Paper Group ANR 1094
General Information Bottleneck Objectives and their Applications to Machine Learning. Structured Group Local Sparse Tracker. Decentralized Online Learning: Take Benefits from Others’ Data without Sharing Your Own to Track Global Trend. DeepRMSA: A Deep Reinforcement Learning Framework for Routing, Modulation and Spectrum Assignment in Elastic Optic …
General Information Bottleneck Objectives and their Applications to Machine Learning
| Title | General Information Bottleneck Objectives and their Applications to Machine Learning |
| Authors | Sayandev Mukherjee |
| Abstract | We view the Information Bottleneck Principle (IBP: Tishby et al., 1999; Schwartz-Ziv and Tishby, 2017) and Predictive Information Bottleneck Principle (PIBP: Still et al., 2007; Alemi, 2019) as special cases of a family of general information bottleneck objectives (IBOs). Each IBO corresponds to a particular constrained optimization problem where the constraints apply to: (a) the mutual information between the training data and the learned model parameters or extracted representation of the data, and (b) the mutual information between the learned model parameters or extracted representation of the data and the test data (if any). The heuristics behind the IBP and PIBP are shown to yield different constraints in the corresponding constrained optimization problem formulations. We show how other heuristics lead to a new IBO, different from both the IBP and PIBP, and use the techniques from (Alemi, 2019) to derive and optimize a variational upper bound on the new IBO. We then apply the theory of general IBOs to resolve the seeming contradiction between, on the one hand, the recommendations of IBP and PIBP to maximize the mutual information between the model parameters and test data, and on the other, recent information-theoretic results (see Xu and Raginsky, 2017) suggesting that this mutual information should be minimized. The key insight is that the heuristics (and thus the constraints in the constrained optimization problems) of IBP and PIBP are not applicable to the scenario analyzed by (Xu and Raginsky, 2017) because the latter makes the additional assumption that the parameters of the trained model have been selected to minimize the empirical loss function. Aided by this insight, we formulate a new IBO that accounts for this property of the parameters of the trained model, and derive and optimize a variational bound on this IBO. |
| Tasks | |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/1912.06248v2 |
| https://arxiv.org/pdf/1912.06248v2.pdf | |
| PWC | https://paperswithcode.com/paper/general-information-bottleneck-objectives-and |
| Repo | |
| Framework | |
Structured Group Local Sparse Tracker
| Title | Structured Group Local Sparse Tracker |
| Authors | Mohammadreza Javanmardi, Xiaojun Qi |
| Abstract | Sparse representation is considered as a viable solution to visual tracking. In this paper, we propose a structured group local sparse tracker (SGLST), which exploits local patches inside target candidates in the particle filter framework. Unlike the conventional local sparse trackers, the proposed optimization model in SGLST not only adopts local and spatial information of the target candidates but also attains the spatial layout structure among them by employing a group-sparsity regularization term. To solve the optimization model, we propose an efficient numerical algorithm consisting of two subproblems with the closed-form solutions. Both qualitative and quantitative evaluations on the benchmarks of challenging image sequences demonstrate the superior performance of the proposed tracker against several state-of-the-art trackers. |
| Tasks | Visual Tracking |
| Published | 2019-02-17 |
| URL | http://arxiv.org/abs/1902.06182v2 |
| http://arxiv.org/pdf/1902.06182v2.pdf | |
| PWC | https://paperswithcode.com/paper/structured-group-local-sparse-tracker |
| Repo | |
| Framework | |
Decentralized Online Learning: Take Benefits from Others’ Data without Sharing Your Own to Track Global Trend
| Title | Decentralized Online Learning: Take Benefits from Others’ Data without Sharing Your Own to Track Global Trend |
| Authors | Yawei Zhao, Chen Yu, Peilin Zhao, Hanlin Tang, Shuang Qiu, Ji Liu |
| Abstract | Decentralized Online Learning (online learning in decentralized networks) attracts more and more attention, since it is believed that Decentralized Online Learning can help the data providers cooperatively better solve their online problems without sharing their private data to a third party or other providers. Typically, the cooperation is achieved by letting the data providers exchange their models between neighbors, e.g., recommendation model. However, the best regret bound for a decentralized online learning algorithm is $\Ocal{n\sqrt{T}}$, where $n$ is the number of nodes (or users) and $T$ is the number of iterations. This is clearly insignificant since this bound can be achieved \emph{without} any communication in the networks. This reminds us to ask a fundamental question: \emph{Can people really get benefit from the decentralized online learning by exchanging information?} In this paper, we studied when and why the communication can help the decentralized online learning to reduce the regret. Specifically, each loss function is characterized by two components: the adversarial component and the stochastic component. Under this characterization, we show that decentralized online gradient (DOG) enjoys a regret bound $\Ocal{n\sqrt{T}G + \sqrt{nT}\sigma}$, where $G$ measures the magnitude of the adversarial component in the private data (or equivalently the local loss function) and $\sigma$ measures the randomness within the private data. This regret suggests that people can get benefits from the randomness in the private data by exchanging private information. Another important contribution of this paper is to consider the dynamic regret – a more practical regret to track users’ interest dynamics. Empirical studies are also conducted to validate our analysis. |
| Tasks | |
| Published | 2019-01-29 |
| URL | https://arxiv.org/abs/1901.10593v4 |
| https://arxiv.org/pdf/1901.10593v4.pdf | |
| PWC | https://paperswithcode.com/paper/decentralized-online-learning-take-benefits |
| Repo | |
| Framework | |
DeepRMSA: A Deep Reinforcement Learning Framework for Routing, Modulation and Spectrum Assignment in Elastic Optical Networks
| Title | DeepRMSA: A Deep Reinforcement Learning Framework for Routing, Modulation and Spectrum Assignment in Elastic Optical Networks |
| Authors | Xiaoliang Chen, Baojia Li, Roberto Proietti, Hongbo Lu, Zuqing Zhu, S. J. Ben Yoo |
| Abstract | This paper proposes DeepRMSA, a deep reinforcement learning framework for routing, modulation and spectrum assignment (RMSA) in elastic optical networks (EONs). DeepRMSA learns the correct online RMSA policies by parameterizing the policies with deep neural networks (DNNs) that can sense complex EON states. The DNNs are trained with experiences of dynamic lightpath provisioning. We first modify the asynchronous advantage actor-critic algorithm and present an episode-based training mechanism for DeepRMSA, namely, DeepRMSA-EP. DeepRMSA-EP divides the dynamic provisioning process into multiple episodes (each containing the servicing of a fixed number of lightpath requests) and performs training by the end of each episode. The optimization target of DeepRMSA-EP at each step of servicing a request is to maximize the cumulative reward within the rest of the episode. Thus, we obviate the need for estimating the rewards related to unknown future states. To overcome the instability issue in the training of DeepRMSA-EP due to the oscillations of cumulative rewards, we further propose a window-based flexible training mechanism, i.e., DeepRMSA-FLX. DeepRMSA-FLX attempts to smooth out the oscillations by defining the optimization scope at each step as a sliding window, and ensuring that the cumulative rewards always include rewards from a fixed number of requests. Evaluations with the two sample topologies show that DeepRMSA-FLX can effectively stabilize the training while achieving blocking probability reductions of more than 20.3% and 14.3%, when compared with the baselines. |
| Tasks | |
| Published | 2019-05-06 |
| URL | https://arxiv.org/abs/1905.02248v2 |
| https://arxiv.org/pdf/1905.02248v2.pdf | |
| PWC | https://paperswithcode.com/paper/deeprmsa-a-deep-reinforcement-learning |
| Repo | |
| Framework | |
Teaching GANs to Sketch in Vector Format
| Title | Teaching GANs to Sketch in Vector Format |
| Authors | Varshaneya V, S Balasubramanian, Vineeth N Balasubramanian |
| Abstract | Sketching is more fundamental to human cognition than speech. Deep Neural Networks (DNNs) have achieved the state-of-the-art in speech-related tasks but have not made significant development in generating stroke-based sketches a.k.a sketches in vector format. Though there are Variational Auto Encoders (VAEs) for generating sketches in vector format, there is no Generative Adversarial Network (GAN) architecture for the same. In this paper, we propose a standalone GAN architecture SkeGAN and a VAE-GAN architecture VASkeGAN, for sketch generation in vector format. SkeGAN is a stochastic policy in Reinforcement Learning (RL), capable of generating both multidimensional continuous and discrete outputs. VASkeGAN hybridizes a VAE and a GAN, in order to couple the efficient representation of data by VAE with the powerful generating capabilities of a GAN, to produce visually appealing sketches. We also propose a new metric called the Ske-score which quantifies the quality of vector sketches. We have validated that SkeGAN and VASkeGAN generate visually appealing sketches by using Human Turing Test and Ske-score. |
| Tasks | |
| Published | 2019-04-07 |
| URL | http://arxiv.org/abs/1904.03620v1 |
| http://arxiv.org/pdf/1904.03620v1.pdf | |
| PWC | https://paperswithcode.com/paper/teaching-gans-to-sketch-in-vector-format |
| Repo | |
| Framework | |
Recurrent U-net: Deep learning to predict daily summertime ozone in the United States
| Title | Recurrent U-net: Deep learning to predict daily summertime ozone in the United States |
| Authors | Tai-Long He, Dylan B. A. Jones, Binxuan Huang, Yuyang Liu, Kazuyuki Miyazaki, Zhe Jiang, E. Charlie White, Helen M. Worden, John R. Worden |
| Abstract | We use a hybrid deep learning model to predict June-July-August (JJA) daily maximum 8-h average (MDA8) surface ozone concentrations in the US. A set of meteorological fields from the ERA-Interim reanalysis as well as monthly mean NO$_x$ emissions from the Community Emissions Data System (CEDS) inventory are selected as predictors. Ozone measurements from the US Environmental Protection Agency (EPA) Air Quality System (AQS) from 1980 to 2009 are used to train the model, whereas data from 2010 to 2014 are used to evaluate the performance of the model. The model captures well daily, seasonal and interannual variability in MDA8 ozone across the US. Feature maps show that the model captures teleconnections between MDA8 ozone and the meteorological fields, which are responsible for driving the ozone dynamics. We used the model to evaluate recent trends in NO$_x$ emissions in the US and found that the trend in the EPA emission inventory produced the largest negative bias in MDA8 ozone between 2010-2016. The top-down emission trends from the Tropospheric Chemistry Reanalysis (TCR-2), which is based on satellite observations, produced predictions in best agreement with observations. In urban regions, the trend in AQS NO$_2$ observations provided ozone predictions in agreement with observations, whereas in rural regions the satellite-derived trends produced the best agreement. In both rural and urban regions the EPA trend resulted in the largest negative bias in predicted ozone. Our results suggest that the EPA inventory is overestimating the reductions in NO$_x$ emissions and that the satellite-derived trend reflects the influence of reductions in NO$_x$ emissions as well as changes in background NO$_x$. Our results demonstrate the significantly greater predictive capability that the deep learning model provides over conventional atmospheric chemical transport models for air quality analyses. |
| Tasks | |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.05841v1 |
| https://arxiv.org/pdf/1908.05841v1.pdf | |
| PWC | https://paperswithcode.com/paper/recurrent-u-net-deep-learning-to-predict |
| Repo | |
| Framework | |
Make a Face: Towards Arbitrary High Fidelity Face Manipulation
| Title | Make a Face: Towards Arbitrary High Fidelity Face Manipulation |
| Authors | Shengju Qian, Kwan-Yee Lin, Wayne Wu, Yangxiaokang Liu, Quan Wang, Fumin Shen, Chen Qian, Ran He |
| Abstract | Recent studies have shown remarkable success in face manipulation task with the advance of GANs and VAEs paradigms, but the outputs are sometimes limited to low-resolution and lack of diversity. In this work, we propose Additive Focal Variational Auto-encoder (AF-VAE), a novel approach that can arbitrarily manipulate high-resolution face images using a simple yet effective model and only weak supervision of reconstruction and KL divergence losses. First, a novel additive Gaussian Mixture assumption is introduced with an unsupervised clustering mechanism in the structural latent space, which endows better disentanglement and boosts multi-modal representation with external memory. Second, to improve the perceptual quality of synthesized results, two simple strategies in architecture design are further tailored and discussed on the behavior of Human Visual System (HVS) for the first time, allowing for fine control over the model complexity and sample quality. Human opinion studies and new state-of-the-art Inception Score (IS) / Frechet Inception Distance (FID) demonstrate the superiority of our approach over existing algorithms, advancing both the fidelity and extremity of face manipulation task. |
| Tasks | |
| Published | 2019-08-20 |
| URL | https://arxiv.org/abs/1908.07191v1 |
| https://arxiv.org/pdf/1908.07191v1.pdf | |
| PWC | https://paperswithcode.com/paper/make-a-face-towards-arbitrary-high-fidelity |
| Repo | |
| Framework | |
Crowd Counting with Deep Structured Scale Integration Network
| Title | Crowd Counting with Deep Structured Scale Integration Network |
| Authors | Lingbo Liu, Zhilin Qiu, Guanbin Li, Shufan Liu, Wanli Ouyang, Liang Lin |
| Abstract | Automatic estimation of the number of people in unconstrained crowded scenes is a challenging task and one major difficulty stems from the huge scale variation of people. In this paper, we propose a novel Deep Structured Scale Integration Network (DSSINet) for crowd counting, which addresses the scale variation of people by using structured feature representation learning and hierarchically structured loss function optimization. Unlike conventional methods which directly fuse multiple features with weighted average or concatenation, we first introduce a Structured Feature Enhancement Module based on conditional random fields (CRFs) to refine multiscale features mutually with a message passing mechanism. In this module, each scale-specific feature is considered as a continuous random variable and passes complementary information to refine the features at other scales. Second, we utilize a Dilated Multiscale Structural Similarity loss to enforce our DSSINet to learn the local correlation of people’s scales within regions of various size, thus yielding high-quality density maps. Extensive experiments on four challenging benchmarks well demonstrate the effectiveness of our method. Specifically, our DSSINet achieves improvements of 9.5% error reduction on Shanghaitech dataset and 24.9% on UCF-QNRF dataset against the state-of-the-art methods. |
| Tasks | Crowd Counting, Representation Learning |
| Published | 2019-08-23 |
| URL | https://arxiv.org/abs/1908.08692v1 |
| https://arxiv.org/pdf/1908.08692v1.pdf | |
| PWC | https://paperswithcode.com/paper/crowd-counting-with-deep-structured-scale |
| Repo | |
| Framework | |
Machine Learning Allows Calibration Models to Predict Trace Element Concentration in Soil with Generalized LIBS Spectra
| Title | Machine Learning Allows Calibration Models to Predict Trace Element Concentration in Soil with Generalized LIBS Spectra |
| Authors | Chen Sun, Ye Tian, Liang Gao, Yishuai Niu, Tianlong Zhang, Hua Li, Yuqing Zhang, Zengqi Yue, Nicole Delepine-Gilon, Jin Yu |
| Abstract | Calibration models have been developed for determination of trace elements, silver for instance, in soil using laser-induced breakdown spectroscopy (LIBS). The major concern is the matrix effect. Although it affects the accuracy of LIBS measurements in a general way, the effect appears accentuated for soil because of large variation of chemical and physical properties among different soils. The purpose is to reduce its influence in such way an accurate and soil-independent calibration model can be constructed. At the same time, the developed model should efficiently reduce experimental fluctuations affecting measurement precision. A univariate model first reveals obvious influence of matrix effect and important experimental fluctuation. A multivariate model has been then developed. A key point is the introduction of generalized spectrum where variables representing the soil type are explicitly included. Machine learning has been used to develop the model. After a necessary pretreatment where a feature selection process reduces the dimension of raw spectrum accordingly to the number of available spectra, the data have been fed in to a back-propagation neuronal networks (BPNN) to train and validate the model. The resulted soilindependent calibration model allows average relative error of calibration (REC) and average relative error of prediction (REP) within the range of 5-6%. |
| Tasks | Calibration, Feature Selection |
| Published | 2019-02-13 |
| URL | https://arxiv.org/abs/1906.08597v1 |
| https://arxiv.org/pdf/1906.08597v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-allows-calibration-models-to |
| Repo | |
| Framework | |
Intriguing Properties of Adversarial ML Attacks in the Problem Space
| Title | Intriguing Properties of Adversarial ML Attacks in the Problem Space |
| Authors | Fabio Pierazzi, Feargus Pendlebury, Jacopo Cortellazzi, Lorenzo Cavallaro |
| Abstract | Recent research efforts on adversarial ML have investigated problem-space attacks, focusing on the generation of real evasive objects in domains where, unlike images, there is no clear inverse mapping to the feature space (e.g., software). However, the design, comparison, and real-world implications of problem-space attacks remain underexplored. This paper makes two major contributions. First, we propose a novel formalization for adversarial ML evasion attacks in the problem-space, which includes the definition of a comprehensive set of constraints on available transformations, preserved semantics, robustness to preprocessing, and plausibility. We shed light on the relationship between feature space and problem space, and we introduce the concept of side-effect features as the byproduct of the inverse feature-mapping problem. This enables us to define and prove necessary and sufficient conditions for the existence of problem-space attacks. We further demonstrate the expressive power of our formalization by using it to describe several attacks from related literature across different domains. Second, building on our formalization, we propose a novel problem-space attack on Android malware that overcomes past limitations. Experiments on a dataset with 170K Android apps from 2017 and 2018 show the practical feasibility of evading a state-of-the-art malware classifier along with its hardened version. Our results demonstrate that “adversarial-malware as a service” is a realistic threat, as we automatically generate thousands of realistic and inconspicuous adversarial applications at scale, where on average it takes only a few minutes to generate an adversarial app. Our formalization of problem-space attacks paves the way to more principled research in this domain. |
| Tasks | |
| Published | 2019-11-05 |
| URL | https://arxiv.org/abs/1911.02142v2 |
| https://arxiv.org/pdf/1911.02142v2.pdf | |
| PWC | https://paperswithcode.com/paper/intriguing-properties-of-adversarial-ml |
| Repo | |
| Framework | |
Evaluating the Portability of an NLP System for Processing Echocardiograms: A Retrospective, Multi-site Observational Study
| Title | Evaluating the Portability of an NLP System for Processing Echocardiograms: A Retrospective, Multi-site Observational Study |
| Authors | Prakash Adekkanattu, Guoqian Jiang, Yuan Luo, Paul R. Kingsbury, Zhenxing Xu, Luke V. Rasmussen, Jennifer A. Pacheco, Richard C. Kiefer, Daniel J. Stone, Pascal S. Brandt, Liang Yao, Yizhen Zhong, Yu Deng, Fei Wang, Jessica S. Ancker, Thomas R. Campion, Jyotishman Pathak |
| Abstract | While natural language processing (NLP) of unstructured clinical narratives holds the potential for patient care and clinical research, portability of NLP approaches across multiple sites remains a major challenge. This study investigated the portability of an NLP system developed initially at the Department of Veterans Affairs (VA) to extract 27 key cardiac concepts from free-text or semi-structured echocardiograms from three academic medical centers: Weill Cornell Medicine, Mayo Clinic and Northwestern Medicine. While the NLP system showed high precision and recall measurements for four target concepts (aortic valve regurgitation, left atrium size at end systole, mitral valve regurgitation, tricuspid valve regurgitation) across all sites, we found moderate or poor results for the remaining concepts and the NLP system performance varied between individual sites. |
| Tasks | |
| Published | 2019-04-02 |
| URL | http://arxiv.org/abs/1905.01961v1 |
| http://arxiv.org/pdf/1905.01961v1.pdf | |
| PWC | https://paperswithcode.com/paper/190501961 |
| Repo | |
| Framework | |
Sampling low-dimensional Markovian dynamics for pre-asymptotically recovering reduced models from data with operator inference
| Title | Sampling low-dimensional Markovian dynamics for pre-asymptotically recovering reduced models from data with operator inference |
| Authors | Benjamin Peherstorfer |
| Abstract | This work introduces a method for learning low-dimensional models from data of high-dimensional black-box dynamical systems. The novelty is that the learned models are exactly the reduced models that are traditionally constructed with model reduction techniques that require full knowledge of governing equations and operators of the high-dimensional systems. Thus, the learned models are guaranteed to inherit the well-studied properties of reduced models from traditional model reduction. The key ingredient is a new data sampling scheme to obtain re-projected trajectories of high-dimensional systems that correspond to Markovian dynamics in low-dimensional subspaces. The exact recovery of reduced models from these re-projected trajectories is guaranteed pre-asymptotically under certain conditions for finite amounts of data and for a large class of systems with polynomial nonlinear terms. Numerical results demonstrate that the low-dimensional models learned with the proposed approach match reduced models from traditional model reduction up to numerical errors in practice. The numerical results further indicate that low-dimensional models fitted to re-projected trajectories are predictive even in situations where models fitted to trajectories without re-projection are inaccurate and unstable. |
| Tasks | |
| Published | 2019-08-29 |
| URL | https://arxiv.org/abs/1908.11233v1 |
| https://arxiv.org/pdf/1908.11233v1.pdf | |
| PWC | https://paperswithcode.com/paper/sampling-low-dimensional-markovian-dynamics |
| Repo | |
| Framework | |
Enhanced 3D convolutional networks for crowd counting
| Title | Enhanced 3D convolutional networks for crowd counting |
| Authors | Zhikang Zou, Huiliang Shao, Xiaoye Qu, Wei Wei, Pan Zhou |
| Abstract | Recently, convolutional neural networks (CNNs) are the leading defacto method for crowd counting. However, when dealing with video datasets, CNN-based methods still process each video frame independently, thus ignoring the powerful temporal information between consecutive frames. In this work, we propose a novel architecture termed as “temporal channel-aware” (TCA) block, which achieves the capability of exploiting the temporal interdependencies among video sequences. Specifically, we incorporate 3D convolution kernels to encode local spatio-temporal features. Furthermore, the global contextual information is encoded into modulation weights which adaptively recalibrate channel-aware feature responses. With the local and global context combined, the proposed block enhances the discriminative ability of the feature representations and contributes to more precise results in diverse scenes. By stacking TCA blocks together, we obtain the deep trainable architecture called enhanced 3D convolutional networks (E3D). The experiments on three benchmark datasets show that the proposed method delivers state-of-the-art performance. To verify the generality, an extended experiment is conducted on a vehicle dataset TRANCOS and our approach beats previous methods by large margins. |
| Tasks | Crowd Counting |
| Published | 2019-08-12 |
| URL | https://arxiv.org/abs/1908.04121v1 |
| https://arxiv.org/pdf/1908.04121v1.pdf | |
| PWC | https://paperswithcode.com/paper/enhanced-3d-convolutional-networks-for-crowd |
| Repo | |
| Framework | |
SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Counting
| Title | SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Counting |
| Authors | Junyu Gao, Qi Wang, Yuan Yuan |
| Abstract | Recently, crowd counting is a hot topic in crowd analysis. Many CNN-based counting algorithms attain good performance. However, these methods only focus on the local appearance features of crowd scenes but ignore the large-range pixel-wise contextual and crowd attention information. To remedy the above problems, in this paper, we introduce the Spatial-/Channel-wise Attention Models into the traditional Regression CNN to estimate the density map, which is named as “SCAR”. It consists of two modules, namely Spatial-wise Attention Model (SAM) and Channel-wise Attention Model (CAM). The former can encode the pixel-wise context of the entire image to more accurately predict density maps at the pixel level. The latter attempts to extract more discriminative features among different channels, which aids model to pay attention to the head region, the core of crowd scenes. Intuitively, CAM alleviates the mistaken estimation for background regions. Finally, two types of attention information and traditional CNN’s feature maps are integrated by a concatenation operation. Furthermore, the extensive experiments are conducted on four popular datasets, Shanghai Tech Part A/B, GCC, and UCF_CC_50 Dataset. The results show that the proposed method achieves state-of-the-art results. |
| Tasks | Crowd Counting |
| Published | 2019-08-10 |
| URL | https://arxiv.org/abs/1908.03716v1 |
| https://arxiv.org/pdf/1908.03716v1.pdf | |
| PWC | https://paperswithcode.com/paper/scar-spatial-channel-wise-attention |
| Repo | |
| Framework | |
Attend To Count: Crowd Counting with Adaptive Capacity Multi-scale CNNs
| Title | Attend To Count: Crowd Counting with Adaptive Capacity Multi-scale CNNs |
| Authors | Zhikang Zou, Yu Cheng, Xiaoye Qu, Shouling Ji, Xiaoxiao Guo, Pan Zhou |
| Abstract | Crowd counting is a challenging task due to the large variations in crowd distributions. Previous methods tend to tackle the whole image with a single fixed structure, which is unable to handle diverse complicated scenes with different crowd densities. Hence, we propose the Adaptive Capacity Multi-scale convolutional neural networks (ACM-CNN), a novel crowd counting approach which can assign different capacities to different portions of the input. The intuition is that the model should focus on important regions of the input image and optimize its capacity allocation conditioning on the crowd intensive degree. ACM-CNN consists of three types of modules: a coarse network, a fine network, and a smooth network. The coarse network is used to explore the areas that need to be focused via count attention mechanism, and generate a rough feature map. Then the fine network processes the areas of interest into a fine feature map. To alleviate the sense of division caused by fusion, the smooth network is designed to combine two feature maps organically to produce high-quality density maps. Extensive experiments are conducted on five mainstream datasets. The results demonstrate the effectiveness of the proposed model for both density estimation and crowd counting tasks. |
| Tasks | Crowd Counting, Density Estimation |
| Published | 2019-08-07 |
| URL | https://arxiv.org/abs/1908.02797v2 |
| https://arxiv.org/pdf/1908.02797v2.pdf | |
| PWC | https://paperswithcode.com/paper/attend-to-count-crowd-counting-with-adaptive |
| Repo | |
| Framework | |
