PyTorchKR Papers

최신 논문

총 9,339편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2302.08510

Text-driven Visual Synthesis with Latent Diffusion Prior

There has been tremendous progress in large-scale text-to-image synthesis driven by diffusion models enabling versatile downstream applications such as 3D object synthesis from texts, image editing, and customized generation. We present a generic approach using latent diffusion models as powerful image priors for various visual synthesis tasks. Existing methods that utilize such priors fail to use these models' full capabilities. To improve this, our core ideas are 1) a feature matching loss between features from different layers of the decoder to provide detailed guidance and 2) a KL divergence loss to regularize the predicted latent features and stabilize the training. We demonstrate the efficacy of our approach on three different applications, text-to-3D, StyleGAN adaptation, and layered image editing. Extensive results show our method compares favorably against baselines.

arXiv:2302.08474

Efficient 3D Object Reconstruction using Visual Transformers

Reconstructing a 3D object from a 2D image is a well-researched vision problem, with many kinds of deep learning techniques having been tried. Most commonly, 3D convolutional approaches are used, though previous work has shown state-of-the-art methods using 2D convolutions that are also significantly more efficient to train. With the recent rise of transformers for vision tasks, often outperforming convolutional methods, along with some earlier attempts to use transformers for 3D object reconstruction, we set out to use visual transformers in place of convolutions in existing efficient, high-performing techniques for 3D object reconstruction in order to achieve superior results on the task. Using a transformer-based encoder and decoder to predict 3D structure from 2D images, we achieve accuracy similar or superior to the baseline approach. This study serves as evidence for the potential of visual transformers in the task of 3D object reconstruction.

arXiv:2302.08268공식 코드 · Papers with Code

Retrieval-augmented Image Captioning

Inspired by retrieval-augmented language generation and pretrained Vision and Language (V&L) encoders, we present a new approach to image captioning that generates sentences given the input image and a set of captions retrieved from a datastore, as opposed to the image alone. The encoder in our model jointly processes the image and retrieved captions using a pretrained V&L BERT, while the decoder attends to the multimodal encoder representations, benefiting from the extra textual evidence from the retrieved captions. Experimental results on the COCO dataset show that image captioning can be effectively formulated from this new perspective. Our model, named EXTRA, benefits from using captions retrieved from the training dataset, and it can also benefit from using an external dataset without the need for retraining. Ablation studies show that retrieving a sufficient number of captions (e.g., k=5) can improve captioning quality. Our work contributes towards using pretrained V&L encoders for generative tasks, instead of standard classification tasks.

arXiv:2302.07387공식 코드 · Papers with Code

PolyFormer: Referring Image Segmentation as Sequential Polygon Generation

In this work, instead of directly predicting the pixel-level segmentation masks, the problem of referring image segmentation is formulated as sequential polygon generation, and the predicted polygons can be later converted into segmentation masks. This is enabled by a new sequence-to-sequence framework, Polygon Transformer (PolyFormer), which takes a sequence of image patches and text query tokens as input, and outputs a sequence of polygon vertices autoregressively. For more accurate geometric localization, we propose a regression-based decoder, which predicts the precise floating-point coordinates directly, without any coordinate quantization error. In the experiments, PolyFormer outperforms the prior art by a clear margin, e.g., 5.40% and 4.52% absolute improvements on the challenging RefCOCO+ and RefCOCOg datasets. It also shows strong generalization ability when evaluated on the referring video segmentation task without fine-tuning, e.g., achieving competitive 61.5% J&F on the Ref-DAVIS17 dataset.

arXiv:2302.07337

Graph Attention Multi-Agent Fleet Autonomy for Advanced Air Mobility

Autonomous mobility is emerging as a new disruptive mode of urban transportation for moving cargo and passengers. However, designing scalable autonomous fleet coordination schemes to accommodate fast-growing mobility systems is challenging primarily due to the increasing heterogeneity of the fleets, time-varying demand patterns, service area expansions, and communication limitations. We introduce the concept of partially observable advanced air mobility games to coordinate a fleet of aerial vehicles by accounting for the heterogeneity of the interacting agents and the self-interested nature inherent to commercial mobility fleets. To model the complex interactions among the agents and the observation uncertainty in the mobility networks, we propose a novel heterogeneous graph attention encoder-decoder (HetGAT Enc-Dec) neural network-based stochastic policy. We train the policy by leveraging deep multi-agent reinforcement learning, allowing decentralized decision-making for the agents using their local observations. Through extensive experimentation, we show that the learned policy generalizes to various fleet compositions, demand patterns, and observation topologies. Further, fleets operating under the HetGAT Enc-Dec policy outperform other state-of-the-art graph neural network policies by achieving the highest fleet reward and fulfillment ratios in on-demand mobility networks.

arXiv:2302.06980

Deep Learning-Based Modeling of 5G Core Control Plane for 5G Network Digital Twin

Digital twin serves as a crucial facilitator in the advancement and implementation of emerging technologies within 5G and beyond networks. However, the intricate structure and diverse functionalities of the existing 5G core network, especially the control plane, present challenges in constructing core network digital twins. In this paper, we propose two novel data-driven architectures for modeling the 5G control plane and implement corresponding deep learning models, namely 5GC-Seq2Seq and 5GC-former, based on the Vanilla Seq2Seq model and Transformer decoder respectively. We also present a solution enabling the interconversion of signaling messages and length-limited vectors to construct a dataset. The experiments are based on 5G core network signaling messages collected by the Spirent C50 network tester, encompassing various procedures such as registration, handover, and PDU sessions. The results show that 5GC-Seq2Seq achieves a 99.997\% F1-score (a metric measuring the accuracy of positive samples) in single UE scenarios with a simple structure, but exhibits significantly reduced performance in handling concurrency. In contrast, 5GC-former surpasses 99.999\% F1-score while maintaining robust performance under concurrent UE scenarios by constructing a more complex and highly parallel model. These findings validate that our method accurately replicates the principal functionalities of the 5G core network control plane.

arXiv:2302.07203

Synthesizing audio from tongue motion during speech using tagged MRI via transformer

Investigating the relationship between internal tissue point motion of the tongue and oropharyngeal muscle deformation measured from tagged MRI and intelligible speech can aid in advancing speech motor control theories and developing novel treatment methods for speech related-disorders. However, elucidating the relationship between these two sources of information is challenging, due in part to the disparity in data structure between spatiotemporal motion fields (i.e., 4D motion fields) and one-dimensional audio waveforms. In this work, we present an efficient encoder-decoder translation network for exploring the predictive information inherent in 4D motion fields via 2D spectrograms as a surrogate of the audio data. Specifically, our encoder is based on 3D convolutional spatial modeling and transformer-based temporal modeling. The extracted features are processed by an asymmetric 2D convolution decoder to generate spectrograms that correspond to 4D motion fields. Furthermore, we incorporate a generative adversarial training approach into our framework to further improve synthesis quality on our generated spectrograms. We experiment on 63 paired motion field sequences and speech waveforms, demonstrating that our framework enables the generation of clear audio waveforms from a sequence of motion fields. Thus, our framework has the potential to improve our understanding of the relationship between these two modalities and inform the development of treatments for speech disorders.

arXiv:2302.06833

VQ3D: Learning a 3D-Aware Generative Model on ImageNet

Recent work has shown the possibility of training generative models of 3D content from 2D image collections on small datasets corresponding to a single object class, such as human faces, animal faces, or cars. However, these models struggle on larger, more complex datasets. To model diverse and unconstrained image collections such as ImageNet, we present VQ3D, which introduces a NeRF-based decoder into a two-stage vector-quantized autoencoder. Our Stage 1 allows for the reconstruction of an input image and the ability to change the camera position around the image, and our Stage 2 allows for the generation of new 3D scenes. VQ3D is capable of generating and reconstructing 3D-aware images from the 1000-class ImageNet dataset of 1.2 million training images. We achieve an ImageNet generation FID score of 16.8, compared to 69.8 for the next best baseline method.

arXiv:2302.05454

Distillation of encoder-decoder transformers for sequence labelling

Driven by encouraging results on a wide range of tasks, the field of NLP is experiencing an accelerated race to develop bigger language models. This race for bigger models has also underscored the need to continue the pursuit of practical distillation approaches that can leverage the knowledge acquired by these big models in a compute-efficient manner. Having this goal in mind, we build on recent work to propose a hallucination-free framework for sequence tagging that is especially suited for distillation. We show empirical results of new state-of-the-art performance across multiple sequence labelling datasets and validate the usefulness of this framework for distilling a large model in a few-shot learning scenario.

arXiv:2302.06560공식 코드 · Papers with Code

Large Scale Multi-Lingual Multi-Modal Summarization Dataset

Significant developments in techniques such as encoder-decoder models have enabled us to represent information comprising multiple modalities. This information can further enhance many downstream tasks in the field of information retrieval and natural language processing; however, improvements in multi-modal techniques and their performance evaluation require large-scale multi-modal data which offers sufficient diversity. Multi-lingual modeling for a variety of tasks like multi-modal summarization, text generation, and translation leverages information derived from high-quality multi-lingual annotated data. In this work, we present the current largest multi-lingual multi-modal summarization dataset (M3LS), and it consists of over a million instances of document-image pairs along with a professionally annotated multi-modal summary for each pair. It is derived from news articles published by British Broadcasting Corporation(BBC) over a decade and spans 20 languages, targeting diversity across five language roots, it is also the largest summarization dataset for 13 languages and consists of cross-lingual summarization data for 2 languages. We formally define the multi-lingual multi-modal summarization task utilizing our dataset and report baseline scores from various state-of-the-art summarization techniques in a multi-lingual setting. We also compare it with many similar datasets to analyze the uniqueness and difficulty of M3LS.

arXiv:2302.05965공식 코드 · Papers with Code

RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL

One of the recent best attempts at Text-to-SQL is the pre-trained language model. Due to the structural property of the SQL queries, the seq2seq model takes the responsibility of parsing both the schema items (i.e., tables and columns) and the skeleton (i.e., SQL keywords). Such coupled targets increase the difficulty of parsing the correct SQL queries especially when they involve many schema items and logic operators. This paper proposes a ranking-enhanced encoding and skeleton-aware decoding framework to decouple the schema linking and the skeleton parsing. Specifically, for a seq2seq encoder-decode model, its encoder is injected by the most relevant schema items instead of the whole unordered ones, which could alleviate the schema linking effort during SQL parsing, and its decoder first generates the skeleton and then the actual SQL query, which could implicitly constrain the SQL parsing. We evaluate our proposed framework on Spider and its three robustness variants: Spider-DK, Spider-Syn, and Spider-Realistic. The experimental results show that our framework delivers promising performance and robustness. Our code is available at https://github.com/RUCKBReasoning/RESDSQL.

arXiv:2302.06052공식 코드 · Papers with Code

CEDNet: A Cascade Encoder-Decoder Network for Dense Prediction

Multi-scale features are essential for dense prediction tasks, such as object detection, instance segmentation, and semantic segmentation. The prevailing methods usually utilize a classification backbone to extract multi-scale features and then fuse these features using a lightweight module (e.g., the fusion module in FPN and BiFPN, two typical object detection methods). However, as these methods allocate most computational resources to the classification backbone, the multi-scale feature fusion in these methods is delayed, which may lead to inadequate feature fusion. While some methods perform feature fusion from early stages, they either fail to fully leverage high-level features to guide low-level feature learning or have complex structures, resulting in sub-optimal performance. We propose a streamlined cascade encoder-decoder network, dubbed CEDNet, tailored for dense \mbox{prediction} tasks. All stages in CEDNet share the same encoder-decoder structure and perform multi-scale feature fusion within the decoder. A hallmark of CEDNet is its ability to incorporate high-level features from early stages to guide low-level feature learning in subsequent stages, thereby enhancing the effectiveness of multi-scale feature fusion. We explored three well-known encoder-decoder structures: Hourglass, UNet, and FPN. When integrated into CEDNet, they performed much better than traditional methods that use a pre-designed classification backbone combined with a lightweight fusion module. Extensive experiments on object detection, instance segmentation, and semantic segmentation demonstrated the effectiveness of our method. The code is available at https://github.com/zhanggang001/CEDNet.

arXiv:2302.05917

Vector Quantized Wasserstein Auto-Encoder

Learning deep discrete latent presentations offers a promise of better symbolic and summarized abstractions that are more useful to subsequent downstream tasks. Inspired by the seminal Vector Quantized Variational Auto-Encoder (VQ-VAE), most of work in learning deep discrete representations has mainly focused on improving the original VQ-VAE form and none of them has studied learning deep discrete representations from the generative viewpoint. In this work, we study learning deep discrete representations from the generative viewpoint. Specifically, we endow discrete distributions over sequences of codewords and learn a deterministic decoder that transports the distribution over the sequences of codewords to the data distribution via minimizing a WS distance between them. We develop further theories to connect it with the clustering viewpoint of WS distance, allowing us to have a better and more controllable clustering solution. Finally, we empirically evaluate our method on several well-known benchmarks, where it achieves better qualitative and quantitative performances than the other VQ-VAE variants in terms of the codebook utilization and image reconstruction/generation.

arXiv:2302.06185

PUPS: Point Cloud Unified Panoptic Segmentation

Point cloud panoptic segmentation is a challenging task that seeks a holistic solution for both semantic and instance segmentation to predict groupings of coherent points. Previous approaches treat semantic and instance segmentation as surrogate tasks, and they either use clustering methods or bounding boxes to gather instance groupings with costly computation and hand-crafted designs in the instance segmentation task. In this paper, we propose a simple but effective point cloud unified panoptic segmentation (PUPS) framework, which use a set of point-level classifiers to directly predict semantic and instance groupings in an end-to-end manner. To realize PUPS, we introduce bipartite matching to our training pipeline so that our classifiers are able to exclusively predict groupings of instances, getting rid of hand-crafted designs, e.g. anchors and Non-Maximum Suppression (NMS). In order to achieve better grouping results, we utilize a transformer decoder to iteratively refine the point classifiers and develop a context-aware CutMix augmentation to overcome the class imbalance problem. As a result, PUPS achieves 1st place on the leader board of SemanticKITTI panoptic segmentation task and state-of-the-art results on nuScenes.

arXiv:2302.06096

Dual-layer Image Compression via Adaptive Downsampling and Spatially Varying Upconversion

Ultra high resolution (UHR) images are almost always downsampled to fit small displays of mobile end devices and upsampled to its original resolution when exhibited on very high-resolution displays. This observation motivates us on jointly optimizing operation pairs of downsampling and upsampling that are spatially adaptive to image contents for maximal rate-distortion performance. In this paper, we propose an adaptive downsampled dual-layer (ADDL) image compression system. In the ADDL compression system, an image is reduced in resolution by learned content-adaptive downsampling kernels and compressed to form a coded base layer. For decompression the base layer is decoded and upconverted to the original resolution using a deep upsampling neural network, aided by the prior knowledge of the learned adaptive downsampling kernels. We restrict the downsampling kernels to the form of Gabor filters in order to reduce the complexity of filter optimization and also reduce the amount of side information needed by the decoder for adaptive upsampling. Extensive experiments demonstrate that the proposed ADDL compression approach of jointly optimized, spatially adaptive downsampling and upconversion outperforms the state of the art image compression methods.

arXiv:2302.05717

Learning by Applying: A General Framework for Mathematical Reasoning via Enhancing Explicit Knowledge Learning

Mathematical reasoning is one of the crucial abilities of general artificial intelligence, which requires machines to master mathematical logic and knowledge from solving problems. However, existing approaches are not transparent (thus not interpretable) in terms of what knowledge has been learned and applied in the reasoning process. In this paper, we propose a general Learning by Applying (LeAp) framework to enhance existing models (backbones) in a principled way by explicit knowledge learning. In LeAp, we perform knowledge learning in a novel problem-knowledge-expression paradigm, with a Knowledge Encoder to acquire knowledge from problem data and a Knowledge Decoder to apply knowledge for expression reasoning. The learned mathematical knowledge, including word-word relations and word-operator relations, forms an explicit knowledge graph, which bridges the knowledge "learning" and "applying" organically. Moreover, for problem solving, we design a semantics-enhanced module and a reasoning-enhanced module that apply knowledge to improve the problem comprehension and symbol reasoning abilities of any backbone, respectively. We theoretically prove the superiority of LeAp's autonomous learning mechanism. Experiments on three real-world datasets show that LeAp improves all backbones' performances, learns accurate knowledge, and achieves a more interpretable reasoning process.

arXiv:2302.05361공식 코드 · Papers with Code

Leveraging Inpainting for Single-Image Shadow Removal

Fully-supervised shadow removal methods achieve the best restoration qualities on public datasets but still generate some shadow remnants. One of the reasons is the lack of large-scale shadow & shadow-free image pairs. Unsupervised methods can alleviate the issue but their restoration qualities are much lower than those of fully-supervised methods. In this work, we find that pretraining shadow removal networks on the image inpainting dataset can reduce the shadow remnants significantly: a naive encoder-decoder network gets competitive restoration quality w.r.t. the state-of-the-art methods via only 10% shadow & shadow-free image pairs. After analyzing networks with/without inpainting pre-training via the information stored in the weight (IIW), we find that inpainting pretraining improves restoration quality in non-shadow regions and enhances the generalization ability of networks significantly. Additionally, shadow removal fine-tuning enables networks to fill in the details of shadow regions. Inspired by these observations we formulate shadow removal as an adaptive fusion task that takes advantage of both shadow removal and image inpainting. Specifically, we develop an adaptive fusion network consisting of two encoders, an adaptive fusion block, and a decoder. The two encoders are responsible for extracting the feature from the shadow image and the shadow-masked image respectively. The adaptive fusion block is responsible for combining these features in an adaptive manner. Finally, the decoder converts the adaptive fused features to the desired shadow-free result. The extensive experiments show that our method empowered with inpainting outperforms all state-of-the-art methods.

arXiv:2302.05071공식 코드 · Papers with Code

EVC: Towards Real-Time Neural Image Compression with Mask Decay

Neural image compression has surpassed state-of-the-art traditional codecs (H.266/VVC) for rate-distortion (RD) performance, but suffers from large complexity and separate models for different rate-distortion trade-offs. In this paper, we propose an Efficient single-model Variable-bit-rate Codec (EVC), which is able to run at 30 FPS with 768x512 input images and still outperforms VVC for the RD performance. By further reducing both encoder and decoder complexities, our small model even achieves 30 FPS with 1920x1080 input images. To bridge the performance gap between our different capacities models, we meticulously design the mask decay, which transforms the large model's parameters into the small model automatically. And a novel sparsity regularization loss is proposed to mitigate shortcomings of $L_p$ regularization. Our algorithm significantly narrows the performance gap by 50% and 30% for our medium and small models, respectively. At last, we advocate the scalable encoder for neural image compression. The encoding complexity is dynamic to meet different latency requirements. We propose decaying the large encoder multiple times to reduce the residual representation progressively. Both mask decay and residual representation learning greatly improve the RD performance of our scalable encoder. Our code is at https://github.com/microsoft/DCVC.

arXiv:2302.05008공식 코드 · Papers with Code

Language-Aware Multilingual Machine Translation with Self-Supervised Learning

Multilingual machine translation (MMT) benefits from cross-lingual transfer but is a challenging multitask optimization problem. This is partly because there is no clear framework to systematically learn language-specific parameters. Self-supervised learning (SSL) approaches that leverage large quantities of monolingual data (where parallel data is unavailable) have shown promise by improving translation performance as complementary tasks to the MMT task. However, jointly optimizing SSL and MMT tasks is even more challenging. In this work, we first investigate how to utilize intra-distillation to learn more *language-specific* parameters and then show the importance of these language-specific parameters. Next, we propose a novel but simple SSL task, concurrent denoising, that co-trains with the MMT task by concurrently denoising monolingual data on both the encoder and decoder. Finally, we apply intra-distillation to this co-training approach. Combining these two approaches significantly improves MMT performance, outperforming three state-of-the-art SSL methods by a large margin, e.g., 11.3\% and 3.7\% improvement on an 8-language and a 15-language benchmark compared with MASS, respectively

arXiv:2302.04676

Stacked Cross-modal Feature Consolidation Attention Networks for Image Captioning

Recently, the attention-enriched encoder-decoder framework has aroused great interest in image captioning due to its overwhelming progress. Many visual attention models directly leverage meaningful regions to generate image descriptions. However, seeking a direct transition from visual space to text is not enough to generate fine-grained captions. This paper exploits a feature-compounding approach to bring together high-level semantic concepts and visual information regarding the contextual environment fully end-to-end. Thus, we propose a stacked cross-modal feature consolidation (SCFC) attention network for image captioning in which we simultaneously consolidate cross-modal features through a novel compounding function in a multi-step reasoning fashion. Besides, we jointly employ spatial information and context-aware attributes (CAA) as the principal components in our proposed compounding function, where our CAA provides a concise context-sensitive semantic representation. To make better use of consolidated features potential, we further propose an SCFC-LSTM as the caption generator, which can leverage discriminative semantic information through the caption generation process. The experimental results indicate that our proposed SCFC can outperform various state-of-the-art image captioning benchmarks in terms of popular metrics on the MSCOCO and Flickr30K datasets.