Transformers have shown impressive performance in various natural language processing and computer vision tasks, due to the capability of modeling long-range dependencies. Recent progress has demonstrated that combining such Transformers with CNN-based semantic image segmentation models is very promising. However, it is not well studied yet on how well a pure Transformer based approach can achieve for image segmentation. In this work, we explore a novel framework for semantic image segmentation, which is encoder-decoder based Fully Transformer Networks (FTN). Specifically, we first propose a Pyramid Group Transformer (PGT) as the encoder for progressively learning hierarchical features, meanwhile reducing the computation complexity of the standard Visual Transformer (ViT). Then, we propose a Feature Pyramid Transformer (FPT) to fuse semantic-level and spatial-level information from multiple levels of the PGT encoder for semantic image segmentation. Surprisingly, this simple baseline can achieve better results on multiple challenging semantic segmentation and face parsing benchmarks, including PASCAL Context, ADE20K, COCOStuff, and CelebAMask-HQ. The source code will be released on https://github.com/BR-IDL/PaddleViT.
Occluded person re-identification (Re-ID) is a challenging task as persons are frequently occluded by various obstacles or other persons, especially in the crowd scenario. To address these issues, we propose a novel end-to-end Part-Aware Transformer (PAT) for occluded person Re-ID through diverse part discovery via a transformer encoderdecoder architecture, including a pixel context based transformer encoder and a part prototype based transformer decoder. The proposed PAT model enjoys several merits. First, to the best of our knowledge, this is the first work to exploit the transformer encoder-decoder architecture for occluded person Re-ID in a unified deep model. Second, to learn part prototypes well with only identity labels, we design two effective mechanisms including part diversity and part discriminability. Consequently, we can achieve diverse part discovery for occluded person Re-ID in a weakly supervised manner. Extensive experimental results on six challenging benchmarks for three tasks (occluded, partial and holistic Re-ID) demonstrate that our proposed PAT performs favorably against stat-of-the-art methods.
We present BERTGEN, a novel generative, decoder-only model which extends BERT by fusing multimodal and multilingual pretrained models VL-BERT and M-BERT, respectively. BERTGEN is auto-regressively trained for language generation tasks, namely image captioning, machine translation and multimodal machine translation, under a multitask setting. With a comprehensive set of evaluations, we show that BERTGEN outperforms many strong baselines across the tasks explored. We also show BERTGEN's ability for zero-shot language generation, where it exhibits competitive performance to supervised counterparts. Finally, we conduct ablation studies which demonstrate that BERTGEN substantially benefits from multi-tasking and effectively transfers relevant inductive biases from the pre-trained models.
Distributed source coding (DSC) is the task of encoding an input in the absence of correlated side information that is only available to the decoder. Remarkably, Slepian and Wolf showed in 1973 that an encoder without access to the side information can asymptotically achieve the same compression rate as when the side information is available to it. While there is vast prior work on this topic, practical DSC has been limited to synthetic datasets and specific correlation structures. Here we present a framework for lossy DSC that is agnostic to the correlation structure and can scale to high dimensions. Rather than relying on hand-crafted source modeling, our method utilizes a conditional Vector-Quantized Variational Autoencoder (VQ-VAE) to learn the distributed encoder and decoder. We evaluate our method on multiple datasets and show that our method can handle complex correlations and achieves state-of-the-art PSNR. Our code is made available at https://github.com/acnagle/neural-dsc.
Keyword spotting aims to identify specific keyword audio utterances. In recent years, deep convolutional neural networks have been widely utilized in keyword spotting systems. However, their model architectures are mainly based on off-the shelfbackbones such as VGG-Net or ResNet, instead of specially designed for the task. In this paper, we utilize neural architecture search to design convolutional neural network models that can boost the performance of keyword spotting while maintaining an acceptable memory footprint. Specifically, we search the model operators and their connections in a specific search space with Encoder-Decoder neural architecture optimization. Extensive evaluations on Google's Speech Commands Dataset show that the model architecture searched by our approach achieves a state-of-the-art accuracy of over 97%.
We consider a linear autoencoder in which the latent variables are quantized, or corrupted by noise, and the constraint is Schur-concave in the set of latent variances. Although finding the optimal encoder/decoder pair for this setup is a nonconvex optimization problem, we show that decomposing the source into its principal components is optimal. If the constraint is strictly Schur-concave and the empirical covariance matrix has only simple eigenvalues, then any optimal encoder/decoder must decompose the source in this way. As one application, we consider a strictly Schur-concave constraint that estimates the number of bits needed to represent the latent variables under fixed-rate encoding, a setup that we call \emph{Principal Bit Analysis (PBA)}. This yields a practical, general-purpose, fixed-rate compressor that outperforms existing algorithms. As a second application, we show that a prototypical autoencoder-based variable-rate compressor is guaranteed to decompose the source into its principal components.
In this paper, we present Uformer, an effective and efficient Transformer-based architecture for image restoration, in which we build a hierarchical encoder-decoder network using the Transformer block. In Uformer, there are two core designs. First, we introduce a novel locally-enhanced window (LeWin) Transformer block, which performs nonoverlapping window-based self-attention instead of global self-attention. It significantly reduces the computational complexity on high resolution feature map while capturing local context. Second, we propose a learnable multi-scale restoration modulator in the form of a multi-scale spatial bias to adjust features in multiple layers of the Uformer decoder. Our modulator demonstrates superior capability for restoring details for various image restoration tasks while introducing marginal extra parameters and computational cost. Powered by these two designs, Uformer enjoys a high capability for capturing both local and global dependencies for image restoration. To evaluate our approach, extensive experiments are conducted on several image restoration tasks, including image denoising, motion deblurring, defocus deblurring and deraining. Without bells and whistles, our Uformer achieves superior or comparable performance compared with the state-of-the-art algorithms. The code and models are available at https://github.com/ZhendongWang6/Uformer.
As an important step towards visual reasoning, visual grounding (e.g., phrase localization, referring expression comprehension/segmentation) has been widely explored Previous approaches to referring expression comprehension (REC) or segmentation (RES) either suffer from limited performance, due to a two-stage setup, or require the designing of complex task-specific one-stage architectures. In this paper, we propose a simple one-stage multi-task framework for visual grounding tasks. Specifically, we leverage a transformer architecture, where two modalities are fused in a visual-lingual encoder. In the decoder, the model learns to generate contextualized lingual queries which are then decoded and used to directly regress the bounding box and produce a segmentation mask for the corresponding referred regions. With this simple but highly contextualized model, we outperform state-of-the-arts methods by a large margin on both REC and RES tasks. We also show that a simple pre-training schedule (on an external dataset) further improves the performance. Extensive experiments and ablations illustrate that our model benefits greatly from contextualized information and multi-task training.
Lossy compression algorithms are typically designed to achieve the lowest possible distortion at a given bit rate. However, recent studies show that pursuing high perceptual quality would lead to increase of the lowest achievable distortion (e.g., MSE). This paper provides nontrivial results theoretically revealing that, \textit{1}) the cost of achieving perfect perception quality is exactly a doubling of the lowest achievable MSE distortion, \textit{2}) an optimal encoder for the "classic" rate-distortion problem is also optimal for the perceptual compression problem, \textit{3}) distortion loss is unnecessary for training a perceptual decoder. Further, we propose a novel training framework to achieve the lowest MSE distortion under perfect perception constraint at a given bit rate. This framework uses a GAN with discriminator conditioned on an MSE-optimized encoder, which is superior over the traditional framework using distortion plus adversarial loss. Experiments are provided to verify the theoretical finding and demonstrate the superiority of the proposed training framework.
To highlight the challenges of achieving representation disentanglement for text domain in an unsupervised setting, in this paper we select a representative set of successfully applied models from the image domain. We evaluate these models on 6 disentanglement metrics, as well as on downstream classification tasks and homotopy. To facilitate the evaluation, we propose two synthetic datasets with known generative factors. Our experiments highlight the existing gap in the text domain and illustrate that certain elements such as representation sparsity (as an inductive bias), or representation coupling with the decoder could impact disentanglement. To the best of our knowledge, our work is the first attempt on the intersection of unsupervised representation disentanglement and text, and provides the experimental framework and datasets for examining future developments in this direction.
Automatic extraction of product attribute values is an important enabling technology in e-Commerce platforms. This task is usually modeled using sequence labeling architectures, with several extensions to handle multi-attribute extraction. One line of previous work constructs attribute-specific models, through separate decoders or entirely separate models. However, this approach constrains knowledge sharing across different attributes. Other contributions use a single multi-attribute model, with different techniques to embed attribute information. But sharing the entire network parameters across all attributes can limit the model's capacity to capture attribute-specific characteristics. In this paper we present AdaTag, which uses adaptive decoding to handle extraction. We parameterize the decoder with pretrained attribute embeddings, through a hypernetwork and a Mixture-of-Experts (MoE) module. This allows for separate, but semantically correlated, decoders to be generated on the fly for different attributes. This approach facilitates knowledge sharing, while maintaining the specificity of each attribute. Our experiments on a real-world e-Commerce dataset show marked improvements over previous methods.
Dialogue policy learning, a subtask that determines the content of system response generation and then the degree of task completion, is essential for task-oriented dialogue systems. However, the unbalanced distribution of system actions in dialogue datasets often causes difficulty in learning to generate desired actions and responses. In this paper, we propose a retrieve-and-memorize framework to enhance the learning of system actions. Specially, we first design a neural context-aware retrieval module to retrieve multiple candidate system actions from the training set given a dialogue context. Then, we propose a memory-augmented multi-decoder network to generate the system actions conditioned on the candidate actions, which allows the network to adaptively select key information in the candidate actions and ignore noises. We conduct experiments on the large-scale multi-domain task-oriented dialogue dataset MultiWOZ 2.0 and MultiWOZ 2.1. Experimental results show that our method achieves competitive performance among several state-of-the-art models in the context-to-response generation task.
Despite the prominence of neural abstractive summarization models, we know little about how they actually form summaries and how to understand where their decisions come from. We propose a two-step method to interpret summarization model decisions. We first analyze the model's behavior by ablating the full model to categorize each decoder decision into one of several generation modes: roughly, is the model behaving like a language model, is it relying heavily on the input, or is it somewhere in between? After isolating decisions that do depend on the input, we explore interpreting these decisions using several different attribution methods. We compare these techniques based on their ability to select content and reconstruct the model's predicted token from perturbations of the input, thus revealing whether highlighted attributions are truly important for the generation of the next token. While this machinery can be broadly useful even beyond summarization, we specifically demonstrate its capability to identify phrases the summarization model has memorized and determine where in the training pipeline this memorization happened, as well as study complex generation phenomena like sentence fusion on a per-instance basis.
We present a novel method for predicting accurate depths from monocular images with high efficiency. This optimal efficiency is achieved by exploiting wavelet decomposition, which is integrated in a fully differentiable encoder-decoder architecture. We demonstrate that we can reconstruct high-fidelity depth maps by predicting sparse wavelet coefficients. In contrast with previous works, we show that wavelet coefficients can be learned without direct supervision on coefficients. Instead we supervise only the final depth image that is reconstructed through the inverse wavelet transform. We additionally show that wavelet coefficients can be learned in fully self-supervised scenarios, without access to ground-truth depth. Finally, we apply our method to different state-of-the-art monocular depth estimation models, in each case giving similar or better results compared to the original model, while requiring less than half the multiply-adds in the decoder network. Code at https://github.com/nianticlabs/wavelet-monodepth
Vision-language pre-training (VLP) on large-scale image-text pairs has achieved huge success for the cross-modal downstream tasks. The most existing pre-training methods mainly adopt a two-step training procedure, which firstly employs a pre-trained object detector to extract region-based visual features, then concatenates the image representation and text embedding as the input of Transformer to train. However, these methods face problems of using task-specific visual representation of the specific object detector for generic cross-modal understanding, and the computation inefficiency of two-stage pipeline. In this paper, we propose the first end-to-end vision-language pre-trained model for both V+L understanding and generation, namely E2E-VLP, where we build a unified Transformer framework to jointly learn visual representation, and semantic alignments between image and text. We incorporate the tasks of object detection and image captioning into pre-training with a unified Transformer encoder-decoder architecture for enhancing visual learning. An extensive set of experiments have been conducted on well-established vision-language downstream tasks to demonstrate the effectiveness of this novel VLP paradigm.
Medical image segmentation, or computing voxelwise semantic masks, is a fundamental yet challenging task to compute a voxel-level semantic mask. To increase the ability of encoder-decoder neural networks to perform this task across large clinical cohorts, contrastive learning provides an opportunity to stabilize model initialization and enhance encoders without labels. However, multiple target objects (with different semantic meanings) may exist in a single image, which poses a problem for adapting traditional contrastive learning methods from prevalent 'image-level classification' to 'pixel-level segmentation'. In this paper, we propose a simple semantic-aware contrastive learning approach leveraging attention masks to advance multi-object semantic segmentation. Briefly, we embed different semantic objects to different clusters rather than the traditional image-level embeddings. We evaluate our proposed method on a multi-organ medical image segmentation task with both in-house data and MICCAI Challenge 2015 BTCV datasets. Compared with current state-of-the-art training strategies, our proposed pipeline yields a substantial improvement of 5.53% and 6.09% on Dice score for both medical image segmentation cohorts respectively (p-value<0.01). The performance of the proposed method is further assessed on natural images via the PASCAL VOC 2012 dataset, and achieves a substantial improvement of 2.75% on mIoU (p-value<0.01).
Emotion detection in dialogues is challenging as it often requires the identification of thematic topics underlying a conversation, the relevant commonsense knowledge, and the intricate transition patterns between the affective states. In this paper, we propose a Topic-Driven Knowledge-Aware Transformer to handle the challenges above. We firstly design a topic-augmented language model (LM) with an additional layer specialized for topic detection. The topic-augmented LM is then combined with commonsense statements derived from a knowledge base based on the dialogue contextual information. Finally, a transformer-based encoder-decoder architecture fuses the topical and commonsense information, and performs the emotion label sequence prediction. The model has been experimented on four datasets in dialogue emotion detection, demonstrating its superiority empirically over the existing state-of-the-art approaches. Quantitative and qualitative results show that the model can discover topics which help in distinguishing emotion categories.
Existing conversational recommendation (CR) systems usually suffer from insufficient item information when conducted on short dialogue history and unfamiliar items. Incorporating external information (e.g., reviews) is a potential solution to alleviate this problem. Given that reviews often provide a rich and detailed user experience on different interests, they are potential ideal resources for providing high-quality recommendations within an informative conversation. In this paper, we design a novel end-to-end framework, namely, Review-augmented Conversational Recommender (RevCore), where reviews are seamlessly incorporated to enrich item information and assist in generating both coherent and informative responses. In detail, we extract sentiment-consistent reviews, perform review-enriched and entity-based recommendations for item suggestions, as well as use a review-attentive encoder-decoder for response generation. Experimental results demonstrate the superiority of our approach in yielding better performance on both recommendation and conversation responding.
This paper develops probabilistic PV forecasters by taking advantage of recent breakthroughs in deep learning. It tailored forecasting tool, named encoder-decoder, is implemented to compute intraday multi-output PV quantiles forecasts to efficiently capture the time correlation. The models are trained using quantile regression, a non-parametric approach that assumes no prior knowledge of the probabilistic forecasting distribution. The case study is composed of PV production monitored on-site at the University of Li\`ege (ULi\`ege), Belgium. The weather forecasts from the regional climate model provided by the Laboratory of Climatology are used as inputs of the deep learning models. The forecast quality is quantitatively assessed by the continuous ranked probability and interval scores. The results indicate this architecture improves the forecast quality and is computationally efficient to be incorporated in an intraday decision-making tool for robust optimization.
Autonomous mobile robots are usually faced with challenging situations when driving in complex environments. Namely, they have to recognize the static and dynamic obstacles, plan the driving path and execute their motion. For addressing the issue of perception and path planning, in this paper, we introduce OctoPath , which is an encoder-decoder deep neural network, trained in a self-supervised manner to predict the local optimal trajectory for the ego-vehicle. Using the discretization provided by a 3D octree environment model, our approach reformulates trajectory prediction as a classification problem with a configurable resolution. During training, OctoPath minimizes the error between the predicted and the manually driven trajectories in a given training dataset. This allows us to avoid the pitfall of regression-based trajectory estimation, in which there is an infinite state space for the output trajectory points. Environment sensing is performed using a 40-channel mechanical LiDAR sensor, fused with an inertial measurement unit and wheels odometry for state estimation. The experiments are performed both in simulation and real-life, using our own developed GridSim simulator and RovisLab's Autonomous Mobile Test Unit platform. We evaluate the predictions of OctoPath in different driving scenarios, both indoor and outdoor, while benchmarking our system against a baseline hybrid A-Star algorithm and a regression-based supervised learning method, as well as against a CNN learning-based optimal path planning method.