Paper Group ANR 120
Principled Hybrids of Generative and Discriminative Domain Adaptation. A Labelling Framework for Probabilistic Argumentation. Prototypal Analysis and Prototypal Regression. Target-Quality Image Compression with Recurrent, Convolutional Neural Networks. A new image compression by gradient Haar wavelet. Foundations for a Probabilistic Event Calculus. …
Principled Hybrids of Generative and Discriminative Domain Adaptation
| Title | Principled Hybrids of Generative and Discriminative Domain Adaptation |
| Authors | Han Zhao, Zhenyao Zhu, Junjie Hu, Adam Coates, Geoff Gordon |
| Abstract | We propose a probabilistic framework for domain adaptation that blends both generative and discriminative modeling in a principled way. Under this framework, generative and discriminative models correspond to specific choices of the prior over parameters. This provides us a very general way to interpolate between generative and discriminative extremes through different choices of priors. By maximizing both the marginal and the conditional log-likelihoods, models derived from this framework can use both labeled instances from the source domain as well as unlabeled instances from both source and target domains. Under this framework, we show that the popular reconstruction loss of autoencoder corresponds to an upper bound of the negative marginal log-likelihoods of unlabeled instances, where marginal distributions are given by proper kernel density estimations. This provides a way to interpret the empirical success of autoencoders in domain adaptation and semi-supervised learning. We instantiate our framework using neural networks, and build a concrete model, DAuto. Empirically, we demonstrate the effectiveness of DAuto on text, image and speech datasets, showing that it outperforms related competitors when domain adaptation is possible. |
| Tasks | Domain Adaptation |
| Published | 2017-05-25 |
| URL | http://arxiv.org/abs/1705.09011v2 |
| http://arxiv.org/pdf/1705.09011v2.pdf | |
| PWC | https://paperswithcode.com/paper/principled-hybrids-of-generative-and |
| Repo | |
| Framework | |
A Labelling Framework for Probabilistic Argumentation
| Title | A Labelling Framework for Probabilistic Argumentation |
| Authors | Regis Riveret, Pietro Baroni, Yang Gao, Guido Governatori, Antonino Rotolo, Giovanni Sartor |
| Abstract | The combination of argumentation and probability paves the way to new accounts of qualitative and quantitative uncertainty, thereby offering new theoretical and applicative opportunities. Due to a variety of interests, probabilistic argumentation is approached in the literature with different frameworks, pertaining to structured and abstract argumentation, and with respect to diverse types of uncertainty, in particular the uncertainty on the credibility of the premises, the uncertainty about which arguments to consider, and the uncertainty on the acceptance status of arguments or statements. Towards a general framework for probabilistic argumentation, we investigate a labelling-oriented framework encompassing a basic setting for rule-based argumentation and its (semi-) abstract account, along with diverse types of uncertainty. Our framework provides a systematic treatment of various kinds of uncertainty and of their relationships and allows us to back or question assertions from the literature. |
| Tasks | Abstract Argumentation |
| Published | 2017-08-01 |
| URL | http://arxiv.org/abs/1708.00109v2 |
| http://arxiv.org/pdf/1708.00109v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-labelling-framework-for-probabilistic |
| Repo | |
| Framework | |
Prototypal Analysis and Prototypal Regression
| Title | Prototypal Analysis and Prototypal Regression |
| Authors | Chenyue Wu, Esteban G. Tabak |
| Abstract | Prototypal analysis is introduced to overcome two shortcomings of archetypal analysis: its sensitivity to outliers and its non-locality, which reduces its applicability as a learning tool. Same as archetypal analysis, prototypal analysis finds prototypes through convex combination of the data points and approximates the data through convex combination of the archetypes, but it adds a penalty for using prototypes distant from the data points for their reconstruction. Prototypal analysis can be extended—via kernel embedding—to probability distributions, since the convexity of the prototypes makes them interpretable as mixtures. Finally, prototypal regression is developed, a robust supervised procedure which allows the use of distributions as either features or labels. |
| Tasks | |
| Published | 2017-01-31 |
| URL | http://arxiv.org/abs/1701.08916v2 |
| http://arxiv.org/pdf/1701.08916v2.pdf | |
| PWC | https://paperswithcode.com/paper/prototypal-analysis-and-prototypal-regression |
| Repo | |
| Framework | |
Target-Quality Image Compression with Recurrent, Convolutional Neural Networks
| Title | Target-Quality Image Compression with Recurrent, Convolutional Neural Networks |
| Authors | Michele Covell, Nick Johnston, David Minnen, Sung Jin Hwang, Joel Shor, Saurabh Singh, Damien Vincent, George Toderici |
| Abstract | We introduce a stop-code tolerant (SCT) approach to training recurrent convolutional neural networks for lossy image compression. Our methods introduce a multi-pass training method to combine the training goals of high-quality reconstructions in areas around stop-code masking as well as in highly-detailed areas. These methods lead to lower true bitrates for a given recursion count, both pre- and post-entropy coding, even using unstructured LZ77 code compression. The pre-LZ77 gains are achieved by trimming stop codes. The post-LZ77 gains are due to the highly unequal distributions of 0/1 codes from the SCT architectures. With these code compressions, the SCT architecture maintains or exceeds the image quality at all compression rates compared to JPEG and to RNN auto-encoders across the Kodak dataset. In addition, the SCT coding results in lower variance in image quality across the extent of the image, a characteristic that has been shown to be important in human ratings of image quality |
| Tasks | Image Compression |
| Published | 2017-05-18 |
| URL | http://arxiv.org/abs/1705.06687v1 |
| http://arxiv.org/pdf/1705.06687v1.pdf | |
| PWC | https://paperswithcode.com/paper/target-quality-image-compression-with |
| Repo | |
| Framework | |
A new image compression by gradient Haar wavelet
| Title | A new image compression by gradient Haar wavelet |
| Authors | Yaser Sadra |
| Abstract | With the development of human communications the usage of Visual Communications has also increased. The advancement of image compression methods is one of the main reasons for the enhancement. This paper first presents main modes of image compression methods such as JPEG and JPEG2000 without mathematical details. Also, the paper describes gradient Haar wavelet transforms in order to construct a preliminary image compression algorithm. Then, a new image compression method is proposed based on the preliminary image compression algorithm that can improve standards of image compression. The new method is compared with original modes of JPEG and JPEG2000 (based on Haar wavelet) by image quality measures such as MAE, PSNAR, and SSIM. The image quality and statistical results confirm that can boost image compression standards. It is suggested that the new method is used in a part or all of an image compression standard. |
| Tasks | Image Compression |
| Published | 2017-04-28 |
| URL | http://arxiv.org/abs/1704.08822v2 |
| http://arxiv.org/pdf/1704.08822v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-image-compression-by-gradient-haar |
| Repo | |
| Framework | |
Foundations for a Probabilistic Event Calculus
| Title | Foundations for a Probabilistic Event Calculus |
| Authors | Fabio Aurelio D’Asaro, Antonis Bikakis, Luke Dickens, Rob Miller |
| Abstract | We present PEC, an Event Calculus (EC) style action language for reasoning about probabilistic causal and narrative information. It has an action language style syntax similar to that of the EC variant Modular-E. Its semantics is given in terms of possible worlds which constitute possible evolutions of the domain, and builds on that of EFEC, an epistemic extension of EC. We also describe an ASP implementation of PEC and show the sense in which this is sound and complete. |
| Tasks | |
| Published | 2017-03-20 |
| URL | http://arxiv.org/abs/1703.06815v2 |
| http://arxiv.org/pdf/1703.06815v2.pdf | |
| PWC | https://paperswithcode.com/paper/foundations-for-a-probabilistic-event |
| Repo | |
| Framework | |
Scalable Generalized Linear Bandits: Online Computation and Hashing
| Title | Scalable Generalized Linear Bandits: Online Computation and Hashing |
| Authors | Kwang-Sung Jun, Aniruddha Bhargava, Robert Nowak, Rebecca Willett |
| Abstract | Generalized Linear Bandits (GLBs), a natural extension of the stochastic linear bandits, has been popular and successful in recent years. However, existing GLBs scale poorly with the number of rounds and the number of arms, limiting their utility in practice. This paper proposes new, scalable solutions to the GLB problem in two respects. First, unlike existing GLBs, whose per-time-step space and time complexity grow at least linearly with time $t$, we propose a new algorithm that performs online computations to enjoy a constant space and time complexity. At its heart is a novel Generalized Linear extension of the Online-to-confidence-set Conversion (GLOC method) that takes \emph{any} online learning algorithm and turns it into a GLB algorithm. As a special case, we apply GLOC to the online Newton step algorithm, which results in a low-regret GLB algorithm with much lower time and memory complexity than prior work. Second, for the case where the number $N$ of arms is very large, we propose new algorithms in which each next arm is selected via an inner product search. Such methods can be implemented via hashing algorithms (i.e., “hash-amenable”) and result in a time complexity sublinear in $N$. While a Thompson sampling extension of GLOC is hash-amenable, its regret bound for $d$-dimensional arm sets scales with $d^{3/2}$, whereas GLOC’s regret bound scales with $d$. Towards closing this gap, we propose a new hash-amenable algorithm whose regret bound scales with $d^{5/4}$. Finally, we propose a fast approximate hash-key computation (inner product) with a better accuracy than the state-of-the-art, which can be of independent interest. We conclude the paper with preliminary experimental results confirming the merits of our methods. |
| Tasks | |
| Published | 2017-06-01 |
| URL | http://arxiv.org/abs/1706.00136v3 |
| http://arxiv.org/pdf/1706.00136v3.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-generalized-linear-bandits-online |
| Repo | |
| Framework | |
Guided Optical Flow Learning
| Title | Guided Optical Flow Learning |
| Authors | Yi Zhu, Zhenzhong Lan, Shawn Newsam, Alexander G. Hauptmann |
| Abstract | We study the unsupervised learning of CNNs for optical flow estimation using proxy ground truth data. Supervised CNNs, due to their immense learning capacity, have shown superior performance on a range of computer vision problems including optical flow prediction. They however require the ground truth flow which is usually not accessible except on limited synthetic data. Without the guidance of ground truth optical flow, unsupervised CNNs often perform worse as they are naturally ill-conditioned. We therefore propose a novel framework in which proxy ground truth data generated from classical approaches is used to guide the CNN learning. The models are further refined in an unsupervised fashion using an image reconstruction loss. Our guided learning approach is competitive with or superior to state-of-the-art approaches on three standard benchmark datasets yet is completely unsupervised and can run in real time. |
| Tasks | Image Reconstruction, Optical Flow Estimation |
| Published | 2017-02-08 |
| URL | http://arxiv.org/abs/1702.02295v2 |
| http://arxiv.org/pdf/1702.02295v2.pdf | |
| PWC | https://paperswithcode.com/paper/guided-optical-flow-learning |
| Repo | |
| Framework | |
Human Associations Help to Detect Conventionalized Multiword Expressions
| Title | Human Associations Help to Detect Conventionalized Multiword Expressions |
| Authors | Natalia Loukachevitch, Anastasia Gerasimova |
| Abstract | In this paper we show that if we want to obtain human evidence about conventionalization of some phrases, we should ask native speakers about associations they have to a given phrase and its component words. We have shown that if component words of a phrase have each other as frequent associations, then this phrase can be considered as conventionalized. Another type of conventionalized phrases can be revealed using two factors: low entropy of phrase associations and low intersection of component word and phrase associations. The association experiments were performed for the Russian language. |
| Tasks | |
| Published | 2017-09-12 |
| URL | http://arxiv.org/abs/1709.03925v1 |
| http://arxiv.org/pdf/1709.03925v1.pdf | |
| PWC | https://paperswithcode.com/paper/human-associations-help-to-detect |
| Repo | |
| Framework | |
Team Applied Robotics: A closer look at our robotic picking system
| Title | Team Applied Robotics: A closer look at our robotic picking system |
| Authors | Wim Abbeloos, Fabian Gouwens, Simon Jansen, Berend Küpers, Maurice Ramaker, Toon Goedemé |
| Abstract | This paper describes the vision based robotic picking system that was developed by our team, Team Applied Robotics, for the Amazon Picking Challenge 2016. This competition challenged teams to develop a robotic system that is able to pick a large variety of products from a shelve or a tote. We discuss the design considerations and our strategy, the high resolution 3D vision system, the use of a combination of texture and shape-based object detection algorithms, the robot path planning and object manipulators that were developed. |
| Tasks | Object Detection |
| Published | 2017-07-23 |
| URL | http://arxiv.org/abs/1707.07244v1 |
| http://arxiv.org/pdf/1707.07244v1.pdf | |
| PWC | https://paperswithcode.com/paper/team-applied-robotics-a-closer-look-at-our |
| Repo | |
| Framework | |
Towards Accurate Binary Convolutional Neural Network
| Title | Towards Accurate Binary Convolutional Neural Network |
| Authors | Xiaofan Lin, Cong Zhao, Wei Pan |
| Abstract | We introduce a novel scheme to train binary convolutional neural networks (CNNs) – CNNs with weights and activations constrained to {-1,+1} at run-time. It has been known that using binary weights and activations drastically reduce memory size and accesses, and can replace arithmetic operations with more efficient bitwise operations, leading to much faster test-time inference and lower power consumption. However, previous works on binarizing CNNs usually result in severe prediction accuracy degradation. In this paper, we address this issue with two major innovations: (1) approximating full-precision weights with the linear combination of multiple binary weight bases; (2) employing multiple binary activations to alleviate information loss. The implementation of the resulting binary CNN, denoted as ABC-Net, is shown to achieve much closer performance to its full-precision counterpart, and even reach the comparable prediction accuracy on ImageNet and forest trail datasets, given adequate binary weight bases and activations. |
| Tasks | |
| Published | 2017-11-30 |
| URL | http://arxiv.org/abs/1711.11294v1 |
| http://arxiv.org/pdf/1711.11294v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-accurate-binary-convolutional-neural |
| Repo | |
| Framework | |
Relative Learning from Web Images for Content-adaptive Enhancement
| Title | Relative Learning from Web Images for Content-adaptive Enhancement |
| Authors | Parag S. Chandakkar, Qiongjie Tian, Baoxin Li |
| Abstract | Personalized and content-adaptive image enhancement can find many applications in the age of social media and mobile computing. This paper presents a relative-learning-based approach, which, unlike previous methods, does not require matching original and enhanced images for training. This allows the use of massive online photo collections to train a ranking model for improved enhancement. We first propose a multi-level ranking model, which is learned from only relatively-labeled inputs that are automatically crawled. Then we design a novel parameter sampling scheme under this model to generate the desired enhancement parameters for a new image. For evaluation, we first verify the effectiveness and the generalization abilities of our approach, using images that have been enhanced/labeled by experts. Then we carry out subjective tests, which show that users prefer images enhanced by our approach over other existing methods. |
| Tasks | Image Enhancement |
| Published | 2017-04-05 |
| URL | http://arxiv.org/abs/1704.01250v1 |
| http://arxiv.org/pdf/1704.01250v1.pdf | |
| PWC | https://paperswithcode.com/paper/relative-learning-from-web-images-for-content |
| Repo | |
| Framework | |
Deep Spatio-temporal Manifold Network for Action Recognition
| Title | Deep Spatio-temporal Manifold Network for Action Recognition |
| Authors | Ce Li, Chen Chen, Baochang Zhang, Qixiang Ye, Jungong Han, Rongrong Ji |
| Abstract | Visual data such as videos are often sampled from complex manifold. We propose leveraging the manifold structure to constrain the deep action feature learning, thereby minimizing the intra-class variations in the feature space and alleviating the over-fitting problem. Considering that manifold can be transferred, layer by layer, from the data domain to the deep features, the manifold priori is posed from the top layer into the back propagation learning procedure of convolutional neural network (CNN). The resulting algorithm –Spatio-Temporal Manifold Network– is solved with the efficient Alternating Direction Method of Multipliers and Backward Propagation (ADMM-BP). We theoretically show that STMN recasts the problem as projection over the manifold via an embedding method. The proposed approach is evaluated on two benchmark datasets, showing significant improvements to the baselines. |
| Tasks | Temporal Action Localization |
| Published | 2017-05-09 |
| URL | http://arxiv.org/abs/1705.03148v1 |
| http://arxiv.org/pdf/1705.03148v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-spatio-temporal-manifold-network-for |
| Repo | |
| Framework | |
Can you tell a face from a HEVC bitstream?
| Title | Can you tell a face from a HEVC bitstream? |
| Authors | Saeed Ranjbar Alvar, Hyomin Choi, Ivan V. Bajic |
| Abstract | Image and video analytics are being increasingly used on a massive scale. Not only is the amount of data growing, but the complexity of the data processing pipelines is also increasing, thereby exacerbating the problem. It is becoming increasingly important to save computational resources wherever possible. We focus on one of the poster problems of visual analytics – face detection – and approach the issue of reducing the computation by asking: Is it possible to detect a face without full image reconstruction from the High Efficiency Video Coding (HEVC) bitstream? We demonstrate that this is indeed possible, with accuracy comparable to conventional face detection, by training a Convolutional Neural Network on the output of the HEVC entropy decoder. |
| Tasks | Face Detection, Image Reconstruction |
| Published | 2017-09-09 |
| URL | http://arxiv.org/abs/1709.02993v1 |
| http://arxiv.org/pdf/1709.02993v1.pdf | |
| PWC | https://paperswithcode.com/paper/can-you-tell-a-face-from-a-hevc-bitstream |
| Repo | |
| Framework | |
Classification and Retrieval of Digital Pathology Scans: A New Dataset
| Title | Classification and Retrieval of Digital Pathology Scans: A New Dataset |
| Authors | Morteza Babaie, Shivam Kalra, Aditya Sriram, Christopher Mitcheltree, Shujin Zhu, Amin Khatami, Shahryar Rahnamayan, H. R. Tizhoosh |
| Abstract | In this paper, we introduce a new dataset, \textbf{Kimia Path24}, for image classification and retrieval in digital pathology. We use the whole scan images of 24 different tissue textures to generate 1,325 test patches of size 1000$\times$1000 (0.5mm$\times$0.5mm). Training data can be generated according to preferences of algorithm designer and can range from approximately 27,000 to over 50,000 patches if the preset parameters are adopted. We propose a compound patch-and-scan accuracy measurement that makes achieving high accuracies quite challenging. In addition, we set the benchmarking line by applying LBP, dictionary approach and convolutional neural nets (CNNs) and report their results. The highest accuracy was 41.80% for CNN. |
| Tasks | Image Classification |
| Published | 2017-05-22 |
| URL | http://arxiv.org/abs/1705.07522v1 |
| http://arxiv.org/pdf/1705.07522v1.pdf | |
| PWC | https://paperswithcode.com/paper/classification-and-retrieval-of-digital |
| Repo | |
| Framework | |
