Paper Group ANR 1617
Bottom-Up Meta-Policy Search. No-regret Non-convex Online Meta-Learning. Model-Agnostic Meta-Learning using Runge-Kutta Methods. Approximate Dynamic Programming with Neural Networks in Linear Discrete Action Spaces. Fundamental Limitations in Sequential Prediction and Recursive Algorithms: $\mathcal{L}_{p}$ Bounds via an Entropic Analysis. Fast and …
Bottom-Up Meta-Policy Search
| Title | Bottom-Up Meta-Policy Search |
| Authors | Luckeciano C. Melo, Marcos R. O. A. Maximo, Adilson Marques da Cunha |
| Abstract | Despite of the recent progress in agents that learn through interaction, there are several challenges in terms of sample efficiency and generalization across unseen behaviors during training. To mitigate these problems, we propose and apply a first-order Meta-Learning algorithm called Bottom-Up Meta-Policy Search (BUMPS), which works with two-phase optimization procedure: firstly, in a meta-training phase, it distills few expert policies to create a meta-policy capable of generalizing knowledge to unseen tasks during training; secondly, it applies a fast adaptation strategy named Policy Filtering, which evaluates few policies sampled from the meta-policy distribution and selects which best solves the task. We conducted all experiments in the RoboCup 3D Soccer Simulation domain, in the context of kick motion learning. We show that, given our experimental setup, BUMPS works in scenarios where simple multi-task Reinforcement Learning does not. Finally, we performed experiments in a way to evaluate each component of the algorithm. |
| Tasks | Meta-Learning |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.10232v2 |
| https://arxiv.org/pdf/1910.10232v2.pdf | |
| PWC | https://paperswithcode.com/paper/bottom-up-meta-policy-search |
| Repo | |
| Framework | |
No-regret Non-convex Online Meta-Learning
| Title | No-regret Non-convex Online Meta-Learning |
| Authors | Zhenxun Zhuang, Yunlong Wang, Kezi Yu, Songtao Lu |
| Abstract | The online meta-learning framework is designed for the continual lifelong learning setting. It bridges two fields: meta-learning which tries to extract prior knowledge from past tasks for fast learning of future tasks, and online-learning which deals with the sequential setting where problems are revealed one by one. In this paper, we generalize the original framework from convex to non-convex setting, and introduce the local regret as the alternative performance measure. We then apply this framework to stochastic settings, and show theoretically that it enjoys a logarithmic local regret, and is robust to any hyperparameter initialization. The empirical test on a real-world task demonstrates its superiority compared with traditional methods. |
| Tasks | Meta-Learning |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.10196v4 |
| https://arxiv.org/pdf/1910.10196v4.pdf | |
| PWC | https://paperswithcode.com/paper/online-meta-learning-on-non-convex-setting |
| Repo | |
| Framework | |
Model-Agnostic Meta-Learning using Runge-Kutta Methods
| Title | Model-Agnostic Meta-Learning using Runge-Kutta Methods |
| Authors | Daniel Jiwoong Im, Yibo Jiang, Nakul Verma |
| Abstract | Meta-learning has emerged as an important framework for learning new tasks from just a few examples. The success of any meta-learning model depends on (i) its fast adaptation to new tasks, as well as (ii) having a shared representation across similar tasks. Here we extend the model-agnostic meta-learning (MAML) framework introduced by Finn et al. (2017) to achieve improved performance by analyzing the temporal dynamics of the optimization procedure via the Runge-Kutta method. This method enables us to gain fine-grained control over the optimization and helps us achieve both the adaptation and representation goals across tasks. By leveraging this refined control, we demonstrate that there are multiple principled ways to update MAML and show that the classic MAML optimization is simply a special case of second-order Runge-Kutta method that mainly focuses on fast-adaptation. Experiments on benchmark classification, regression and reinforcement learning tasks show that this refined control helps attain improved results. |
| Tasks | Meta-Learning |
| Published | 2019-10-16 |
| URL | https://arxiv.org/abs/1910.07368v2 |
| https://arxiv.org/pdf/1910.07368v2.pdf | |
| PWC | https://paperswithcode.com/paper/model-agnostic-meta-learning-using-runge |
| Repo | |
| Framework | |
Approximate Dynamic Programming with Neural Networks in Linear Discrete Action Spaces
| Title | Approximate Dynamic Programming with Neural Networks in Linear Discrete Action Spaces |
| Authors | Wouter van Heeswijk, Han La Poutré |
| Abstract | Real-world problems of operations research are typically high-dimensional and combinatorial. Linear programs are generally used to formulate and efficiently solve these large decision problems. However, in multi-period decision problems, we must often compute expected downstream values corresponding to current decisions. When applying stochastic methods to approximate these values, linear programs become restrictive for designing value function approximations (VFAs). In particular, the manual design of a polynomial VFA is challenging. This paper presents an integrated approach for complex optimization problems, focusing on applications in the domain of operations research. It develops a hybrid solution method that combines linear programming and neural networks as part of approximate dynamic programming. Our proposed solution method embeds neural network VFAs into linear decision problems, combining the nonlinear expressive power of neural networks with the efficiency of solving linear programs. As a proof of concept, we perform numerical experiments on a transportation problem. The neural network VFAs consistently outperform polynomial VFAs, with limited design and tuning effort. |
| Tasks | |
| Published | 2019-02-26 |
| URL | http://arxiv.org/abs/1902.09855v1 |
| http://arxiv.org/pdf/1902.09855v1.pdf | |
| PWC | https://paperswithcode.com/paper/approximate-dynamic-programming-with-neural |
| Repo | |
| Framework | |
Fundamental Limitations in Sequential Prediction and Recursive Algorithms: $\mathcal{L}_{p}$ Bounds via an Entropic Analysis
| Title | Fundamental Limitations in Sequential Prediction and Recursive Algorithms: $\mathcal{L}_{p}$ Bounds via an Entropic Analysis |
| Authors | Song Fang, Quanyan Zhu |
| Abstract | In this paper, we obtain fundamental $\mathcal{L}_{p}$ bounds in sequential prediction and recursive algorithms via an entropic analysis. Both classes of problems are examined by investigating the underlying entropic relationships of the data and/or noises involved, and the derived lower bounds may all be quantified in a conditional entropy characterization. We also study the conditions to achieve the generic bounds from an innovations’ viewpoint. |
| Tasks | |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.02628v1 |
| https://arxiv.org/pdf/1912.02628v1.pdf | |
| PWC | https://paperswithcode.com/paper/fundamental-limitations-in-sequential |
| Repo | |
| Framework | |
Fast and Accurate Capitalization and Punctuation for Automatic Speech Recognition Using Transformer and Chunk Merging
| Title | Fast and Accurate Capitalization and Punctuation for Automatic Speech Recognition Using Transformer and Chunk Merging |
| Authors | Binh Nguyen, Vu Bao Hung Nguyen, Hien Nguyen, Pham Ngoc Phuong, The-Loc Nguyen, Quoc Truong Do, Luong Chi Mai |
| Abstract | In recent years, studies on automatic speech recognition (ASR) have shown outstanding results that reach human parity on short speech segments. However, there are still difficulties in standardizing the output of ASR such as capitalization and punctuation restoration for long-speech transcription. The problems obstruct readers to understand the ASR output semantically and also cause difficulties for natural language processing models such as NER, POS and semantic parsing. In this paper, we propose a method to restore the punctuation and capitalization for long-speech ASR transcription. The method is based on Transformer models and chunk merging that allows us to (1), build a single model that performs punctuation and capitalization in one go, and (2), perform decoding in parallel while improving the prediction accuracy. Experiments on British National Corpus showed that the proposed approach outperforms existing methods in both accuracy and decoding speed. |
| Tasks | Semantic Parsing, Speech Recognition |
| Published | 2019-08-07 |
| URL | https://arxiv.org/abs/1908.02404v1 |
| https://arxiv.org/pdf/1908.02404v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-accurate-capitalization-and |
| Repo | |
| Framework | |
Really should we pruning after model be totally trained? Pruning based on a small amount of training
| Title | Really should we pruning after model be totally trained? Pruning based on a small amount of training |
| Authors | Li Yue, Zhao Weibin, Shang Lin |
| Abstract | Pre-training of models in pruning algorithms plays an important role in pruning decision-making. We find that excessive pre-training is not necessary for pruning algorithms. According to this idea, we propose a pruning algorithm—Incremental pruning based on less training (IPLT). Compared with the traditional pruning algorithm based on a large number of pre-training, IPLT has competitive compression effect than the traditional pruning algorithm under the same simple pruning strategy. On the premise of ensuring accuracy, IPLT can achieve 8x-9x compression for VGG-19 on CIFAR-10 and only needs to pre-train few epochs. For VGG-19 on CIFAR-10, we can not only achieve 10 times test acceleration, but also about 10 times training acceleration. At present, the research mainly focuses on the compression and acceleration in the application stage of the model, while the compression and acceleration in the training stage are few. We newly proposed a pruning algorithm that can compress and accelerate in the training stage. It is novel to consider the amount of pre-training required by pruning algorithm. Our results have implications: Too much pre-training may be not necessary for pruning algorithms. |
| Tasks | Decision Making |
| Published | 2019-01-24 |
| URL | http://arxiv.org/abs/1901.08455v1 |
| http://arxiv.org/pdf/1901.08455v1.pdf | |
| PWC | https://paperswithcode.com/paper/really-should-we-pruning-after-model-be |
| Repo | |
| Framework | |
SparseSense: Human Activity Recognition from Highly Sparse Sensor Data-streams Using Set-based Neural Networks
| Title | SparseSense: Human Activity Recognition from Highly Sparse Sensor Data-streams Using Set-based Neural Networks |
| Authors | Alireza Abedin, S. Hamid Rezatofighi, Qinfeng Shi, Damith C. Ranasinghe |
| Abstract | Batteryless or so called passive wearables are providing new and innovative methods for human activity recognition (HAR), especially in healthcare applications for older people. Passive sensors are low cost, lightweight, unobtrusive and desirably disposable; attractive attributes for healthcare applications in hospitals and nursing homes. Despite the compelling propositions for sensing applications, the data streams from these sensors are characterised by high sparsity—the time intervals between sensor readings are irregular while the number of readings per unit time are often limited. In this paper, we rigorously explore the problem of learning activity recognition models from temporally sparse data. We describe how to learn directly from sparse data using a deep learning paradigm in an end-to-end manner. We demonstrate significant classification performance improvements on real-world passive sensor datasets from older people over the state-of-the-art deep learning human activity recognition models. Further, we provide insights into the model’s behaviour through complementary experiments on a benchmark dataset and visualisation of the learned activity feature spaces. |
| Tasks | Activity Recognition, Human Activity Recognition |
| Published | 2019-06-06 |
| URL | https://arxiv.org/abs/1906.02399v1 |
| https://arxiv.org/pdf/1906.02399v1.pdf | |
| PWC | https://paperswithcode.com/paper/sparsesense-human-activity-recognition-from |
| Repo | |
| Framework | |
BoxNet: A Deep Learning Method for 2D Bounding Box Estimation from Bird’s-Eye View Point Cloud
| Title | BoxNet: A Deep Learning Method for 2D Bounding Box Estimation from Bird’s-Eye View Point Cloud |
| Authors | Ehsan Nezhadarya, Yang Liu, Bingbing Liu |
| Abstract | We present a learning-based method to estimate the object bounding box from its 2D bird’s-eye view (BEV) LiDAR points. Our method, entitled BoxNet, exploits a simple deep neural network that can efficiently handle unordered points. The method takes as input the 2D coordinates of all the points and the output is a vector consisting of both the box pose (position and orientation in LiDAR coordinate system) and its size (width and length). In order to deal with the angle discontinuity problem, we propose to estimate the double-angle sinusoidal values rather than the angle itself. We also predict the center relative to the point cloud mean to boost the performance of estimating the location of the box. The proposed method does not rely on the ordering of points as in many existing approaches, and can accurately predict the actual size of the bounding box based on the prior information that is obtained from the training data. BoxNet is validated using the KITTI 3D object dataset, with significant improvement compared with the state-of-the-art non-learning based methods |
| Tasks | |
| Published | 2019-08-19 |
| URL | https://arxiv.org/abs/1908.07085v1 |
| https://arxiv.org/pdf/1908.07085v1.pdf | |
| PWC | https://paperswithcode.com/paper/boxnet-a-deep-learning-method-for-2d-bounding |
| Repo | |
| Framework | |
Generation mechanism of cell assembly to store information about hand recognition
| Title | Generation mechanism of cell assembly to store information about hand recognition |
| Authors | Takahiro Homma |
| Abstract | A specific memory is stored in a cell assembly that is activated during fear learning in mice; however, research regarding cell assemblies associated with procedural and habit learning processes is lacking. In modeling studies, simulations of the learning process for hand regard, which is a type of procedural learning, resulted in the formation of cell assemblies. However, the mechanisms through which the cell assemblies form and the information stored in these cell assemblies remain unknown. In this paper, the relationship between hand movements and weight changes during the simulated learning process for hand regard was used to elucidate the mechanism through which inhibitory weights are generated, which plays an important role in the formation of cell assemblies. During the early training phase, trial and error attempts to bring the hand into the field of view caused the generation of inhibitory weights, and the cell assemblies self-organized from these inhibitory weights. The information stored in the cell assemblies was estimated by examining the contributions of the cell assemblies outputs to hand movements. During sustained hand regard, the outputs from these cell assemblies moved the hand into the field of view, using hand-related inputs almost exclusively. Therefore, infants are likely able to select the inputs associated with their hand (that is, distinguish between their hand and others), based on the information stored in the cell assembly, and move their hands into the field of view during sustained hand regard. |
| Tasks | |
| Published | 2019-09-18 |
| URL | https://arxiv.org/abs/1909.08158v1 |
| https://arxiv.org/pdf/1909.08158v1.pdf | |
| PWC | https://paperswithcode.com/paper/generation-mechanism-of-cell-assembly-to |
| Repo | |
| Framework | |
Learning to Fuse Local Geometric Features for 3D Rigid Data Matching
| Title | Learning to Fuse Local Geometric Features for 3D Rigid Data Matching |
| Authors | Jiaqi Yang, Chen Zhao, Ke Xian, Angfan Zhu, Zhiguo Cao |
| Abstract | This paper presents a simple yet very effective data-driven approach to fuse both low-level and high-level local geometric features for 3D rigid data matching. It is a common practice to generate distinctive geometric descriptors by fusing low-level features from various viewpoints or subspaces, or enhance geometric feature matching by leveraging multiple high-level features. In prior works, they are typically performed via linear operations such as concatenation and min pooling. We show that more compact and distinctive representations can be achieved by optimizing a neural network (NN) model under the triplet framework that non-linearly fuses local geometric features in Euclidean spaces. The NN model is trained by an improved triplet loss function that fully leverages all pairwise relationships within the triplet. Moreover, the fused descriptor by our approach is also competitive to deep learned descriptors from raw data while being more lightweight and rotational invariant. Experimental results on four standard datasets with various data modalities and application contexts confirm the advantages of our approach in terms of both feature matching and geometric registration. |
| Tasks | |
| Published | 2019-04-27 |
| URL | http://arxiv.org/abs/1904.12099v1 |
| http://arxiv.org/pdf/1904.12099v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-fuse-local-geometric-features-for |
| Repo | |
| Framework | |
Bi-objective Framework for Sensor Fusion in RGB-D Multi-View Systems: Applications in Calibration
| Title | Bi-objective Framework for Sensor Fusion in RGB-D Multi-View Systems: Applications in Calibration |
| Authors | Hassan Afzal, Djamila Aouada, Michel Antunes, David Fofi, Bruno Mirbach, Björn Ottersten |
| Abstract | Complete and textured 3D reconstruction of dynamic scenes has been facilitated by mapped RGB and depth information acquired by RGB-D cameras based multi-view systems. One of the most critical steps in such multi-view systems is to determine the relative poses of all cameras via a process known as extrinsic calibration. In this work, we propose a sensor fusion framework based on a weighted bi-objective optimization for refinement of extrinsic calibration tailored for RGB-D multi-view systems. The weighted bi-objective cost function, which makes use of 2D information from RGB images and 3D information from depth images, is analytically derived via the Maximum Likelihood (ML) method. The weighting factor appears as a function of noise in 2D and 3D measurements and takes into account the affect of residual errors on the optimization. We propose an iterative scheme to estimate noise variances in 2D and 3D measurements, for simultaneously computing the weighting factor together with the camera poses. An extensive quantitative and qualitative evaluation of the proposed approach shows improved calibration performance as compared to refinement schemes which use only 2D or 3D measurement information. |
| Tasks | 3D Reconstruction, Calibration, Sensor Fusion |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.09939v1 |
| https://arxiv.org/pdf/1905.09939v1.pdf | |
| PWC | https://paperswithcode.com/paper/bi-objective-framework-for-sensor-fusion-in |
| Repo | |
| Framework | |
Predominant Musical Instrument Classification based on Spectral Features
| Title | Predominant Musical Instrument Classification based on Spectral Features |
| Authors | Ankit Khairkar, Chaudhari Bhushan Jayant, Karthikeya Racharla, Paturu Harish, Vineet Kumar |
| Abstract | This work aims to examine one of the cornerstone problems of Musical Instrument Recognition, in particular instrument classification. IRMAS (Instrument recognition in Musical Audio Signals) data set is chosen. The data includes music obtained from various decades in the last century, thus having a wide variety in audio quality. We have presented a very concise summary of past work in this domain. Having implemented various supervised learning algorithms for this classification task, SVM classifier has outperformed the other state-of-the-art models with an accuracy of 79%. The classifier had a major challenge distinguishing between flute and organ. We also implemented Unsupervised techniques out of which Hierarchical Clustering has performed well. We have included most of the code (jupyter notebook) for easy reproducibility. |
| Tasks | |
| Published | 2019-11-30 |
| URL | https://arxiv.org/abs/1912.02606v1 |
| https://arxiv.org/pdf/1912.02606v1.pdf | |
| PWC | https://paperswithcode.com/paper/predominant-musical-instrument-classification |
| Repo | |
| Framework | |
Plane-Based Optimization of Geometry and Texture for RGB-D Reconstruction of Indoor Scenes
| Title | Plane-Based Optimization of Geometry and Texture for RGB-D Reconstruction of Indoor Scenes |
| Authors | Chao Wang, Xiaohu Guo |
| Abstract | We present a novel approach to reconstruct RGB-D indoor scene with plane primitives. Our approach takes as input a RGB-D sequence and a dense coarse mesh reconstructed by some 3D reconstruction method on the sequence, and generate a lightweight, low-polygonal mesh with clear face textures and sharp features without losing geometry details from the original scene. To achieve this, we firstly partition the input mesh with plane primitives, simplify it into a lightweight mesh next, then optimize plane parameters, camera poses and texture colors to maximize the photometric consistency across frames, and finally optimize mesh geometry to maximize consistency between geometry and planes. Compared to existing planar reconstruction methods which only cover large planar regions in the scene, our method builds the entire scene by adaptive planes without losing geometry details and preserves sharp features in the final mesh. We demonstrate the effectiveness of our approach by applying it onto several RGB-D scans and comparing it to other state-of-the-art reconstruction methods. |
| Tasks | 3D Reconstruction |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.09829v1 |
| https://arxiv.org/pdf/1905.09829v1.pdf | |
| PWC | https://paperswithcode.com/paper/plane-based-optimization-of-geometry-and |
| Repo | |
| Framework | |
Separating Overlapping Tissue Layers from Microscopy Images
| Title | Separating Overlapping Tissue Layers from Microscopy Images |
| Authors | Zahra Montazeri, Gopi M |
| Abstract | Manual preparation of tissue slices for microscopy imaging can introduce tissue tears and overlaps. Typically, further digital processing algorithms such as registration and 3D reconstruction from tissue image stacks cannot handle images with tissue tear/overlap artifacts, and so such images are usually discarded. In this paper, we propose an imaging model and an algorithm to digitally separate overlapping tissue data of mouse brain images into two layers. We show the correctness of our model and the algorithm by comparing our results with the ground truth. |
| Tasks | 3D Reconstruction |
| Published | 2019-05-22 |
| URL | https://arxiv.org/abs/1905.09231v1 |
| https://arxiv.org/pdf/1905.09231v1.pdf | |
| PWC | https://paperswithcode.com/paper/separating-overlapping-tissue-layers-from |
| Repo | |
| Framework | |
