Paper Group ANR 1683
End-to-End Learning Using Cycle Consistency for Image-to-Caption Transformations. ANTNets: Mobile Convolutional Neural Networks for Resource Efficient Image Classification. Semi-Supervised Semantic Mapping through Label Propagation with Semantic Texture Meshes. Learning Representations by Humans, for Humans. Region Refinement Network for Salient Ob …
End-to-End Learning Using Cycle Consistency for Image-to-Caption Transformations
| Title | End-to-End Learning Using Cycle Consistency for Image-to-Caption Transformations |
| Authors | Keisuke Hagiwara, Yusuke Mukuta, Tatsuya Harada |
| Abstract | So far, research to generate captions from images has been carried out from the viewpoint that a caption holds sufficient information for an image. If it is possible to generate an image that is close to the input image from a generated caption, i.e., if it is possible to generate a natural language caption containing sufficient information to reproduce the image, then the caption is considered to be faithful to the image. To make such regeneration possible, learning using the cycle-consistency loss is effective. In this study, we propose a method of generating captions by learning end-to-end mutual transformations between images and texts. To evaluate our method, we perform comparative experiments with and without the cycle consistency. The results are evaluated by an automatic evaluation and crowdsourcing, demonstrating that our proposed method is effective. |
| Tasks | |
| Published | 2019-03-25 |
| URL | http://arxiv.org/abs/1903.10118v1 |
| http://arxiv.org/pdf/1903.10118v1.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-learning-using-cycle-consistency |
| Repo | |
| Framework | |
ANTNets: Mobile Convolutional Neural Networks for Resource Efficient Image Classification
| Title | ANTNets: Mobile Convolutional Neural Networks for Resource Efficient Image Classification |
| Authors | Yunyang Xiong, Hyunwoo J. Kim, Varsha Hedau |
| Abstract | Deep convolutional neural networks have achieved remarkable success in computer vision. However, deep neural networks require large computing resources to achieve high performance. Although depthwise separable convolution can be an efficient module to approximate a standard convolution, it often leads to reduced representational power of networks. In this paper, under budget constraints such as computational cost (MAdds) and the parameter count, we propose a novel basic architectural block, ANTBlock. It boosts the representational power by modeling, in a high dimensional space, interdependency of channels between a depthwise convolution layer and a projection layer in the ANTBlocks. Our experiments show that ANTNet built by a sequence of ANTBlocks, consistently outperforms state-of-the-art low-cost mobile convolutional neural networks across multiple datasets. On CIFAR100, our model achieves 75.7% top-1 accuracy, which is 1.5% higher than MobileNetV2 with 8.3% fewer parameters and 19.6% less computational cost. On ImageNet, our model achieves 72.8% top-1 accuracy, which is 0.8% improvement, with 157.7ms (20% faster) on iPhone 5s over MobileNetV2. |
| Tasks | Image Classification |
| Published | 2019-04-07 |
| URL | https://arxiv.org/abs/1904.03775v2 |
| https://arxiv.org/pdf/1904.03775v2.pdf | |
| PWC | https://paperswithcode.com/paper/antnets-mobile-convolutional-neural-networks |
| Repo | |
| Framework | |
Semi-Supervised Semantic Mapping through Label Propagation with Semantic Texture Meshes
| Title | Semi-Supervised Semantic Mapping through Label Propagation with Semantic Texture Meshes |
| Authors | Radu Alexandru Rosu, Jan Quenzel, Sven Behnke |
| Abstract | Scene understanding is an important capability for robots acting in unstructured environments. While most SLAM approaches provide a geometrical representation of the scene, a semantic map is necessary for more complex interactions with the surroundings. Current methods treat the semantic map as part of the geometry which limits scalability and accuracy. We propose to represent the semantic map as a geometrical mesh and a semantic texture coupled at independent resolution. The key idea is that in many environments the geometry can be greatly simplified without loosing fidelity, while semantic information can be stored at a higher resolution, independent of the mesh. We construct a mesh from depth sensors to represent the scene geometry and fuse information into the semantic texture from segmentations of individual RGB views of the scene. Making the semantics persistent in a global mesh enables us to enforce temporal and spatial consistency of the individual view predictions. For this, we propose an efficient method of establishing consensus between individual segmentations by iteratively retraining semantic segmentation with the information stored within the map and using the retrained segmentation to re-fuse the semantics. We demonstrate the accuracy and scalability of our approach by reconstructing semantic maps of scenes from NYUv2 and a scene spanning large buildings. |
| Tasks | Scene Understanding, Semantic Segmentation |
| Published | 2019-06-17 |
| URL | https://arxiv.org/abs/1906.07029v1 |
| https://arxiv.org/pdf/1906.07029v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-semantic-mapping-through |
| Repo | |
| Framework | |
Learning Representations by Humans, for Humans
| Title | Learning Representations by Humans, for Humans |
| Authors | Sophie Hilgard, Nir Rosenfeld, Mahzarin R. Banaji, Jack Cao, David C. Parkes |
| Abstract | We propose a new, complementary approach to interpretability, in which machines are not considered as experts whose role it is to suggest what should be done and why, but rather as advisers. The objective of these models is to communicate to a human decision-maker not what to decide but how to decide. In this way, we propose that machine learning pipelines will be more readily adopted, since they allow a decision-maker to retain agency. Specifically, we develop a framework for learning representations by humans, for humans, in which we learn representations of inputs (“advice”) that are effective for human decision-making. Representation-generating models are trained with humans-in-the-loop, implicitly incorporating the human decision-making model. We show that optimizing for human decision-making rather than accuracy is effective in promoting good decisions in various classification tasks while inherently maintaining a sense of interpretability. |
| Tasks | Decision Making |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12686v1 |
| https://arxiv.org/pdf/1905.12686v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-representations-by-humans-for-humans |
| Repo | |
| Framework | |
Region Refinement Network for Salient Object Detection
| Title | Region Refinement Network for Salient Object Detection |
| Authors | Zhuotao Tian, Hengshuang Zhao, Michelle Shu, Jiaze Wang, Ruiyu Li, Xiaoyong Shen, Jiaya Jia |
| Abstract | Albeit intensively studied, false prediction and unclear boundaries are still major issues of salient object detection. In this paper, we propose a Region Refinement Network (RRN), which recurrently filters redundant information and explicitly models boundary information for saliency detection. Different from existing refinement methods, we propose a Region Refinement Module (RRM) that optimizes salient region prediction by incorporating supervised attention masks in the intermediate refinement stages. The module only brings a minor increase in model size and yet significantly reduces false predictions from the background. To further refine boundary areas, we propose a Boundary Refinement Loss (BRL) that adds extra supervision for better distinguishing foreground from background. BRL is parameter free and easy to train. We further observe that BRL helps retain the integrity in prediction by refining the boundary. Extensive experiments on saliency detection datasets show that our refinement module and loss bring significant improvement to the baseline and can be easily applied to different frameworks. We also demonstrate that our proposed model generalizes well to portrait segmentation and shadow detection tasks. |
| Tasks | Object Detection, Saliency Detection, Salient Object Detection, Shadow Detection |
| Published | 2019-06-27 |
| URL | https://arxiv.org/abs/1906.11443v1 |
| https://arxiv.org/pdf/1906.11443v1.pdf | |
| PWC | https://paperswithcode.com/paper/region-refinement-network-for-salient-object |
| Repo | |
| Framework | |
Exploring Apprenticeship Learning for Player Modelling in Interactive Narratives
| Title | Exploring Apprenticeship Learning for Player Modelling in Interactive Narratives |
| Authors | Jessica Rivera-Villicana, Fabio Zambetta, James Harland, Marsha Berry |
| Abstract | In this paper we present an early Apprenticeship Learning approach to mimic the behaviour of different players in a short adaption of the interactive fiction Anchorhead. Our motivation is the need to understand and simulate player behaviour to create systems to aid the design and personalisation of Interactive Narratives (INs). INs are partially observable for the players and their goals are dynamic as a result. We used Receding Horizon IRL (RHIRL) to learn players’ goals in the form of reward functions, and derive policies to imitate their behaviour. Our preliminary results suggest that RHIRL is able to learn action sequences to complete a game, and provided insights towards generating behaviour more similar to specific players. |
| Tasks | |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.07268v1 |
| https://arxiv.org/pdf/1909.07268v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-apprenticeship-learning-for-player |
| Repo | |
| Framework | |
Using Scene Graph Context to Improve Image Generation
| Title | Using Scene Graph Context to Improve Image Generation |
| Authors | Subarna Tripathi, Anahita Bhiwandiwalla, Alexei Bastidas, Hanlin Tang |
| Abstract | Generating realistic images from scene graphs asks neural networks to be able to reason about object relationships and compositionality. As a relatively new task, how to properly ensure the generated images comply with scene graphs or how to measure task performance remains an open question. In this paper, we propose to harness scene graph context to improve image generation from scene graphs. We introduce a scene graph context network that pools features generated by a graph convolutional neural network that are then provided to both the image generation network and the adversarial loss. With the context network, our model is trained to not only generate realistic looking images, but also to better preserve non-spatial object relationships. We also define two novel evaluation metrics, the relation score and the mean opinion relation score, for this task that directly evaluate scene graph compliance. We use both quantitative and qualitative studies to demonstrate that our pro-posed model outperforms the state-of-the-art on this challenging task. |
| Tasks | Image Generation |
| Published | 2019-01-11 |
| URL | http://arxiv.org/abs/1901.03762v2 |
| http://arxiv.org/pdf/1901.03762v2.pdf | |
| PWC | https://paperswithcode.com/paper/using-scene-graph-context-to-improve-image |
| Repo | |
| Framework | |
Neural Plasticity Networks
| Title | Neural Plasticity Networks |
| Authors | Yang Li, Shihao Ji |
| Abstract | Neural plasticity is an important functionality of human brain, in which number of neurons and synapses can shrink or expand in response to stimuli throughout the span of life. We model this dynamic learning process as an $L_0$-norm regularized binary optimization problem, in which each unit of a neural network (e.g., weight, neuron or channel, etc.) is attached with a stochastic binary gate, whose parameters determine the level of activity of a unit in the network. At the beginning, only a small portion of binary gates (therefore the corresponding neurons) are activated, while the remaining neurons are in a hibernation mode. As the learning proceeds, some neurons might be activated or deactivated if doing so can be justified by the cost-benefit tradeoff measured by the $L_0$-norm regularized objective. As the training gets mature, the probability of transition between activation and deactivation will diminish until a final hardening stage. We demonstrate that all of these learning dynamics can be modulated by a single parameter $k$ seamlessly. Our neural plasticity network (NPN) can prune or expand a network depending on the initial capacity of network provided by the user; it also unifies dropout (when $k=0$), traditional training of DNNs (when $k=\infty$) and interpolates between these two. To the best of our knowledge, this is the first learning framework that unifies network sparsification and network expansion in an end-to-end training pipeline. Extensive experiments on synthetic dataset and multiple image classification benchmarks demonstrate the superior performance of NPN. We show that both network sparsification and network expansion can yield compact models of similar architectures and of similar predictive accuracies that are close to or sometimes even higher than baseline networks. We plan to release our code to facilitate the research in this area. |
| Tasks | Image Classification |
| Published | 2019-08-13 |
| URL | https://arxiv.org/abs/1908.08118v2 |
| https://arxiv.org/pdf/1908.08118v2.pdf | |
| PWC | https://paperswithcode.com/paper/neural-plasticity-networks |
| Repo | |
| Framework | |
Impact of Argument Type and Concerns in Argumentation with a Chatbot
| Title | Impact of Argument Type and Concerns in Argumentation with a Chatbot |
| Authors | Lisa A. Chalaguine, Anthony Hunter, Fiona L. Hamilton, Henry W. W. Potts |
| Abstract | Conversational agents, also known as chatbots, are versatile tools that have the potential of being used in dialogical argumentation. They could possibly be deployed in tasks such as persuasion for behaviour change (e.g. persuading people to eat more fruit, to take regular exercise, etc.) However, to achieve this, there is a need to develop methods for acquiring appropriate arguments and counterargument that reflect both sides of the discussion. For instance, to persuade someone to do regular exercise, the chatbot needs to know counterarguments that the user might have for not doing exercise. To address this need, we present methods for acquiring arguments and counterarguments, and importantly, meta-level information that can be useful for deciding when arguments can be used during an argumentation dialogue. We evaluate these methods in studies with participants and show how harnessing these methods in a chatbot can make it more persuasive. |
| Tasks | Chatbot |
| Published | 2019-05-02 |
| URL | http://arxiv.org/abs/1905.00646v1 |
| http://arxiv.org/pdf/1905.00646v1.pdf | |
| PWC | https://paperswithcode.com/paper/impact-of-argument-type-and-concerns-in |
| Repo | |
| Framework | |
Generalized Approximate Survey Propagation for High-Dimensional Estimation
| Title | Generalized Approximate Survey Propagation for High-Dimensional Estimation |
| Authors | Luca Saglietti, Yue M. Lu, Carlo Lucibello |
| Abstract | In Generalized Linear Estimation (GLE) problems, we seek to estimate a signal that is observed through a linear transform followed by a component-wise, possibly nonlinear and noisy, channel. In the Bayesian optimal setting, Generalized Approximate Message Passing (GAMP) is known to achieve optimal performance for GLE. However, its performance can significantly degrade whenever there is a mismatch between the assumed and the true generative model, a situation frequently encountered in practice. In this paper, we propose a new algorithm, named Generalized Approximate Survey Propagation (GASP), for solving GLE in the presence of prior or model mis-specifications. As a prototypical example, we consider the phase retrieval problem, where we show that GASP outperforms the corresponding GAMP, reducing the reconstruction threshold and, for certain choices of its parameters, approaching Bayesian optimal performance. Furthermore, we present a set of State Evolution equations that exactly characterize the dynamics of GASP in the high-dimensional limit. |
| Tasks | |
| Published | 2019-05-13 |
| URL | https://arxiv.org/abs/1905.05313v1 |
| https://arxiv.org/pdf/1905.05313v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalized-approximate-survey-propagation |
| Repo | |
| Framework | |
Using stigmergy as a computational memory in the design of recurrent neural networks
| Title | Using stigmergy as a computational memory in the design of recurrent neural networks |
| Authors | Federico A. Galatolo, Mario G. C. A. Cimino, Gigliola Vaglini |
| Abstract | In this paper, a novel architecture of Recurrent Neural Network (RNN) is designed and experimented. The proposed RNN adopts a computational memory based on the concept of stigmergy. The basic principle of a Stigmergic Memory (SM) is that the activity of deposit/removal of a quantity in the SM stimulates the next activities of deposit/removal. Accordingly, subsequent SM activities tend to reinforce/weaken each other, generating a coherent coordination between the SM activities and the input temporal stimulus. We show that, in a problem of supervised classification, the SM encodes the temporal input in an emergent representational model, by coordinating the deposit, removal and classification activities. This study lays down a basic framework for the derivation of a SM-RNN. A formal ontology of SM is discussed, and the SM-RNN architecture is detailed. To appreciate the computational power of an SM-RNN, comparative NNs have been selected and trained to solve the MNIST handwritten digits recognition benchmark in its two variants: spatial (sequences of bitmap rows) and temporal (sequences of pen strokes). |
| Tasks | |
| Published | 2019-01-09 |
| URL | http://arxiv.org/abs/1903.01341v1 |
| http://arxiv.org/pdf/1903.01341v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-stigmergy-as-a-computational-memory-in |
| Repo | |
| Framework | |
Vertex Classification on Weighted Networks
| Title | Vertex Classification on Weighted Networks |
| Authors | Hayden Helm, Joshua Vogelstein, Carey Priebe |
| Abstract | This paper proposes a discrimination technique for vertices in a weighted network. We assume that the edge weights and adjacencies in the network are conditionally independent and that both sources of information encode class membership information. In particular, we introduce a edge weight distribution matrix to the standard K-Block Stochastic Block Model to model weighted networks. This allows us to develop simple yet powerful extensions of classification techniques using the spectral embedding of the unweighted adjacency matrix. We consider two assumptions on the edge weight distributions and propose classification procedures in both settings. We show the effectiveness of the proposed classifiers by comparing them to quadratic discriminant analysis following the spectral embedding of a transformed weighted network. Moreover, we discuss and show how the methods perform when the edge weights do not encode class membership information. |
| Tasks | |
| Published | 2019-06-07 |
| URL | https://arxiv.org/abs/1906.02881v1 |
| https://arxiv.org/pdf/1906.02881v1.pdf | |
| PWC | https://paperswithcode.com/paper/vertex-classification-on-weighted-networks |
| Repo | |
| Framework | |
Theoretically-Efficient and Practical Parallel DBSCAN
| Title | Theoretically-Efficient and Practical Parallel DBSCAN |
| Authors | Yiqiu Wang, Yan Gu, Julian Shun |
| Abstract | The DBSCAN method for spatial clustering has received significant attention due to its applicability in a variety of data analysis tasks. There are fast sequential algorithms for DBSCAN in Euclidean space that take $O(n\log n)$ work for two dimensions, sub-quadratic work for three or more dimensions, and can be computed approximately in linear work for any constant number of dimensions. However, existing parallel DBSCAN algorithms require quadratic work in the worst case, making them inefficient for large datasets. This paper bridges the gap between theory and practice of parallel DBSCAN by presenting new parallel algorithms for Euclidean exact DBSCAN and approximate DBSCAN that match the work bounds of their sequential counterparts, and are highly parallel (polylogarithmic depth). We present implementations of our algorithms along with optimizations that improve their practical performance. We perform a comprehensive experimental evaluation of our algorithms on a variety of datasets and parameter settings. Our experiments on a 36-core machine with hyper-threading show that we outperform existing parallel DBSCAN implementations by up to several orders of magnitude, and achieve speedups by up to 33x over the best sequential algorithms. |
| Tasks | |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/1912.06255v2 |
| https://arxiv.org/pdf/1912.06255v2.pdf | |
| PWC | https://paperswithcode.com/paper/theoretically-efficient-and-practical |
| Repo | |
| Framework | |
Priority-based Parameter Propagation for Distributed DNN Training
| Title | Priority-based Parameter Propagation for Distributed DNN Training |
| Authors | Anand Jayarajan, Jinliang Wei, Garth Gibson, Alexandra Fedorova, Gennady Pekhimenko |
| Abstract | Data parallel training is widely used for scaling distributed deep neural network (DNN) training. However, the performance benefits are often limited by the communication-heavy parameter synchronization step. In this paper, we take advantage of the domain specific knowledge of DNN training and overlap parameter synchronization with computation in order to improve the training performance. We make two key observations: (1) the optimal data representation granularity for the communication may differ from that used by the underlying DNN model implementation and (2) different parameters can afford different synchronization delays. Based on these observations, we propose a new synchronization mechanism called Priority-based Parameter Propagation (P3). P3 synchronizes parameters at a finer granularity and schedules data transmission in such a way that the training process incurs minimal communication delay. We show that P3 can improve the training throughput of ResNet-50, Sockeye and VGG-19 by as much as 25%, 38% and 66% respectively on clusters with realistic network bandwidth |
| Tasks | |
| Published | 2019-05-10 |
| URL | https://arxiv.org/abs/1905.03960v1 |
| https://arxiv.org/pdf/1905.03960v1.pdf | |
| PWC | https://paperswithcode.com/paper/priority-based-parameter-propagation-for |
| Repo | |
| Framework | |
Updating Pre-trained Word Vectors and Text Classifiers using Monolingual Alignment
| Title | Updating Pre-trained Word Vectors and Text Classifiers using Monolingual Alignment |
| Authors | Piotr Bojanowski, Onur Celebi, Tomas Mikolov, Edouard Grave, Armand Joulin |
| Abstract | In this paper, we focus on the problem of adapting word vector-based models to new textual data. Given a model pre-trained on large reference data, how can we adapt it to a smaller piece of data with a slightly different language distribution? We frame the adaptation problem as a monolingual word vector alignment problem, and simply average models after alignment. We align vectors using the RCSLS criterion. Our formulation results in a simple and efficient algorithm that allows adapting general-purpose models to changing word distributions. In our evaluation, we consider applications to word embedding and text classification models. We show that the proposed approach yields good performance in all setups and outperforms a baseline consisting in fine-tuning the model on new data. |
| Tasks | Text Classification |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.06241v2 |
| https://arxiv.org/pdf/1910.06241v2.pdf | |
| PWC | https://paperswithcode.com/paper/updating-pre-trained-word-vectors-and-text |
| Repo | |
| Framework | |
