Recovering the 3D shape of an object from single or multiple images with deep neural networks has been attracting increasing attention in the past few years. Mainstream works (e.g. 3D-R2N2) use recurrent neural networks (RNNs) to sequentially fuse feature maps of input images. However, RNN-based approaches are unable to produce consistent reconstruction results when given the same input images with different orders. Moreover, RNNs may forget important features from early input images due to long-term memory loss. To address these issues, we propose a novel framework for single-view and multi-view 3D object reconstruction, named Pix2Vox++. By using a well-designed encoder-decoder, it generates a coarse 3D volume from each input image. A multi-scale context-aware fusion module is then introduced to adaptively select high-quality reconstructions for different parts from all coarse 3D volumes to obtain a fused 3D volume. To further correct the wrongly recovered parts in the fused 3D volume, a refiner is adopted to generate the final output. Experimental results on the ShapeNet, Pix3D, and Things3D benchmarks show that Pix2Vox++ performs favorably against state-of-the-art methods in terms of both accuracy and efficiency.
We propose HookNet, a semantic segmentation model for histopathology whole-slide images, which combines context and details via multiple branches of encoder-decoder convolutional neural networks. Concentricpatches at multiple resolutions with different fields of view are used to feed different branches of HookNet, and intermediate representations are combined via a hooking mechanism. We describe a framework to design and train HookNet for achieving high-resolution semantic segmentation and introduce constraints to guarantee pixel-wise alignment in feature maps during hooking. We show the advantages of using HookNet in two histopathology image segmentation tasks where tissue type prediction accuracy strongly depends on contextual information, namely (1) multi-class tissue segmentation in breast cancer and, (2) segmentation of tertiary lymphoid structures and germinal centers in lung cancer. Weshow the superiority of HookNet when compared with single-resolution U-Net models working at different resolutions as well as with a recently published multi-resolution model for histopathology image segmentation
In this study, we present a baseline approach for AutoImplant (https://autoimplant.grand-challenge.org/) - the cranial implant design challenge, which, as suggested by the organizers, can be formulated as a volumetric shape learning task. In this task, the defective skull, the complete skull and the cranial implant are represented as binary voxel grids. To accomplish this task, the implant can be either reconstructed directly from the defective skull or obtained by taking the difference between a defective skull and a complete skull. In the latter case, a complete skull has to be reconstructed given a defective skull, which defines a volumetric shape completion problem. Our baseline approach for this task is based on the former formulation, i.e., a deep neural network is trained to predict the implants directly from the defective skulls. The approach generates high-quality implants in two steps: First, an encoder-decoder network learns a coarse representation of the implant from down-sampled, defective skulls; The coarse implant is only used to generate the bounding box of the defected region in the original high-resolution skull. Second, another encoder-decoder network is trained to generate a fine implant from the bounded area. On the test set, the proposed approach achieves an average dice similarity score (DSC) of 0.8555 and Hausdorff distance (HD) of 5.1825 mm. The code is publicly available at https://github.com/Jianningli/autoimplant.
We propose an end-to-end speaker-attributed automatic speech recognition model that unifies speaker counting, speech recognition, and speaker identification on monaural overlapped speech. Our model is built on serialized output training (SOT) with attention-based encoder-decoder, a recently proposed method for recognizing overlapped speech comprising an arbitrary number of speakers. We extend SOT by introducing a speaker inventory as an auxiliary input to produce speaker labels as well as multi-speaker transcriptions. All model parameters are optimized by speaker-attributed maximum mutual information criterion, which represents a joint probability for overlapped speech recognition and speaker identification. Experiments on LibriSpeech corpus show that our proposed method achieves significantly better speaker-attributed word error rate than the baseline that separately performs overlapped speech recognition and speaker identification.
We present a new program synthesis approach that combines an encoder-decoder based synthesis architecture with a differentiable program fixer. Our approach is inspired from the fact that human developers seldom get their program correct on the first attempt, and perform iterative testing-based program fixing to get to the desired program functionality. Similarly, our approach first learns a distribution over programs conditioned on an encoding of a set of input-output examples, and then iteratively performs fix operations using the differentiable fixer. The fixer takes as input the original examples and the current program's outputs on example inputs, and generates a new distribution over the programs with the goal of reducing the discrepancies between the current program outputs and the desired example outputs. We train our architecture end-to-end on the RobustFill domain, and show that the addition of the fixer module leads to a significant improvement on synthesis accuracy compared to using beam search.
In recent years generative models of visual data have made a great progress, and now they are able to produce images of high quality and diversity. In this work we study representations learnt by a GAN generator. First, we show that these representations can be easily projected onto semantic segmentation map using a lightweight decoder. We find that such semantic projection can be learnt from just a few annotated images. Based on this finding, we propose LayerMatch scheme for approximating the representation of a GAN generator that can be used for unsupervised domain-specific pretraining. We consider the semi-supervised learning scenario when a small amount of labeled data is available along with a large unlabeled dataset from the same domain. We find that the use of LayerMatch-pretrained backbone leads to superior accuracy compared to standard supervised pretraining on ImageNet. Moreover, this simple approach also outperforms recent semi-supervised semantic segmentation methods that use both labeled and unlabeled data during training. Source code for reproducing our experiments will be available at the time of publication.
Much recent effort has been invested in non-autoregressive neural machine translation, which appears to be an efficient alternative to state-of-the-art autoregressive machine translation on modern GPUs. In contrast to the latter, where generation is sequential, the former allows generation to be parallelized across target token positions. Some of the latest non-autoregressive models have achieved impressive translation quality-speed tradeoffs compared to autoregressive baselines. In this work, we reexamine this tradeoff and argue that autoregressive baselines can be substantially sped up without loss in accuracy. Specifically, we study autoregressive models with encoders and decoders of varied depths. Our extensive experiments show that given a sufficiently deep encoder, a single-layer autoregressive decoder can substantially outperform strong non-autoregressive models with comparable inference speed. We show that the speed disadvantage for autoregressive baselines compared to non-autoregressive methods has been overestimated in three aspects: suboptimal layer allocation, insufficient speed measurement, and lack of knowledge distillation. Our results establish a new protocol for future research toward fast, accurate machine translation. Our code is available at https://github.com/jungokasai/deep-shallow.
Due to their high computational efficiency on a continuous space, gradient optimization methods have shown great potential in the neural architecture search (NAS) domain. The mapping of network representation from the discrete space to a latent space is the key to discovering novel architectures, however, existing gradient-based methods fail to fully characterize the networks. In this paper, we propose an efficient NAS approach to optimize network architectures in a continuous space, where the latent space is built upon variational autoencoder (VAE) and graph neural networks (GNN). The framework jointly learns four components: the encoder, the performance predictor, the complexity predictor and the decoder in an end-to-end manner. The encoder and the decoder belong to a graph VAE, mapping architectures between continuous representations and network architectures. The predictors are two regression models, fitting the performance and computational complexity, respectively. Those predictors ensure the discovered architectures characterize both excellent performance and high computational efficiency. Extensive experiments demonstrate our framework not only generates appropriate continuous representations but also discovers powerful neural architectures.
Most prior work in the sequence-to-sequence paradigm focused on datasets with input sequence lengths in the hundreds of tokens due to the computational constraints of common RNN and Transformer architectures. In this paper, we study long-form abstractive text summarization, a sequence-to-sequence setting with input sequence lengths up to 100,000 tokens and output sequence lengths up to 768 tokens. We propose SEAL, a Transformer-based model, featuring a new encoder-decoder attention that dynamically extracts/selects input snippets to sparsely attend to for each output segment. Using only the original documents and summaries, we derive proxy labels that provide weak supervision for extractive layers simultaneously with regular supervision from abstractive summaries. The SEAL model achieves state-of-the-art results on existing long-form summarization tasks, and outperforms strong baseline models on a new dataset/task we introduce, Search2Wiki, with much longer input text. Since content selection is explicit in the SEAL model, a desirable side effect is that the selection can be inspected for enhanced interpretability.
Modelling the behaviours of other agents is essential for understanding how agents interact and making effective decisions. Existing methods for agent modelling commonly assume knowledge of the local observations and chosen actions of the modelled agents during execution. To eliminate this assumption, we extract representations from the local information of the controlled agent using encoder-decoder architectures. Using the observations and actions of the modelled agents during training, our models learn to extract representations about the modelled agents conditioned only on the local observations of the controlled agent. The representations are used to augment the controlled agent's decision policy which is trained via deep reinforcement learning; thus, during execution, the policy does not require access to other agents' information. We provide a comprehensive evaluation and ablations studies in cooperative, competitive and mixed multi-agent environments, showing that our method achieves higher returns than baseline methods which do not use the learned representations.
Despite their popularity, to date, the application of normalizing flows on categorical data stays limited. The current practice of using dequantization to map discrete data to a continuous space is inapplicable as categorical data has no intrinsic order. Instead, categorical data have complex and latent relations that must be inferred, like the synonymy between words. In this paper, we investigate \emph{Categorical Normalizing Flows}, that is normalizing flows for categorical data. By casting the encoding of categorical data in continuous space as a variational inference problem, we jointly optimize the continuous representation and the model likelihood. Using a factorized decoder, we introduce an inductive bias to model any interactions in the normalizing flow. As a consequence, we do not only simplify the optimization compared to having a joint decoder, but also make it possible to scale up to a large number of categories that is currently impossible with discrete normalizing flows. Based on Categorical Normalizing Flows, we propose GraphCNF a permutation-invariant generative model on graphs. GraphCNF implements a three step approach modeling the nodes, edges and adjacency matrix stepwise to increase efficiency. On molecule generation, GraphCNF outperforms both one-shot and autoregressive flow-based state-of-the-art.
The outpainting results produced by existing approaches are often too random to meet users' requirement. In this work, we take the image outpainting one step forward by allowing users to harvest personal custom outpainting results using sketches as the guidance. To this end, we propose an encoder-decoder based network to conduct sketch-guided outpainting, where two alignment modules are adopted to impose the generated content to be realistic and consistent with the provided sketches. First, we apply a holistic alignment module to make the synthesized part be similar to the real one from the global view. Second, we reversely produce the sketches from the synthesized part and encourage them be consistent with the ground-truth ones using a sketch alignment module. In this way, the learned generator will be imposed to pay more attention to fine details and be sensitive to the guiding sketches. To our knowledge, this work is the first attempt to explore the challenging yet meaningful conditional scenery image outpainting. We conduct extensive experiments on two collected benchmarks to qualitatively and quantitatively validate the effectiveness of our approach compared with the other state-of-the-art generative models.
Terrain assessment is a key aspect for autonomous exploration rovers, surrounding environment recognition is required for multiple purposes, such as optimal trajectory planning and autonomous target identification. In this work we present a technique to generate accurate three-dimensional semantic maps for Martian environment. The algorithm uses as input a stereo image acquired by a camera mounted on a rover. Firstly, images are labeled with DeepLabv3+, which is an encoder-decoder Convolutional Neural Networl (CNN). Then, the labels obtained by the semantic segmentation are combined to stereo depth-maps in a Voxel representation. We evaluate our approach on the ESA Katwijk Beach Planetary Rover Dataset.
Neural implicit shape representations are an emerging paradigm that offers many potential benefits over conventional discrete representations, including memory efficiency at a high spatial resolution. Generalizing across shapes with such neural implicit representations amounts to learning priors over the respective function space and enables geometry reconstruction from partial or noisy observations. Existing generalization methods rely on conditioning a neural network on a low-dimensional latent code that is either regressed by an encoder or jointly optimized in the auto-decoder framework. Here, we formalize learning of a shape space as a meta-learning problem and leverage gradient-based meta-learning algorithms to solve this task. We demonstrate that this approach performs on par with auto-decoder based approaches while being an order of magnitude faster at test-time inference. We further demonstrate that the proposed gradient-based method outperforms encoder-decoder based methods that leverage pooling-based set encoders.
We present Graformer, a novel Transformer-based encoder-decoder architecture for graph-to-text generation. With our novel graph self-attention, the encoding of a node relies on all nodes in the input graph - not only direct neighbors - facilitating the detection of global patterns. We represent the relation between two nodes as the length of the shortest path between them. Graformer learns to weight these node-node relations differently for different attention heads, thus virtually learning differently connected views of the input graph. We evaluate Graformer on two popular graph-to-text generation benchmarks, AGENDA and WebNLG, where it achieves strong performance while using many fewer parameters than other approaches.
Accurate real-time catheter segmentation is an important pre-requisite for robot-assisted endovascular intervention. Most of the existing learning-based methods for catheter segmentation and tracking are only trained on small-scale datasets or synthetic data due to the difficulties of ground-truth annotation. Furthermore, the temporal continuity in intraoperative imaging sequences is not fully utilised. In this paper, we present FW-Net, an end-to-end and real-time deep learning framework for endovascular intervention. The proposed FW-Net has three modules: a segmentation network with encoder-decoder architecture, a flow network to extract optical flow information, and a novel flow-guided warping function to learn the frame-to-frame temporal continuity. We show that by effectively learning temporal continuity, the network can successfully segment and track the catheters in real-time sequences using only raw ground-truth for training. Detailed validation results confirm that our FW-Net outperforms state-of-the-art techniques while achieving real-time performance.
The ever-growing amounts of visual contents captured on a daily basis necessitate the use of lossy compression methods in order to save storage space and transmission bandwidth. While extensive research efforts are devoted to improving compression techniques, every method inevitably discards information. Especially at low bit rates, this information often corresponds to semantically meaningful visual cues, so that decompression involves significant ambiguity. In spite of this fact, existing decompression algorithms typically produce only a single output, and do not allow the viewer to explore the set of images that map to the given compressed code. In this work we propose the first image decompression method to facilitate user-exploration of the diverse set of natural images that could have given rise to the compressed input code, thus granting users the ability to determine what could and what could not have been there in the original scene. Specifically, we develop a novel deep-network based decoder architecture for the ubiquitous JPEG standard, which allows traversing the set of decompressed images that are consistent with the compressed JPEG file. To allow for simple user interaction, we develop a graphical user interface comprising several intuitive exploration tools, including an automatic tool for examining specific solutions of interest. We exemplify our framework on graphical, medical and forensic use cases, demonstrating its wide range of potential applications.
High dimensional data is often assumed to be concentrated on or near a low-dimensional manifold. Autoencoders (AE) is a popular technique to learn representations of such data by pushing it through a neural network with a low dimension bottleneck while minimizing a reconstruction error. Using high capacity AE often leads to a large collection of minimizers, many of which represent a low dimensional manifold that fits the data well but generalizes poorly. Two sources of bad generalization are: extrinsic, where the learned manifold possesses extraneous parts that are far from the data; and intrinsic, where the encoder and decoder introduce arbitrary distortion in the low dimensional parameterization. An approach taken to alleviate these issues is to add a regularizer that favors a particular solution; common regularizers promote sparsity, small derivatives, or robustness to noise. In this paper, we advocate an isometry (i.e., local distance preserving) regularizer. Specifically, our regularizer encourages: (i) the decoder to be an isometry; and (ii) the encoder to be the decoder's pseudo-inverse, that is, the encoder extends the inverse of the decoder to the ambient space by orthogonal projection. In a nutshell, (i) and (ii) fix both intrinsic and extrinsic degrees of freedom and provide a non-linear generalization to principal component analysis (PCA). Experimenting with the isometry regularizer on dimensionality reduction tasks produces useful low-dimensional data representations.
Driveable area detection is a key component for various applications in the field of autonomous driving (AD), such as ground-plane detection, obstacle detection and maneuver planning. Additionally, bulky and over-parameterized networks can be easily forgone and replaced with smaller networks for faster inference on embedded systems. The driveable area detection, posed as a two class segmentation task, can be efficiently modeled with slim binary networks. This paper proposes a novel binarized driveable area detection network (binary DAD-Net), which uses only binary weights and activations in the encoder, the bottleneck, and the decoder part. The latent space of the bottleneck is efficiently increased (x32 -> x16 downsampling) through binary dilated convolutions, learning more complex features. Along with automatically generated training data, the binary DAD-Net outperforms state-of-the-art semantic segmentation networks on public datasets. In comparison to a full-precision model, our approach has a x14.3 reduced compute complexity on an FPGA and it requires only 0.9MB memory resources. Therefore, commodity SIMD-based AD-hardware is capable of accelerating the binary DAD-Net.
Generating inferential texts about an event in different perspectives requires reasoning over different contexts that the event occurs. Existing works usually ignore the context that is not explicitly provided, resulting in a context-independent semantic representation that struggles to support the generation. To address this, we propose an approach that automatically finds evidence for an event from a large text corpus, and leverages the evidence to guide the generation of inferential texts. Our approach works in an encoder-decoder manner and is equipped with a Vector Quantised-Variational Autoencoder, where the encoder outputs representations from a distribution over discrete variables. Such discrete representations enable automatically selecting relevant evidence, which not only facilitates evidence-aware generation, but also provides a natural way to uncover rationales behind the generation. Our approach provides state-of-the-art performance on both Event2Mind and ATOMIC datasets. More importantly, we find that with discrete representations, our model selectively uses evidence to generate different inferential texts.