We introduce a dynamical spatio-temporal model formalized as a recurrent neural network for forecasting time series of spatial processes, i.e. series of observations sharing temporal and spatial dependencies. The model learns these dependencies through a structured latent dynamical component, while a decoder predicts the observations from the latent representations. We consider several variants of this model, corresponding to different prior hypothesis about the spatial relations between the series. The model is evaluated and compared to state-of-the-art baselines, on a variety of forecasting problems representative of different application areas: epidemiology, geo-spatial statistics and car-traffic prediction. Besides these evaluations, we also describe experiments showing the ability of this approach to extract relevant spatial relations.
In this paper, we present a novel deep learning architecture for infrared and visible images fusion problem. In contrast to conventional convolutional networks, our encoding network is combined by convolutional layers, fusion layer and dense block in which the output of each layer is connected to every other layer. We attempt to use this architecture to get more useful features from source images in encoding process. And two fusion layers(fusion strategies) are designed to fuse these features. Finally, the fused image is reconstructed by decoder. Compared with existing fusion methods, the proposed fusion method achieves state-of-the-art performance in objective and subjective assessment. Code and pre-trained models are available at https://github.com/hli1221/imagefusion_densefuse
The ability to quickly recognize and learn new visual concepts from limited samples enables humans to swiftly adapt to new environments. This ability is enabled by semantic associations of novel concepts with those that have already been learned and stored in memory. Computers can start to ascertain similar abilities by utilizing a semantic concept space. A concept space is a high-dimensional semantic space in which similar abstract concepts appear close and dissimilar ones far apart. In this paper, we propose a novel approach to one-shot learning that builds on this idea. Our approach learns to map a novel sample instance to a concept, relates that concept to the existing ones in the concept space and generates new instances, by interpolating among the concepts, to help learning. Instead of synthesizing new image instance, we propose to directly synthesize instance features by leveraging semantics using a novel auto-encoder network we call dual TriNet. The encoder part of the TriNet learns to map multi-layer visual features of deep CNNs, that is, multi-level concepts, to a semantic vector. In semantic space, we search for related concepts, which are then projected back into the image feature spaces by the decoder portion of the TriNet. Two strategies in the semantic space are explored. Notably, this seemingly simple strategy results in complex augmented feature distributions in the image feature space, leading to substantially better performance.
We explore multitask models for neural translation of speech, augmenting them in order to reflect two intuitive notions. First, we introduce a model where the second task decoder receives information from the decoder of the first task, since higher-level intermediate representations should provide useful information. Second, we apply regularization that encourages transitivity and invertibility. We show that the application of these notions on jointly trained models improves performance on the tasks of low-resource speech transcription and translation. It also leads to better performance when using attention information for word discovery over unsegmented input.
To overcome the poor scalability of convolutional neural network, recurrent attention model(RAM) selectively choose what and where to look on the image. By directing recurrent attention model how to look the image, RAM can be even more successful in that the given clue narrow down the scope of the possible focus zone. In this perspective, this work proposes clued recurrent attention model (CRAM) which add clue or constraint on the RAM better problem solving. CRAM follows encoder-decoder framework, encoder utilizes recurrent attention model with spatial transformer network and decoder which varies depending on the task. To ensure the performance, CRAM tackles two computer vision task. One is the image classification task, with clue given as the binary image saliency which indicates the approximate location of object. The other is the inpainting task, with clue given as binary mask which indicates the occluded part. In both tasks, CRAM shows better performance than existing methods showing the successful extension of RAM.
Low-dose computed tomography (CT) has attracted a major attention in the medical imaging field, since CT-associated x-ray radiation carries health risks for patients. The reduction of CT radiation dose, however, compromises the signal-to-noise ratio, and may compromise the image quality and the diagnostic performance. Recently, deep-learning-based algorithms have achieved promising results in low-dose CT denoising, especially convolutional neural network (CNN) and generative adversarial network (GAN). This article introduces a Contracting Path-based Convolutional Encoder-decoder (CPCE) network in 2D and 3D configurations within the GAN framework for low-dose CT denoising. A novel feature of our approach is that an initial 3D CPCE denoising model can be directly obtained by extending a trained 2D CNN and then fine-tuned to incorporate 3D spatial information from adjacent slices. Based on the transfer learning from 2D to 3D, the 3D network converges faster and achieves a better denoising performance than that trained from scratch. By comparing the CPCE with recently published methods based on the simulated Mayo dataset and the real MGH dataset, we demonstrate that the 3D CPCE denoising model has a better performance, suppressing image noise and preserving subtle structures.
To see is to sketch -- free-hand sketching naturally builds ties between human and machine vision. In this paper, we present a novel approach for translating an object photo to a sketch, mimicking the human sketching process. This is an extremely challenging task because the photo and sketch domains differ significantly. Furthermore, human sketches exhibit various levels of sophistication and abstraction even when depicting the same object instance in a reference photo. This means that even if photo-sketch pairs are available, they only provide weak supervision signal to learn a translation model. Compared with existing supervised approaches that solve the problem of D(E(photo)) -> sketch, where E($\cdot$) and D($\cdot$) denote encoder and decoder respectively, we take advantage of the inverse problem (e.g., D(E(sketch)) -> photo), and combine with the unsupervised learning tasks of within-domain reconstruction, all within a multi-task learning framework. Compared with existing unsupervised approaches based on cycle consistency (i.e., D(E(D(E(photo)))) -> photo), we introduce a shortcut consistency enforced at the encoder bottleneck (e.g., D(E(photo)) -> photo) to exploit the additional self-supervision. Both qualitative and quantitative results show that the proposed model is superior to a number of state-of-the-art alternatives. We also show that the synthetic sketches can be used to train a better fine-grained sketch-based image retrieval (FG-SBIR) model, effectively alleviating the problem of sketch data scarcity.
Human motion modeling is a classic problem in computer vision and graphics. Challenges in modeling human motion include high dimensional prediction as well as extremely complicated dynamics.We present a novel approach to human motion modeling based on convolutional neural networks (CNN). The hierarchical structure of CNN makes it capable of capturing both spatial and temporal correlations effectively. In our proposed approach,a convolutional long-term encoder is used to encode the whole given motion sequence into a long-term hidden variable, which is used with a decoder to predict the remainder of the sequence. The decoder itself also has an encoder-decoder structure, in which the short-term encoder encodes a shorter sequence to a short-term hidden variable, and the spatial decoder maps the long and short-term hidden variable to motion predictions. By using such a model, we are able to capture both invariant and dynamic information of human motion, which results in more accurate predictions. Experiments show that our algorithm outperforms the state-of-the-art methods on the Human3.6M and CMU Motion Capture datasets. Our code is available at the project website.
Skip connections in deep networks have improved both segmentation and classification performance by facilitating the training of deeper network architectures, and reducing the risks for vanishing gradients. They equip encoder-decoder-like networks with richer feature representations, but at the cost of higher memory usage, computation, and possibly resulting in transferring non-discriminative feature maps. In this paper, we focus on improving skip connections used in segmentation networks (e.g., U-Net, V-Net, and The One Hundred Layers Tiramisu (DensNet) architectures). We propose light, learnable skip connections which learn to first select the most discriminative channels and then attend to the most discriminative regions of the selected feature maps. The output of the proposed skip connections is a unique feature map which not only reduces the memory usage and network parameters to a high extent, but also improves segmentation accuracy. We evaluate the proposed method on three different 2D and volumetric datasets and demonstrate that the proposed light, learnable skip connections can outperform the traditional heavy skip connections in terms of segmentation accuracy, memory usage, and number of network parameters.
The Knowledge Base (KB) used for real-world applications, such as booking a movie or restaurant reservation, keeps changing over time. End-to-end neural networks trained for these task-oriented dialogs are expected to be immune to any changes in the KB. However, existing approaches breakdown when asked to handle such changes. We propose an encoder-decoder architecture (BoSsNet) with a novel Bag-of-Sequences (BoSs) memory, which facilitates the disentangled learning of the response's language model and its knowledge incorporation. Consequently, the KB can be modified with new knowledge without a drop in interpretability. We find that BoSsNet outperforms state-of-the-art models, with considerable improvements (> 10\%) on bAbI OOV test sets and other human-human datasets. We also systematically modify existing datasets to measure disentanglement and show BoSsNet to be robust to KB modifications.
The need for fast acquisition and automatic analysis of MRI data is growing in the age of big data. Although compressed sensing magnetic resonance imaging (CS-MRI) has been studied to accelerate MRI by reducing k-space measurements, in current CS-MRI techniques MRI applications such as segmentation are overlooked when doing image reconstruction. In this paper, we test the utility of CS-MRI methods in automatic segmentation models and propose a unified deep neural network architecture called SegNetMRI which we apply to the combined CS-MRI reconstruction and segmentation problem. SegNetMRI is built upon a MRI reconstruction network with multiple cascaded blocks each containing an encoder-decoder unit and a data fidelity unit, and MRI segmentation networks having the same encoder-decoder structure. The two subnetworks are pre-trained and fine-tuned with shared reconstruction encoders. The outputs are merged into the final segmentation. Our experiments show that SegNetMRI can improve both the reconstruction and segmentation performance when using compressive measurements.
We present deep communicating agents in an encoder-decoder architecture to address the challenges of representing a long document for abstractive summarization. With deep communicating agents, the task of encoding a long text is divided across multiple collaborating agents, each in charge of a subsection of the input text. These encoders are connected to a single decoder, trained end-to-end using reinforcement learning to generate a focused and coherent summary. Empirical results demonstrate that multiple communicating encoders lead to a higher quality summary compared to several strong baselines, including those based on a single encoder or multiple non-communicating encoders.
We present the first end to end approach for real time material estimation for general object shapes with uniform material that only requires a single color image as input. In addition to Lambertian surface properties, our approach fully automatically computes the specular albedo, material shininess, and a foreground segmentation. We tackle this challenging and ill posed inverse rendering problem using recent advances in image to image translation techniques based on deep convolutional encoder decoder architectures. The underlying core representations of our approach are specular shading, diffuse shading and mirror images, which allow to learn the effective and accurate separation of diffuse and specular albedo. In addition, we propose a novel highly efficient perceptual rendering loss that mimics real world image formation and obtains intermediate results even during run time. The estimation of material parameters at real time frame rates enables exciting mixed reality applications, such as seamless illumination consistent integration of virtual objects into real world scenes, and virtual material cloning. We demonstrate our approach in a live setup, compare it to the state of the art, and demonstrate its effectiveness through quantitative and qualitative evaluation.
With parallelizable attention networks, the neural Transformer is very fast to train. However, due to the auto-regressive architecture and self-attention in the decoder, the decoding procedure becomes slow. To alleviate this issue, we propose an average attention network as an alternative to the self-attention network in the decoder of the neural Transformer. The average attention network consists of two layers, with an average layer that models dependencies on previous positions and a gating layer that is stacked over the average layer to enhance the expressiveness of the proposed attention network. We apply this network on the decoder part of the neural Transformer to replace the original target-side self-attention model. With masking tricks and dynamic programming, our model enables the neural Transformer to decode sentences over four times faster than its original version with almost no loss in training time and translation performance. We conduct a series of experiments on WMT17 translation tasks, where on 6 different language pairs, we obtain robust and consistent speed-ups in decoding.
We consider the scene text recognition problem under the attention-based encoder-decoder framework, which is the state of the art. The existing methods usually employ a frame-wise maximal likelihood loss to optimize the models. When we train the model, the misalignment between the ground truth strings and the attention's output sequences of probability distribution, which is caused by missing or superfluous characters, will confuse and mislead the training process, and consequently make the training costly and degrade the recognition accuracy. To handle this problem, we propose a novel method called edit probability (EP) for scene text recognition. EP tries to effectively estimate the probability of generating a string from the output sequence of probability distribution conditioned on the input image, while considering the possible occurrences of missing/superfluous characters. The advantage lies in that the training process can focus on the missing, superfluous and unrecognized characters, and thus the impact of the misalignment problem can be alleviated or even overcome. We conduct extensive experiments on standard benchmarks, including the IIIT-5K, Street View Text and ICDAR datasets. Experimental results show that the EP can substantially boost scene text recognition performance.
We propose a novel deep neural network architecture for the challenging problem of single image dehazing, which aims to recover the clear image from a degraded hazy image. Instead of relying on hand-crafted image priors or explicitly estimating the components of the widely used atmospheric scattering model, our end-to-end system directly generates the clear image from an input hazy image. The proposed network has an encoder-decoder architecture with skip connections and instance normalization. We adopt the convolutional layers of the pre-trained VGG network as encoder to exploit the representation power of deep features, and demonstrate the effectiveness of instance normalization for image dehazing. Our simple yet effective network outperforms the state-of-the-art methods by a large margin on the benchmark datasets.
Stylistic dialogue response generation, with valuable applications in personality-based conversational agents, is a challenging task because the response needs to be fluent, contextually-relevant, as well as paralinguistically accurate. Moreover, parallel datasets for regular-to-stylistic pairs are usually unavailable. We present three weakly-supervised models that can generate diverse polite (or rude) dialogue responses without parallel data. Our late fusion model (Fusion) merges the decoder of an encoder-attention-decoder dialogue model with a language model trained on stand-alone polite utterances. Our label-fine-tuning (LFT) model prepends to each source sequence a politeness-score scaled label (predicted by our state-of-the-art politeness classifier) during training, and at test time is able to generate polite, neutral, and rude responses by simply scaling the label embedding by the corresponding score. Our reinforcement learning model (Polite-RL) encourages politeness generation by assigning rewards proportional to the politeness classifier score of the sampled response. We also present two retrieval-based polite dialogue model baselines. Human evaluation validates that while the Fusion and the retrieval-based models achieve politeness with poorer context-relevance, the LFT and Polite-RL models can produce significantly more polite responses without sacrificing dialogue quality.
There is debate if phoneme or viseme units are the most effective for a lipreading system. Some studies use phoneme units even though phonemes describe unique short sounds; other studies tried to improve lipreading accuracy by focusing on visemes with varying results. We compare the performance of a lipreading system by modeling visual speech using either 13 viseme or 38 phoneme units. We report the accuracy of our system at both word and unit levels. The evaluation task is large vocabulary continuous speech using the TCD-TIMIT corpus. We complete our visual speech modeling via hybrid DNN-HMMs and our visual speech decoder is a Weighted Finite-State Transducer (WFST). We use DCT and Eigenlips as a representation of mouth ROI image. The phoneme lipreading system word accuracy outperforms the viseme based system word accuracy. However, the phoneme system achieved lower accuracy at the unit level which shows the importance of the dictionary for decoding classification outputs into words.
In this paper, we propose a deep learning based vehicle trajectory prediction technique which can generate the future trajectory sequence of surrounding vehicles in real time. We employ the encoder-decoder architecture which analyzes the pattern underlying in the past trajectory using the long short-term memory (LSTM) based encoder and generates the future trajectory sequence using the LSTM based decoder. This structure produces the $K$ most likely trajectory candidates over occupancy grid map by employing the beam search technique which keeps the $K$ locally best candidates from the decoder output. The experiments conducted on highway traffic scenarios show that the prediction accuracy of the proposed method is significantly higher than the conventional trajectory prediction techniques.
Conventional Open Information Extraction (Open IE) systems are usually built on hand-crafted patterns from other NLP tools such as syntactic parsing, yet they face problems of error propagation. In this paper, we propose a neural Open IE approach with an encoder-decoder framework. Distinct from existing methods, the neural Open IE approach learns highly confident arguments and relation tuples bootstrapped from a state-of-the-art Open IE system. An empirical study on a large benchmark dataset shows that the neural Open IE system significantly outperforms several baselines, while maintaining comparable computational efficiency.