Recent studies on image memorability have shed light on the visual features that make generic images, object images or face photographs memorable. However, a clear understanding and reliable estimation of natural scene memorability remain elusive. In this paper, we provide an attempt to answer: "what exactly makes natural scene memorable". Specifically, we first build LNSIM, a large-scale natural scene image memorability database (containing 2,632 images and memorability annotations). Then, we mine our database to investigate how low-, middle- and high-level handcrafted features affect the memorability of natural scene. In particular, we find that high-level feature of scene category is rather correlated with natural scene memorability. Thus, we propose a deep neural network based natural scene memorability (DeepNSM) predictor, which takes advantage of scene category. Finally, the experimental results validate the effectiveness of DeepNSM.

Cloze tests are widely adopted in language exams to evaluate students' language proficiency. In this paper, we propose the first large-scale human-created cloze test dataset CLOTH, containing questions used in middle-school and high-school language exams. With missing blanks carefully created by teachers and candidate choices purposely designed to be nuanced, CLOTH requires a deeper language understanding and a wider attention span than previously automatically-generated cloze datasets. We test the performance of dedicatedly designed baseline models including a language model trained on the One Billion Word Corpus and show humans outperform them by a significant margin. We investigate the source of the performance gap, trace model deficiencies to some distinct properties of CLOTH, and identify the limited ability of comprehending the long-term context to be the key bottleneck.

Deep Learning has a hierarchical network architecture to represent the complicated feature of input patterns. The adaptive structural learning method of Deep Belief Network (DBN) has been developed. The method can discover an optimal number of hidden neurons for given input data in a Restricted Boltzmann Machine (RBM) by neuron generation-annihilation algorithm, and generate a new hidden layer in DBN by the extension of the algorithm. In this paper, the proposed adaptive structural learning of DBN was applied to the comprehensive medical examination data for the cancer prediction. The prediction system shows higher classification accuracy (99.8% for training and 95.5% for test) than the traditional DBN. Moreover, the explicit knowledge with respect to the relation between input and output patterns was extracted from the trained DBN network by C4.5. Some characteristics extracted in the form of IF-THEN rules to find an initial cancer at the early stage were reported in this paper.

In the past few years, various advancements have been made in generative models owing to the formulation of Generative Adversarial Networks (GANs). GANs have been shown to perform exceedingly well on a wide variety of tasks pertaining to image generation and style transfer. In the field of Natural Language Processing, word embeddings such as word2vec and GLoVe are state-of-the-art methods for applying neural network models on textual data. Attempts have been made for utilizing GANs with word embeddings for text generation. This work presents an approach to text generation using Skip-Thought sentence embeddings in conjunction with GANs based on gradient penalty functions and f-measures. The results of using sentence embeddings with GANs for generating text conditioned on input information are comparable to the approaches where word embeddings are used.

We compare the robustness of humans and current convolutional deep neural networks (DNNs) on object recognition under twelve different types of image degradations. First, using three well known DNNs (ResNet-152, VGG-19, GoogLeNet) we find the human visual system to be more robust to nearly all of the tested image manipulations, and we observe progressively diverging classification error-patterns between humans and DNNs when the signal gets weaker. Secondly, we show that DNNs trained directly on distorted images consistently surpass human performance on the exact distortion types they were trained on, yet they display extremely poor generalisation abilities when tested on other distortion types. For example, training on salt-and-pepper noise does not imply robustness on uniform white noise and vice versa. Thus, changes in the noise distribution between training and testing constitutes a crucial challenge to deep learning vision systems that can be systematically addressed in a lifelong machine learning approach. Our new dataset consisting of 83K carefully measured human psychophysical trials provide a useful reference for lifelong robustness against image degradations set by the human visual system.

Inducing sparseness while training neural networks has been shown to yield models with a lower memory footprint but similar effectiveness to dense models. However, sparseness is typically induced starting from a dense model, and thus this advantage does not hold during training. We propose techniques to enforce sparseness upfront in recurrent sequence models for NLP applications, to also benefit training. First, in language modeling, we show how to increase hidden state sizes in recurrent layers without increasing the number of parameters, leading to more expressive models. Second, for sequence labeling, we show that word embeddings with predefined sparseness lead to similar performance as dense embeddings, at a fraction of the number of trainable parameters.

This paper presents an unsupervised deep learning framework called UnDEMoN for estimating dense depth map and 6-DoF camera pose information directly from monocular images. The proposed network is trained using unlabeled monocular stereo image pairs and is shown to provide superior performance in depth and ego-motion estimation compared to the existing state-of-the-art. These improvements are achieved by introducing a new objective function that aims to minimize spatial as well as temporal reconstruction losses simultaneously. These losses are defined using bi-linear sampling kernel and penalized using the Charbonnier penalty function. The objective function, thus created, provides robustness to image gradient noises thereby improving the overall estimation accuracy without resorting to any coarse to fine strategies which are currently prevalent in the literature. Another novelty lies in the fact that we combine a disparity-based depth estimation network with a pose estimation network to obtain absolute scale-aware 6 DOF Camera pose and superior depth map. The effectiveness of the proposed approach is demonstrated through performance comparison with the existing supervised and unsupervised methods on the KITTI driving dataset.

Abstract--We present a comprehensive study and evaluation of existing single image dehazing algorithms, using a new largescale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single Image DEhazing (RESIDE). RESIDE highlights diverse data sources and image contents, and is divided into five subsets, each serving different training or evaluation purposes. We further provide a rich variety of criteria for dehazing algorithm evaluation, ranging from full-reference metrics, to no-reference metrics, to subjective evaluation and the novel task-driven evaluation. Experiments on RESIDE shed light on the comparisons and limitations of state-of-the-art dehazing algorithms, and suggest promising future directions. A. Problem Description: Single Image Dehazing Images captured in outdoor scenes often suffer from poor visibility, reduced contrasts, fainted surfaces and color shift, due to the presence of haze. Caused by aerosols such as dust, mist, and fumes, the existence of haze adds complicated, nonlinear and data-dependent noise to the images, making the haze removal (a.k.a. Moreover, many computer vision algorithms can only work well with the scene radiance that is haze-free. However, a dependable vision system must reckon with the entire spectrum of degradations from unconstrained environments. Taking autonomous driving for example, hazy and foggy weather will obscure the vision of on-board cameras and create confusing reflections and glare, leaving state-of-the-art self-driving cars in struggle [1]. Boyi Li is with the Computer Science Department, Cornell University, USA.

Latest deep learning methods for object detection provide remarkable performance, but have limits when used in robotic applications. One of the most relevant issues is the long training time, which is due to the large size and imbalance of the associated training sets, characterized by few positive and a large number of negative examples (i.e. background). Proposed approaches are based on end-to-end learning by back-propagation [22] or kernel methods trained with Hard Negatives Mining on top of deep features [8]. These solutions are effective, but prohibitively slow for on-line applications. In this paper we propose a novel pipeline for object detection that overcomes this problem and provides comparable performance, with a 60x training speedup. Our pipeline combines (i) the Region Proposal Network and the deep feature extractor from [22] to efficiently select candidate RoIs and encode them into powerful representations, with (ii) the FALKON [23] algorithm, a novel kernel-based method that allows fast training on large scale problems (millions of points). We address the size and imbalance of training data by exploiting the stochastic subsampling intrinsic into the method and a novel, fast, bootstrapping approach. We assess the effectiveness of the approach on a standard Computer Vision dataset (PASCAL VOC 2007 [5]) and demonstrate its applicability to a real robotic scenario with the iCubWorld Transformations [18] dataset.

As for the humanoid robots, the internal noise, which is generated by motors, fans and mechanical components when the robot is moving or shaking its body, severely degrades the performance of the speech recognition accuracy. In this paper, a novel speech recognition system robust to ego-noise for humanoid robots is proposed, in which on/off state of the motor is employed as auxiliary information for finding the relevant input features. For this, we consider the bottleneck features, which have been successfully applied to deep neural network (DNN) based automatic speech recognition (ASR) system. When learning the bottleneck features to catch, we first exploit the motor on/off state data as supplementary information in addition to the acoustic features as the input of the first deep neural network (DNN) for preliminary acoustic modeling. Then, the second DNN for primary acoustic modeling employs both the bottleneck features tossed from the first DNN and the acoustics features. When the proposed method is evaluated in terms of phoneme error rate (PER) on TIMIT database, the experimental results show that achieve obvious improvement (11% relative) is achieved by our algorithm over the conventional systems.