trained in simulation and are then transferred to a physical robotic manipulator. It is shown that augmenting the reward signal with the Hindsight Experience Replay exploration technique increases the average return of off-policy agents between 7 and 9 folds when the target position is initialised randomly at the beginning of each episode.

arXiv:2011.05717공식 코드 · Papers with Code

Learning Constrained Distributions of Robot Configurations with Generative Adversarial Network

In high dimensional robotic system, the manifold of the valid configuration space often has a complex shape, especially under constraints such as end-effector orientation or static stability. We propose a generative adversarial network approach to learn the distribution of valid robot configurations under such constraints. It can generate configurations that are close to the constraint manifold. We present two applications of this method. First, by learning the conditional distribution with respect to the desired end-effector position, we can do fast inverse kinematics even for very high degrees of freedom (DoF) systems. Then, we use it to generate samples in sampling-based constrained motion planning algorithms to reduce the necessary projection steps, speeding up the computation. We validate the approach in simulation using the 7-DoF Panda manipulator and the 28-DoF humanoid robot Talos.

arXiv:2011.02910공식 코드 · Papers with Code

Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers

Stereo depth estimation relies on optimal correspondence matching between pixels on epipolar lines in the left and right images to infer depth. In this work, we revisit the problem from a sequence-to-sequence correspondence perspective to replace cost volume construction with dense pixel matching using position information and attention. This approach, named STereo TRansformer (STTR), has several advantages: It 1) relaxes the limitation of a fixed disparity range, 2) identifies occluded regions and provides confidence estimates, and 3) imposes uniqueness constraints during the matching process. We report promising results on both synthetic and real-world datasets and demonstrate that STTR generalizes across different domains, even without fine-tuning.

arXiv:2010.11704공식 코드 · Papers with Code

Using Conditional Generative Adversarial Networks to Reduce the Effects of Latency in Robotic Telesurgery

The introduction of surgical robots brought about advancements in surgical procedures. The applications of remote telesurgery range from building medical clinics in underprivileged areas, to placing robots abroad in military hot-spots where accessibility and diversity of medical experience may be limited. Poor wireless connectivity may result in a prolonged delay, referred to as latency, between a surgeon's input and action a robot takes. In surgery, any micro-delay can injure a patient severely and in some cases, result in fatality. One was to increase safety is to mitigate the effects of latency using deep learning aided computer vision. While the current surgical robots use calibrated sensors to measure the position of the arms and tools, in this work we present a purely optical approach that provides a measurement of the tool position in relation to the patient's tissues. This research aimed to produce a neural network that allowed a robot to detect its own mechanical manipulator arms. A conditional generative adversarial networks (cGAN) was trained on 1107 frames of mock gastrointestinal robotic surgery data from the 2015 EndoVis Instrument Challenge and corresponding hand-drawn labels for each frame. When run on new testing data, the network generated near-perfect labels of the input images which were visually consistent with the hand-drawn labels and was able to do this in 299 milliseconds. These accurately generated labels can then be used as simplified identifiers for the robot to track its own controlled tools. These results show potential for conditional GANs as a reaction mechanism such that the robot can detect when its arms move outside the operating area within a patient. This system allows for more accurate monitoring of the position of surgical instruments in relation to the patient's tissue, increasing safety measures that are integral to successful telesurgery systems.

arXiv:2010.06065공식 코드 · Papers with Code

Zero-shot Entity Linking with Efficient Long Range Sequence Modeling

This paper considers the problem of zero-shot entity linking, in which a link in the test time may not present in training. Following the prevailing BERT-based research efforts, we find a simple yet effective way is to expand the long-range sequence modeling. Unlike many previous methods, our method does not require expensive pre-training of BERT with long position embedding. Instead, we propose an efficient position embeddings initialization method called Embedding-repeat, which initializes larger position embeddings based on BERT-Base. On Wikia's zero-shot EL dataset, our method improves the SOTA from 76.06% to 79.08%, and for its long data, the corresponding improvement is from 74.57% to 82.14%. Our experiments suggest the effectiveness of long-range sequence modeling without retraining the BERT model.

arXiv:2010.06269공식 코드 · Papers with Code

BRUMS at SemEval-2020 Task 3: Contextualised Embeddings for Predicting the (Graded) Effect of Context in Word Similarity

This paper presents the team BRUMS submission to SemEval-2020 Task 3: Graded Word Similarity in Context. The system utilises state-of-the-art contextualised word embeddings, which have some task-specific adaptations, including stacked embeddings and average embeddings. Overall, the approach achieves good evaluation scores across all the languages, while maintaining simplicity. Following the final rankings, our approach is ranked within the top 5 solutions of each language while preserving the 1st position of Finnish subtask 2.

arXiv:2010.04903공식 코드 · Papers with Code

What Do Position Embeddings Learn? An Empirical Study of Pre-Trained Language Model Positional Encoding

In recent years, pre-trained Transformers have dominated the majority of NLP benchmark tasks. Many variants of pre-trained Transformers have kept breaking out, and most focus on designing different pre-training objectives or variants of self-attention. Embedding the position information in the self-attention mechanism is also an indispensable factor in Transformers however is often discussed at will. Therefore, this paper carries out an empirical study on position embeddings of mainstream pre-trained Transformers, which mainly focuses on two questions: 1) Do position embeddings really learn the meaning of positions? 2) How do these different learned position embeddings affect Transformers for NLP tasks? This paper focuses on providing a new insight of pre-trained position embeddings through feature-level analysis and empirical experiments on most of iconic NLP tasks. It is believed that our experimental results can guide the future work to choose the suitable positional encoding function for specific tasks given the application property.

arXiv:2010.05465공식 코드 · Papers with Code

COGS: A Compositional Generalization Challenge Based on Semantic Interpretation

Natural language is characterized by compositionality: the meaning of a complex expression is constructed from the meanings of its constituent parts. To facilitate the evaluation of the compositional abilities of language processing architectures, we introduce COGS, a semantic parsing dataset based on a fragment of English. The evaluation portion of COGS contains multiple systematic gaps that can only be addressed by compositional generalization; these include new combinations of familiar syntactic structures, or new combinations of familiar words and familiar structures. In experiments with Transformers and LSTMs, we found that in-distribution accuracy on the COGS test set was near-perfect (96--99%), but generalization accuracy was substantially lower (16--35%) and showed high sensitivity to random seed ($\pm$6--8%). These findings indicate that contemporary standard NLP models are limited in their compositional generalization capacity, and position COGS as a good way to measure progress.

arXiv:2010.04595공식 코드 · Papers with Code

GRF: Learning a General Radiance Field for 3D Representation and Rendering

We present a simple yet powerful neural network that implicitly represents and renders 3D objects and scenes only from 2D observations. The network models 3D geometries as a general radiance field, which takes a set of 2D images with camera poses and intrinsics as input, constructs an internal representation for each point of the 3D space, and then renders the corresponding appearance and geometry of that point viewed from an arbitrary position. The key to our approach is to learn local features for each pixel in 2D images and to then project these features to 3D points, thus yielding general and rich point representations. We additionally integrate an attention mechanism to aggregate pixel features from multiple 2D views, such that visual occlusions are implicitly taken into account. Extensive experiments demonstrate that our method can generate high-quality and realistic novel views for novel objects, unseen categories and challenging real-world scenes.

arXiv:2010.03026공식 코드 · Papers with Code

Place Recognition in Forests with Urquhart Tessellations

In this letter, we present a novel descriptor based on Urquhart tessellations derived from the position of trees in a forest. We propose a framework that uses these descriptors to detect previously seen observations and landmark correspondences, even with partial overlap and noise. We run loop closure detection experiments in simulation and real-world data map-merging from different flights of an Unmanned Aerial Vehicle (UAV) in a pine tree forest and show that our method outperforms state-of-the-art approaches in accuracy and robustness.

arXiv:2010.02609공식 코드 · Papers with Code

Position-Aware Tagging for Aspect Sentiment Triplet Extraction

Aspect Sentiment Triplet Extraction (ASTE) is the task of extracting the triplets of target entities, their associated sentiment, and opinion spans explaining the reason for the sentiment. Existing research efforts mostly solve this problem using pipeline approaches, which break the triplet extraction process into several stages. Our observation is that the three elements within a triplet are highly related to each other, and this motivates us to build a joint model to extract such triplets using a sequence tagging approach. However, how to effectively design a tagging approach to extract the triplets that can capture the rich interactions among the elements is a challenging research question. In this work, we propose the first end-to-end model with a novel position-aware tagging scheme that is capable of jointly extracting the triplets. Our experimental results on several existing datasets show that jointly capturing elements in the triplet using our approach leads to improved performance over the existing approaches. We also conducted extensive experiments to investigate the model effectiveness and robustness.

arXiv:2010.03240공식 코드 · Papers with Code

Bias and Debias in Recommender System: A Survey and Future Directions

While recent years have witnessed a rapid growth of research papers on recommender system (RS), most of the papers focus on inventing machine learning models to better fit user behavior data. However, user behavior data is observational rather than experimental. This makes various biases widely exist in the data, including but not limited to selection bias, position bias, exposure bias, and popularity bias. Blindly fitting the data without considering the inherent biases will result in many serious issues, e.g., the discrepancy between offline evaluation and online metrics, hurting user satisfaction and trust on the recommendation service, etc. To transform the large volume of research models into practical improvements, it is highly urgent to explore the impacts of the biases and perform debiasing when necessary. When reviewing the papers that consider biases in RS, we find that, to our surprise, the studies are rather fragmented and lack a systematic organization. The terminology ``bias'' is widely used in the literature, but its definition is usually vague and even inconsistent across papers. This motivates us to provide a systematic survey of existing work on RS biases. In this paper, we first summarize seven types of biases in recommendation, along with their definitions and characteristics. We then provide a taxonomy to position and organize the existing work on recommendation debiasing. Finally, we identify some open challenges and envision some future directions, with the hope of inspiring more research work on this important yet less investigated topic. The summary of debiasing methods reviewed in this survey can be found at \url{https://github.com/jiawei-chen/RecDebiasing}.

arXiv:2010.01707공식 코드 · Papers with Code

Rank Position Forecasting in Car Racing

Forecasting is challenging since uncertainty resulted from exogenous factors exists. This work investigates the rank position forecasting problem in car racing, which predicts the rank positions at the future laps for cars. Among the many factors that bring changes to the rank positions, pit stops are critical but irregular and rare. We found existing methods, including statistical models, machine learning regression models, and state-of-the-art deep forecasting model based on encoder-decoder architecture, all have limitations in the forecasting. By elaborative analysis of pit stops events, we propose a deep model, RankNet, with the cause effects decomposition that modeling the rank position sequence and pit stop events separately. It also incorporates probabilistic forecasting to model the uncertainty inside each sub-model. Through extensive experiments, RankNet demonstrates a strong performance improvement over the baselines, e.g., MAE improves more than 10% consistently, and is also more stable when adapting to unseen new data. Details of model optimization, performance profiling are presented. It is promising to provide useful forecasting tools for the car racing analysis and shine a light on solutions to similar challenging issues in general forecasting problems.

arXiv:2010.01114공식 코드 · Papers with Code

Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position Estimation

In this paper, we present Goal-GAN, an interpretable and end-to-end trainable model for human trajectory prediction. Inspired by human navigation, we model the task of trajectory prediction as an intuitive two-stage process: (i) goal estimation, which predicts the most likely target positions of the agent, followed by a (ii) routing module which estimates a set of plausible trajectories that route towards the estimated goal. We leverage information about the past trajectory and visual context of the scene to estimate a multi-modal probability distribution over the possible goal positions, which is used to sample a potential goal during the inference. The routing is governed by a recurrent neural network that reacts to physical constraints in the nearby surroundings and generates feasible paths that route towards the sampled goal. Our extensive experimental evaluation shows that our method establishes a new state-of-the-art on several benchmarks while being able to generate a realistic and diverse set of trajectories that conform to physical constraints.

arXiv:2009.03767공식 코드 · Papers with Code

Safe-by-Design Control for Euler-Lagrange Systems

Safety-critical control is characterized as ensuring constraint satisfaction for a given dynamical system. Recent developments in zeroing control barrier functions (ZCBFs) have provided a framework for ensuring safety of a superlevel set of a single constraint function. Euler-Lagrange systems represent many real-world systems including robots and vehicles, which must abide by safety-regulations, especially for use in human-occupied environments. These safety regulations include state constraints (position and velocity) and input constraints that must be respected at all times. ZCBFs are valuable for satisfying system constraints for general nonlinear systems, however their construction to satisfy state and input constraints is not straightforward. Furthermore, the existing barrier function methods do not address the multiple state constraints that are required for safety of Euler-Lagrange systems. In this paper, we propose a methodology to construct multiple, non-conflicting control barrier functions for Euler-Lagrange systems subject to input constraints to satisfy safety regulations, while concurrently taking into account robustness margins and sampling-time effects. The proposed approach consists of a sampled-data controller and an algorithm for barrier function construction to enforce safety (i.e satisfy position and velocity constraints). The proposed method is validated in simulation on a 2-DOF planar manipulator.

arXiv:2009.14237공식 코드 · Papers with Code

Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbols

Despite the central importance of research papers to scientific progress, they can be difficult to read. Comprehension is often stymied when the information needed to understand a passage resides somewhere else: in another section, or in another paper. In this work, we envision how interfaces can bring definitions of technical terms and symbols to readers when and where they need them most. We introduce ScholarPhi, an augmented reading interface with four novel features: (1) tooltips that surface position-sensitive definitions from elsewhere in a paper, (2) a filter over the paper that "declutters" it to reveal how the term or symbol is used across the paper, (3) automatic equation diagrams that expose multiple definitions in parallel, and (4) an automatically generated glossary of important terms and symbols. A usability study showed that the tool helps researchers of all experience levels read papers. Furthermore, researchers were eager to have ScholarPhi's definitions available to support their everyday reading.

arXiv:2009.13658공식 코드 · Papers with Code

Improve Transformer Models with Better Relative Position Embeddings

Transformer architectures rely on explicit position encodings in order to preserve a notion of word order. In this paper, we argue that existing work does not fully utilize position information. For example, the initial proposal of a sinusoid embedding is fixed and not learnable. In this paper, we first review absolute position embeddings and existing methods for relative position embeddings. We then propose new techniques that encourage increased interaction between query, key and relative position embeddings in the self-attention mechanism. Our most promising approach is a generalization of the absolute position embedding, improving results on SQuAD1.1 compared to previous position embeddings approaches. In addition, we address the inductive property of whether a position embedding can be robust enough to handle long sequences. We demonstrate empirically that our relative position embedding method is reasonably generalized and robust from the inductive perspective. Finally, we show that our proposed method can be adopted as a near drop-in replacement for improving the accuracy of large models with a small computational budget.