PyTorchKR Papers

최신 논문

총 9,339편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2210.00543공식 코드 · Papers with Code

Fine-grained Contrastive Learning for Definition Generation

Recently, pre-trained transformer-based models have achieved great success in the task of definition generation (DG). However, previous encoder-decoder models lack effective representation learning to contain full semantic components of the given word, which leads to generating under-specific definitions. To address this problem, we propose a novel contrastive learning method, encouraging the model to capture more detailed semantic representations from the definition sequence encoding. According to both automatic and manual evaluation, the experimental results on three mainstream benchmarks demonstrate that the proposed method could generate more specific and high-quality definitions compared with several state-of-the-art models.

arXiv:2210.00765

Few-Shot Segmentation via Rich Prototype Generation and Recurrent Prediction Enhancement

Prototype learning and decoder construction are the keys for few-shot segmentation. However, existing methods use only a single prototype generation mode, which can not cope with the intractable problem of objects with various scales. Moreover, the one-way forward propagation adopted by previous methods may cause information dilution from registered features during the decoding process. In this research, we propose a rich prototype generation module (RPGM) and a recurrent prediction enhancement module (RPEM) to reinforce the prototype learning paradigm and build a unified memory-augmented decoder for few-shot segmentation, respectively. Specifically, the RPGM combines superpixel and K-means clustering to generate rich prototype features with complementary scale relationships and adapt the scale gap between support and query images. The RPEM utilizes the recurrent mechanism to design a round-way propagation decoder. In this way, registered features can provide object-aware information continuously. Experiments show that our method consistently outperforms other competitors on two popular benchmarks PASCAL-${{5}^{i}}$ and COCO-${{20}^{i}}$.

arXiv:2210.00519공식 코드 · Papers with Code

Exploiting More Information in Sparse Point Cloud for 3D Single Object Tracking

3D single object tracking is a key task in 3D computer vision. However, the sparsity of point clouds makes it difficult to compute the similarity and locate the object, posing big challenges to the 3D tracker. Previous works tried to solve the problem and improved the tracking performance in some common scenarios, but they usually failed in some extreme sparse scenarios, such as for tracking objects at long distances or partially occluded. To address the above problems, in this letter, we propose a sparse-to-dense and transformer-based framework for 3D single object tracking. First, we transform the 3D sparse points into 3D pillars and then compress them into 2D BEV features to have a dense representation. Then, we propose an attention-based encoder to achieve global similarity computation between template and search branches, which could alleviate the influence of sparsity. Meanwhile, the encoder applies the attention on multi-scale features to compensate for the lack of information caused by the sparsity of point cloud and the single scale of features. Finally, we use set-prediction to track the object through a two-stage decoder which also utilizes attention. Extensive experiments show that our method achieves very promising results on the KITTI and NuScenes datasets.

arXiv:2210.01069

Dual-former: Hybrid Self-attention Transformer for Efficient Image Restoration

Recently, image restoration transformers have achieved comparable performance with previous state-of-the-art CNNs. However, how to efficiently leverage such architectures remains an open problem. In this work, we present Dual-former whose critical insight is to combine the powerful global modeling ability of self-attention modules and the local modeling ability of convolutions in an overall architecture. With convolution-based Local Feature Extraction modules equipped in the encoder and the decoder, we only adopt a novel Hybrid Transformer Block in the latent layer to model the long-distance dependence in spatial dimensions and handle the uneven distribution between channels. Such a design eliminates the substantial computational complexity in previous image restoration transformers and achieves superior performance on multiple image restoration tasks. Experiments demonstrate that Dual-former achieves a 1.91dB gain over the state-of-the-art MAXIM method on the Indoor dataset for single image dehazing while consuming only 4.2% GFLOPs as MAXIM. For single image deraining, it exceeds the SOTA method by 0.1dB PSNR on the average results of five datasets with only 21.5% GFLOPs. Dual-former also substantially surpasses the latest desnowing method on various datasets, with fewer parameters.

arXiv:2210.00637공식 코드 · Papers with Code

Benign Autoencoders

Recent progress in Generative Artificial Intelligence (AI) relies on efficient data representations, often featuring encoder-decoder architectures. We formalize the mathematical problem of finding the optimal encoder-decoder pair and characterize its solution, which we name the "benign autoencoder" (BAE). We prove that BAE projects data onto a manifold whose dimension is the optimal compressibility dimension of the generative problem. We highlight surprising connections between BAE and several recent developments in AI, such as conditional GANs, context encoders, stable diffusion, stacked autoencoders, and the learning capabilities of generative models. As an illustration, we show how BAE can find optimal, low-dimensional latent representations that improve the performance of a discriminator under a distribution shift. By compressing "malignant" data dimensions, BAE leads to smoother and more stable gradients.

arXiv:2210.00313공식 코드 · Papers with Code

CRISP: Curriculum based Sequential Neural Decoders for Polar Code Family

Polar codes are widely used state-of-the-art codes for reliable communication that have recently been included in the 5th generation wireless standards (5G). However, there remains room for the design of polar decoders that are both efficient and reliable in the short blocklength regime. Motivated by recent successes of data-driven channel decoders, we introduce a novel $\textbf{C}$ur$\textbf{RI}$culum based $\textbf{S}$equential neural decoder for $\textbf{P}$olar codes (CRISP). We design a principled curriculum, guided by information-theoretic insights, to train CRISP and show that it outperforms the successive-cancellation (SC) decoder and attains near-optimal reliability performance on the Polar(32,16) and Polar(64,22) codes. The choice of the proposed curriculum is critical in achieving the accuracy gains of CRISP, as we show by comparing against other curricula. More notably, CRISP can be readily extended to Polarization-Adjusted-Convolutional (PAC) codes, where existing SC decoders are significantly less reliable. To the best of our knowledge, CRISP constructs the first data-driven decoder for PAC codes and attains near-optimal performance on the PAC(32,16) code.

arXiv:2209.15200공식 코드 · Papers with Code

An efficient encoder-decoder architecture with top-down attention for speech separation

Deep neural networks have shown excellent prospects in speech separation tasks. However, obtaining good results while keeping a low model complexity remains challenging in real-world applications. In this paper, we provide a bio-inspired efficient encoder-decoder architecture by mimicking the brain's top-down attention, called TDANet, with decreased model complexity without sacrificing performance. The top-down attention in TDANet is extracted by the global attention (GA) module and the cascaded local attention (LA) layers. The GA module takes multi-scale acoustic features as input to extract global attention signal, which then modulates features of different scales by direct top-down connections. The LA layers use features of adjacent layers as input to extract the local attention signal, which is used to modulate the lateral input in a top-down manner. On three benchmark datasets, TDANet consistently achieved competitive separation performance to previous state-of-the-art (SOTA) methods with higher efficiency. Specifically, TDANet's multiply-accumulate operations (MACs) are only 5\% of Sepformer, one of the previous SOTA models, and CPU inference time is only 10\% of Sepformer. In addition, a large-size version of TDANet obtained SOTA results on three datasets, with MACs still only 10\% of Sepformer and the CPU inference time only 24\% of Sepformer.

arXiv:2209.15614공식 코드 · Papers with Code

TinyTurbo: Efficient Turbo Decoders on Edge

In this paper, we introduce a neural-augmented decoder for Turbo codes called TINYTURBO . TINYTURBO has complexity comparable to the classical max-log-MAP algorithm but has much better reliability than the max-log-MAP baseline and performs close to the MAP algorithm. We show that TINYTURBO exhibits strong robustness on a variety of practical channels of interest, such as EPA and EVA channels, which are included in the LTE standards. We also show that TINYTURBO strongly generalizes across different rate, blocklengths, and trellises. We verify the reliability and efficiency of TINYTURBO via over-the-air experiments.

arXiv:2209.15258

Transformers for Object Detection in Large Point Clouds

We present TransLPC, a novel detection model for large point clouds that is based on a transformer architecture. While object detection with transformers has been an active field of research, it has proved difficult to apply such models to point clouds that span a large area, e.g. those that are common in autonomous driving, with lidar or radar data. TransLPC is able to remedy these issues: The structure of the transformer model is modified to allow for larger input sequence lengths, which are sufficient for large point clouds. Besides this, we propose a novel query refinement technique to improve detection accuracy, while retaining a memory-friendly number of transformer decoder queries. The queries are repositioned between layers, moving them closer to the bounding box they are estimating, in an efficient manner. This simple technique has a significant effect on detection accuracy, which is evaluated on the challenging nuScenes dataset on real-world lidar data. Besides this, the proposed method is compatible with existing transformer-based solutions that require object detection, e.g. for joint multi-object tracking and detection, and enables them to be used in conjunction with large point clouds.

arXiv:2209.15121

Heterogeneous reconstruction of deformable atomic models in Cryo-EM

Cryogenic electron microscopy (cryo-EM) provides a unique opportunity to study the structural heterogeneity of biomolecules. Being able to explain this heterogeneity with atomic models would help our understanding of their functional mechanisms but the size and ruggedness of the structural space (the space of atomic 3D cartesian coordinates) presents an immense challenge. Here, we describe a heterogeneous reconstruction method based on an atomistic representation whose deformation is reduced to a handful of collective motions through normal mode analysis. Our implementation uses an autoencoder. The encoder jointly estimates the amplitude of motion along the normal modes and the 2D shift between the center of the image and the center of the molecule . The physics-based decoder aggregates a representation of the heterogeneity readily interpretable at the atomic level. We illustrate our method on 3 synthetic datasets corresponding to different distributions along a simulated trajectory of adenylate kinase transitioning from its open to its closed structures. We show for each distribution that our approach is able to recapitulate the intermediate atomic models with atomic-level accuracy.

arXiv:2209.15323공식 코드 · Papers with Code

SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation

Recent advances in image captioning have focused on scaling the data and model size, substantially increasing the cost of pre-training and finetuning. As an alternative to large models, we present SmallCap, which generates a caption conditioned on an input image and related captions retrieved from a datastore. Our model is lightweight and fast to train, as the only learned parameters are in newly introduced cross-attention layers between a pre-trained CLIP encoder and GPT-2 decoder. SmallCap can transfer to new domains without additional finetuning and can exploit large-scale data in a training-free fashion since the contents of the datastore can be readily replaced. Our experiments show that SmallCap, trained only on COCO, has competitive performance on this benchmark, and also transfers to other domains without retraining, solely through retrieval from target-domain data. Further improvement is achieved through the training-free exploitation of diverse human-labeled and web data, which proves to be effective for a range of domains, including the nocaps benchmark, designed to test generalization to unseen visual concepts.

arXiv:2209.14694

GROOT: Corrective Reward Optimization for Generative Sequential Labeling

Sequential labeling is a fundamental NLP task, forming the backbone of many applications. Supervised learning of Seq2Seq models has shown great success on these problems. However, the training objectives are still significantly disconnected with the metrics and desiderata we care about in practice. For example, a practical sequence tagging application may want to optimize for a certain precision-recall trade-off (of the top-k predictions) which is quite different from the standard objective of maximizing the likelihood of the gold labeled sequence. Thus to bridge this gap, we propose GROOT -- a simple yet effective framework for Generative Reward Optimization Of Text sequences. GROOT works by training a generative sequential labeling model to match the decoder output distribution with that of the (black-box) reward function. Using an iterative training regime, we first generate prediction candidates, then correct errors in them, and finally contrast those candidates (based on their reward values). As demonstrated via extensive experiments on four public benchmarks, GROOT significantly improves all reward metrics. Furthermore, GROOT leads to improvements of the overall decoder distribution as evidenced by the quality gains of the top-$k$ candidates.

arXiv:2209.14829

Lightweight Monocular Depth Estimation with an Edge Guided Network

Monocular depth estimation is an important task that can be applied to many robotic applications. Existing methods focus on improving depth estimation accuracy via training increasingly deeper and wider networks, however these suffer from large computational complexity. Recent studies found that edge information are important cues for convolutional neural networks (CNNs) to estimate depth. Inspired by the above observations, we present a novel lightweight Edge Guided Depth Estimation Network (EGD-Net) in this study. In particular, we start out with a lightweight encoder-decoder architecture and embed an edge guidance branch which takes as input image gradients and multi-scale feature maps from the backbone to learn the edge attention features. In order to aggregate the context information and edge attention features, we design a transformer-based feature aggregation module (TRFA). TRFA captures the long-range dependencies between the context information and edge attention features through cross-attention mechanism. We perform extensive experiments on the NYU depth v2 dataset. Experimental results show that the proposed method runs about 96 fps on a Nvidia GTX 1080 GPU whilst achieving the state-of-the-art performance in terms of accuracy.

arXiv:2209.14783공식 코드 · Papers with Code

Training β-VAE by Aggregating a Learned Gaussian Posterior with a Decoupled Decoder

The reconstruction loss and the Kullback-Leibler divergence (KLD) loss in a variational autoencoder (VAE) often play antagonistic roles, and tuning the weight of the KLD loss in $\beta$-VAE to achieve a balance between the two losses is a tricky and dataset-specific task. As a result, current practices in VAE training often result in a trade-off between the reconstruction fidelity and the continuity$/$disentanglement of the latent space, if the weight $\beta$ is not carefully tuned. In this paper, we present intuitions and a careful analysis of the antagonistic mechanism of the two losses, and propose, based on the insights, a simple yet effective two-stage method for training a VAE. Specifically, the method aggregates a learned Gaussian posterior $z \sim q_{\theta} (z|x)$ with a decoder decoupled from the KLD loss, which is trained to learn a new conditional distribution $p_{\phi} (x|z)$ of the input data $x$. Experimentally, we show that the aggregated VAE maximally satisfies the Gaussian assumption about the latent space, while still achieves a reconstruction error comparable to when the latent space is only loosely regularized by $\mathcal{N}(\mathbf{0},I)$. The proposed approach does not require hyperparameter (i.e., the KLD weight $\beta$) tuning given a specific dataset as required in common VAE training practices. We evaluate the method using a medical dataset intended for 3D skull reconstruction and shape completion, and the results indicate promising generative capabilities of the VAE trained using the proposed method. Besides, through guided manipulation of the latent variables, we establish a connection between existing autoencoder (AE)-based approaches and generative approaches, such as VAE, for the shape completion problem. Codes and pre-trained weights are available at https://github.com/Jianningli/skullVAE

arXiv:2209.14698공식 코드 · Papers with Code

Facial Landmark Predictions with Applications to Metaverse

This research aims to make metaverse characters more realistic by adding lip animations learnt from videos in the wild. To achieve this, our approach is to extend Tacotron 2 text-to-speech synthesizer to generate lip movements together with mel spectrogram in one pass. The encoder and gate layer weights are pre-trained on LJ Speech 1.1 data set while the decoder is retrained on 93 clips of TED talk videos extracted from LRS 3 data set. Our novel decoder predicts displacement in 20 lip landmark positions across time, using labels automatically extracted by OpenFace 2.0 landmark predictor. Training converged in 7 hours using less than 5 minutes of video. We conducted ablation study for Pre/Post-Net and pre-trained encoder weights to demonstrate the effectiveness of transfer learning between audio and visual speech data.

arXiv:2209.14604

Spherical Image Inpainting with Frame Transformation and Data-driven Prior Deep Networks

Spherical image processing has been widely applied in many important fields, such as omnidirectional vision for autonomous cars, global climate modelling, and medical imaging. It is non-trivial to extend an algorithm developed for flat images to the spherical ones. In this work, we focus on the challenging task of spherical image inpainting with deep learning-based regularizer. Instead of a naive application of existing models for planar images, we employ a fast directional spherical Haar framelet transform and develop a novel optimization framework based on a sparsity assumption of the framelet transform. Furthermore, by employing progressive encoder-decoder architecture, a new and better-performed deep CNN denoiser is carefully designed and works as an implicit regularizer. Finally, we use a plug-and-play method to handle the proposed optimization model, which can be implemented efficiently by training the CNN denoiser prior. Numerical experiments are conducted and show that the proposed algorithms can greatly recover damaged spherical images and achieve the best performance over purely using deep learning denoiser and plug-and-play model.

arXiv:2209.14792

Make-A-Video: Text-to-Video Generation without Text-Video Data

We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V). Our intuition is simple: learn what the world looks like and how it is described from paired text-image data, and learn how the world moves from unsupervised video footage. Make-A-Video has three advantages: (1) it accelerates training of the T2V model (it does not need to learn visual and multimodal representations from scratch), (2) it does not require paired text-video data, and (3) the generated videos inherit the vastness (diversity in aesthetic, fantastical depictions, etc.) of today's image generation models. We design a simple yet effective way to build on T2I models with novel and effective spatial-temporal modules. First, we decompose the full temporal U-Net and attention tensors and approximate them in space and time. Second, we design a spatial temporal pipeline to generate high resolution and frame rate videos with a video decoder, interpolation model and two super resolution models that can enable various applications besides T2V. In all aspects, spatial and temporal resolution, faithfulness to text, and quality, Make-A-Video sets the new state-of-the-art in text-to-video generation, as determined by both qualitative and quantitative measures.

arXiv:2209.14627공식 코드 · Papers with Code

An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation

Open-domain dialogue systems aim to interact with humans through natural language texts in an open-ended fashion. Despite the recent success of super large dialogue systems such as ChatGPT, using medium-to-small-sized dialogue systems remains the common practice as they are more lightweight and accessible; however, generating diverse dialogue responses is challenging, especially with smaller models. In this work, we propose an Equal-size Hard Expectation--Maximization (EqHard-EM) algorithm to train a multi-decoder model for diverse dialogue generation. Our algorithm assigns a sample to a decoder in a hard manner and additionally imposes an equal-assignment constraint to ensure that all decoders are well-trained. We provide detailed theoretical analysis to justify our approach. Further, experiments on two large-scale open-domain dialogue datasets verify that our EqHard-EM algorithm generates high-quality diverse responses.

arXiv:2209.14290

FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation

Retrieval-augmented generation models offer many benefits over standalone language models: besides a textual answer to a given query they provide provenance items retrieved from an updateable knowledge base. However, they are also more complex systems and need to handle long inputs. In this work, we introduce FiD-Light to strongly increase the efficiency of the state-of-the-art retrieval-augmented FiD model, while maintaining the same level of effectiveness. Our FiD-Light model constrains the information flow from the encoder (which encodes passages separately) to the decoder (using concatenated encoded representations). Furthermore, we adapt FiD-Light with re-ranking capabilities through textual source pointers, to improve the top-ranked provenance precision. Our experiments on a diverse set of seven knowledge intensive tasks (KILT) show FiD-Light consistently improves the Pareto frontier between query latency and effectiveness. FiD-Light with source pointing sets substantial new state-of-the-art results on six KILT tasks for combined text generation and provenance retrieval evaluation, while maintaining reasonable efficiency.

arXiv:2209.14150

Speech Enhancement Using Self-Supervised Pre-Trained Model and Vector Quantization

With the development of deep learning, neural network-based speech enhancement (SE) models have shown excellent performance. Meanwhile, it was shown that the development of self-supervised pre-trained models can be applied to various downstream tasks. In this paper, we will consider the application of the pre-trained model to the real-time SE problem. Specifically, the encoder and bottleneck layer of the DEMUCS model are initialized using the self-supervised pretrained WavLM model, the convolution in the encoder is replaced by causal convolution, and the transformer encoder in the bottleneck layer is based on causal attention mask. In addition, as discretizing the noisy speech representations is more beneficial for denoising, we utilize a quantization module to discretize the representation output from the bottleneck layer, which is then fed into the decoder to reconstruct the clean speech waveform. Experimental results on the Valentini dataset and an internal dataset show that the pre-trained model based initialization can improve the SE performance and the discretization operation suppresses the noise component in the representations to some extent, which can further improve the performance.