PyTorchKR Papers

최신 논문

총 9,339편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2207.13529

A Variational AutoEncoder for Transformers with Nonparametric Variational Information Bottleneck

We propose a VAE for Transformers by developing a variational information bottleneck regulariser for Transformer embeddings. We formalise the embedding space of Transformer encoders as mixture probability distributions, and use Bayesian nonparametrics to derive a nonparametric variational information bottleneck (NVIB) for such attention-based embeddings. The variable number of mixture components supported by nonparametric methods captures the variable number of vectors supported by attention, and the exchangeability of our nonparametric distributions captures the permutation invariance of attention. This allows NVIB to regularise the number of vectors accessible with attention, as well as the amount of information in individual vectors. By regularising the cross-attention of a Transformer encoder-decoder with NVIB, we propose a nonparametric variational autoencoder (NVAE). Initial experiments on training a NVAE on natural language text show that the induced embedding space has the desired properties of a VAE for Transformers.

arXiv:2207.12554

Inter-Frame Compression for Dynamic Point Cloud Geometry Coding

Efficient point cloud compression is essential for applications like virtual and mixed reality, autonomous driving, and cultural heritage. This paper proposes a deep learning-based inter-frame encoding scheme for dynamic point cloud geometry compression. We propose a lossy geometry compression scheme that predicts the latent representation of the current frame using the previous frame by employing a novel feature space inter-prediction network. The proposed network utilizes sparse convolutions with hierarchical multiscale 3D feature learning to encode the current frame using the previous frame. The proposed method introduces a novel predictor network for motion compensation in the feature domain to map the latent representation of the previous frame to the coordinates of the current frame to predict the current frame's feature embedding. The framework transmits the residual of the predicted features and the actual features by compressing them using a learned probabilistic factorized entropy model. At the receiver, the decoder hierarchically reconstructs the current frame by progressively rescaling the feature embedding. The proposed framework is compared to the state-of-the-art Video-based Point Cloud Compression (V-PCC) and Geometry-based Point Cloud Compression (G-PCC) schemes standardized by the Moving Picture Experts Group (MPEG). The proposed method achieves more than 88% BD-Rate (Bjontegaard Delta Rate) reduction against G-PCCv20 Octree, more than 56% BD-Rate savings against G-PCCv20 Trisoup, more than 62% BD-Rate reduction against V-PCC intra-frame encoding mode, and more than 52% BD-Rate savings against V-PCC P-frame-based inter-frame encoding mode using HEVC. These significant performance gains are cross-checked and verified in the MPEG working group.

arXiv:2207.13085공식 코드 · Papers with Code

Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment

Detection transformer (DETR) relies on one-to-one assignment, assigning one ground-truth object to one prediction, for end-to-end detection without NMS post-processing. It is known that one-to-many assignment, assigning one ground-truth object to multiple predictions, succeeds in detection methods such as Faster R-CNN and FCOS. While the naive one-to-many assignment does not work for DETR, and it remains challenging to apply one-to-many assignment for DETR training. In this paper, we introduce Group DETR, a simple yet efficient DETR training approach that introduces a group-wise way for one-to-many assignment. This approach involves using multiple groups of object queries, conducting one-to-one assignment within each group, and performing decoder self-attention separately. It resembles data augmentation with automatically-learned object query augmentation. It is also equivalent to simultaneously training parameter-sharing networks of the same architecture, introducing more supervision and thus improving DETR training. The inference process is the same as DETR trained normally and only needs one group of queries without any architecture modification. Group DETR is versatile and is applicable to various DETR variants. The experiments show that Group DETR significantly speeds up the training convergence and improves the performance of various DETR-based models. Code will be available at \url{https://github.com/Atten4Vis/GroupDETR}.

arXiv:2207.12995공식 코드 · Papers with Code

Exploring Generalizable Distillation for Efficient Medical Image Segmentation

Efficient medical image segmentation aims to provide accurate pixel-wise predictions for medical images with a lightweight implementation framework. However, lightweight frameworks generally fail to achieve superior performance and suffer from poor generalizable ability on cross-domain tasks. In this paper, we explore the generalizable knowledge distillation for the efficient segmentation of cross-domain medical images. Considering the domain gaps between different medical datasets, we propose the Model-Specific Alignment Networks (MSAN) to obtain the domain-invariant representations. Meanwhile, a customized Alignment Consistency Training (ACT) strategy is designed to promote the MSAN training. Considering the domain-invariant representative vectors in MSAN, we propose two generalizable knowledge distillation schemes for cross-domain distillation, Dual Contrastive Graph Distillation (DCGD) and Domain-Invariant Cross Distillation (DICD). Specifically, in DCGD, two types of implicit contrastive graphs are designed to represent the intra-coupling and inter-coupling semantic correlations from the perspective of data distribution. In DICD, the domain-invariant semantic vectors from the two models (i.e., teacher and student) are leveraged to cross-reconstruct features by the header exchange of MSAN, which achieves improvement in the generalization of both the encoder and decoder in the student model. Furthermore, a metric named Frechet Semantic Distance (FSD) is tailored to verify the effectiveness of the regularized domain-invariant features. Extensive experiments conducted on the Liver and Retinal Vessel Segmentation datasets demonstrate the superiority of our method, in terms of performance and generalization on lightweight frameworks.

arXiv:2207.12967

TransFiner: A Full-Scale Refinement Approach for Multiple Object Tracking

Multiple object tracking (MOT) is the task containing detection and association. Plenty of trackers have achieved competitive performance. Unfortunately, for the lack of informative exchange on these subtasks, they are often biased toward one of the two and underperform in complex scenarios, such as the inevitable misses and mistaken trajectories of targets when tracking individuals within a crowd. This paper proposes TransFiner, a transformer-based approach to post-refining MOT. It is a generic attachment framework that depends on query pairs, the bridge between an original tracker and TransFiner. Each query pair, through the fusion decoder, produces refined detection and motion clues for a specific object. Before that, they are feature-aligned and group-labeled under the guidance of tracking results (locations and class predictions) from the original tracker, finishing tracking refinement with focus and comprehensively. Experiments show that our design is effective, on the MOT17 benchmark, we elevate the CenterTrack from 67.8% MOTA and 64.7% IDF1 to 71.5% MOTA and 66.8% IDF1.

arXiv:2207.12888공식 코드 · Papers with Code

LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection

Visual question answering (VQA) often requires an understanding of visual concepts and language semantics, which relies on external knowledge. Most existing methods exploit pre-trained language models or/and unstructured text, but the knowledge in these resources are often incomplete and noisy. Some other methods prefer to use knowledge graphs (KGs) which often have intensive structured knowledge, but the research is still quite preliminary. In this paper, we propose LaKo, a knowledge-driven VQA method via Late Knowledge-to-text Injection. To effectively incorporate an external KG, we transfer triples into textual format and propose a late injection mechanism for knowledge fusion. Finally we address VQA as a text generation task with an effective encoder-decoder paradigm, which achieves state-of-the-art results on OKVQA dataset.

arXiv:2207.12323

Unsupervised Hebbian Learning on Point Sets in StarCraft II

Learning the evolution of real-time strategy (RTS) game is a challenging problem in artificial intelligent (AI) system. In this paper, we present a novel Hebbian learning method to extract the global feature of point sets in StarCraft II game units, and its application to predict the movement of the points. Our model includes encoder, LSTM, and decoder, and we train the encoder with the unsupervised learning method. We introduce the concept of neuron activity aware learning combined with k-Winner-Takes-All. The optimal value of neuron activity is mathematically derived, and experiments support the effectiveness of the concept over the downstream task. Our Hebbian learning rule benefits the prediction with lower loss compared to self-supervised learning. Also, our model significantly saves the computational cost such as activations and FLOPs compared to a frame-based approach.

arXiv:2207.12013

Effective and Interpretable Information Aggregation with Capacity Networks

How to aggregate information from multiple instances is a key question multiple instance learning. Prior neural models implement different variants of the well-known encoder-decoder strategy according to which all input features are encoded a single, high-dimensional embedding which is then decoded to generate an output. In this work, inspired by Choquet capacities, we propose Capacity networks. Unlike encoder-decoders, Capacity networks generate multiple interpretable intermediate results which can be aggregated in a semantically meaningful space to obtain the final output. Our experiments show that implementing this simple inductive bias leads to improvements over different encoder-decoder architectures in a wide range of experiments. Moreover, the interpretable intermediate results make Capacity networks interpretable by design, which allows a semantically meaningful inspection, evaluation, and regularization of the network internals.

arXiv:2207.11984공식 코드 · Papers with Code

RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation

Existing self-supervised monocular depth estimation methods can get rid of expensive annotations and achieve promising results. However, these methods suffer from severe performance degradation when directly adopting a model trained on a fixed resolution to evaluate at other different resolutions. In this paper, we propose a resolution adaptive self-supervised monocular depth estimation method (RA-Depth) by learning the scale invariance of the scene depth. Specifically, we propose a simple yet efficient data augmentation method to generate images with arbitrary scales for the same scene. Then, we develop a dual high-resolution network that uses the multi-path encoder and decoder with dense interactions to aggregate multi-scale features for accurate depth inference. Finally, to explicitly learn the scale invariance of the scene depth, we formulate a cross-scale depth consistency loss on depth predictions with different scales. Extensive experiments on the KITTI, Make3D and NYU-V2 datasets demonstrate that RA-Depth not only achieves state-of-the-art performance, but also exhibits a good ability of resolution adaptation.

arXiv:2207.11677공식 코드 · Papers with Code

Learnable Privacy-Preserving Anonymization for Pedestrian Images

This paper studies a novel privacy-preserving anonymization problem for pedestrian images, which preserves personal identity information (PII) for authorized models and prevents PII from being recognized by third parties. Conventional anonymization methods unavoidably cause semantic information loss, leading to limited data utility. Besides, existing learned anonymization techniques, while retaining various identity-irrelevant utilities, will change the pedestrian identity, and thus are unsuitable for training robust re-identification models. To explore the privacy-utility trade-off for pedestrian images, we propose a joint learning reversible anonymization framework, which can reversibly generate full-body anonymous images with little performance drop on person re-identification tasks. The core idea is that we adopt desensitized images generated by conventional methods as the initial privacy-preserving supervision and jointly train an anonymization encoder with a recovery decoder and an identity-invariant model. We further propose a progressive training strategy to improve the performance, which iteratively upgrades the initial anonymization supervision. Experiments further demonstrate the effectiveness of our anonymized pedestrian images for privacy protection, which boosts the re-identification performance while preserving privacy. Code is available at \url{https://github.com/whuzjw/privacy-reid}.

arXiv:2207.11776

Incorporating Heterogeneous User Behaviors and Social Influences for Predictive Analysis

Behavior prediction based on historical behavioral data have practical real-world significance. It has been applied in recommendation, predicting academic performance, etc. With the refinement of user data description, the development of new functions, and the fusion of multiple data sources, heterogeneous behavioral data which contain multiple types of behaviors become more and more common. In this paper, we aim to incorporate heterogeneous user behaviors and social influences for behavior predictions. To this end, this paper proposes a variant of Long-Short Term Memory (LSTM) which can consider context information while modeling a behavior sequence, a projection mechanism which can model multi-faceted relationships among different types of behaviors, and a multi-faceted attention mechanism which can dynamically find out informative periods from different facets. Many kinds of behavioral data belong to spatio-temporal data. An unsupervised way to construct a social behavior graph based on spatio-temporal data and to model social influences is proposed. Moreover, a residual learning-based decoder is designed to automatically construct multiple high-order cross features based on social behavior representation and other types of behavior representations. Qualitative and quantitative experiments on real-world datasets have demonstrated the effectiveness of this model.

arXiv:2207.11749공식 코드 · Papers with Code

Simultaneous source separation of unknown numbers of single-channel underwater acoustic signals based on deep neural networks with separator-decoder structure

The separation of single-channel underwater acoustic signals is a challenging problem with practical significance. Few existing studies focus on the source separation problem with unknown numbers of signals, and how to evaluate the performance of the systems is not yet clear. In this paper, a deep learning-based simultaneous separating solution with a fixed number of output channels equal to the maximum number of possible targets is proposed to address these two problems. This solution avoids the dimensional disaster caused by the permutation problem induced by the alignment of outputs to targets. Specifically, we propose a two-step learning-based separation model with a separator-decoder structure. A performance evaluation method with two quantitative metrics of the separation system for situations with mute channels in the output channels that do not contain target signals is also proposed. Experiments conducted on simulated mixtures of radiated ship noise show that the proposed solution can achieve similar separation performance to that attained with a known number of signals. The proposed separation model with separator-decoder structure achieved competitive performance as two models developed for known numbers of signals, which is highly explainable and extensible and gets the state of the art under this framework.

arXiv:2207.11697공식 코드 · Papers with Code

Improving Mandarin Speech Recogntion with Block-augmented Transformer

Recently Convolution-augmented Transformer (Conformer) has shown promising results in Automatic Speech Recognition (ASR), outperforming the previous best published Transformer Transducer. In this work, we believe that the output information of each block in the encoder and decoder is not completely inclusive, in other words, their output information may be complementary. We study how to take advantage of the complementary information of each block in a parameter-efficient way, and it is expected that this may lead to more robust performance. Therefore we propose the Block-augmented Transformer for speech recognition, named Blockformer. We have implemented two block ensemble methods: the base Weighted Sum of the Blocks Output (Base-WSBO), and the Squeeze-and-Excitation module to Weighted Sum of the Blocks Output (SE-WSBO). Experiments have proved that the Blockformer significantly outperforms the state-of-the-art Conformer-based models on AISHELL-1, our model achieves a CER of 4.29\% without using a language model and 4.05\% with an external language model on the testset.

arXiv:2207.11553공식 코드 · Papers with Code

High-Resolution Swin Transformer for Automatic Medical Image Segmentation

The Resolution of feature maps is critical for medical image segmentation. Most of the existing Transformer-based networks for medical image segmentation are U-Net-like architecture that contains an encoder that utilizes a sequence of Transformer blocks to convert the input medical image from high-resolution representation into low-resolution feature maps and a decoder that gradually recovers the high-resolution representation from low-resolution feature maps. Unlike previous studies, in this paper, we utilize the network design style from the High-Resolution Network (HRNet), replace the convolutional layers with Transformer blocks, and continuously exchange information from the different resolution feature maps that are generated by Transformer blocks. The newly Transformer-based network presented in this paper is denoted as High-Resolution Swin Transformer Network (HRSTNet). Extensive experiments illustrate that HRSTNet can achieve comparable performance with the state-of-the-art Transformer-based U-Net-like architecture on Brain Tumor Segmentation(BraTS) 2021 and the liver dataset from Medical Segmentation Decathlon. The code of HRSTNet will be publicly available at https://github.com/auroua/HRSTNet.

arXiv:2207.11463공식 코드 · Papers with Code

When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition

Recently, most handwritten mathematical expression recognition (HMER) methods adopt the encoder-decoder networks, which directly predict the markup sequences from formula images with the attention mechanism. However, such methods may fail to accurately read formulas with complicated structure or generate long markup sequences, as the attention results are often inaccurate due to the large variance of writing styles or spatial layouts. To alleviate this problem, we propose an unconventional network for HMER named Counting-Aware Network (CAN), which jointly optimizes two tasks: HMER and symbol counting. Specifically, we design a weakly-supervised counting module that can predict the number of each symbol class without the symbol-level position annotations, and then plug it into a typical attention-based encoder-decoder model for HMER. Experiments on the benchmark datasets for HMER validate that both joint optimization and counting results are beneficial for correcting the prediction errors of encoder-decoder models, and CAN consistently outperforms the state-of-the-art methods. In particular, compared with an encoder-decoder model for HMER, the extra time cost caused by the proposed counting module is marginal. The source code is available at https://github.com/LBH1024/CAN.

arXiv:2207.11280

PanGu-Coder: Program Synthesis with Function-Level Language Modeling

We present PanGu-Coder, a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation, i.e. the synthesis of programming language solutions given a natural language problem description. We train PanGu-Coder using a two-stage strategy: the first stage employs Causal Language Modelling (CLM) to pre-train on raw programming language data, while the second stage uses a combination of Causal Language Modelling and Masked Language Modelling (MLM) training objectives that focus on the downstream task of text-to-code generation and train on loosely curated pairs of natural language program definitions and code functions. Finally, we discuss PanGu-Coder-FT, which is fine-tuned on a combination of competitive programming problems and code with continuous integration tests. We evaluate PanGu-Coder with a focus on whether it generates functionally correct programs and demonstrate that it achieves equivalent or better performance than similarly sized models, such as CodeX, while attending a smaller context window and training on less data.

arXiv:2207.11025공식 코드 · Papers with Code

Custom Structure Preservation in Face Aging

In this work, we propose a novel architecture for face age editing that can produce structural modifications while maintaining relevant details present in the original image. We disentangle the style and content of the input image and propose a new decoder network that adopts a style-based strategy to combine the style and content representations of the input image while conditioning the output on the target age. We go beyond existing aging methods allowing users to adjust the degree of structure preservation in the input image during inference. To this purpose, we introduce a masking mechanism, the CUstom Structure Preservation module, that distinguishes relevant regions in the input image from those that should be discarded. CUSP requires no additional supervision. Finally, our quantitative and qualitative analysis which include a user study, show that our method outperforms prior art and demonstrates the effectiveness of our strategy regarding image editing and adjustable structure preservation. Code and pretrained models are available at https://github.com/guillermogotre/CUSP.

arXiv:2207.10866공식 코드 · Papers with Code

Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation

This paper presents a novel cost aggregation network, called Volumetric Aggregation with Transformers (VAT), for few-shot segmentation. The use of transformers can benefit correlation map aggregation through self-attention over a global receptive field. However, the tokenization of a correlation map for transformer processing can be detrimental, because the discontinuity at token boundaries reduces the local context available near the token edges and decreases inductive bias. To address this problem, we propose a 4D Convolutional Swin Transformer, where a high-dimensional Swin Transformer is preceded by a series of small-kernel convolutions that impart local context to all pixels and introduce convolutional inductive bias. We additionally boost aggregation performance by applying transformers within a pyramidal structure, where aggregation at a coarser level guides aggregation at a finer level. Noise in the transformer output is then filtered in the subsequent decoder with the help of the query's appearance embedding. With this model, a new state-of-the-art is set for all the standard benchmarks in few-shot segmentation. It is shown that VAT attains state-of-the-art performance for semantic correspondence as well, where cost aggregation also plays a central role.

arXiv:2207.10852공식 코드 · Papers with Code

Spatio-Temporal Deformable Attention Network for Video Deblurring

The key success factor of the video deblurring methods is to compensate for the blurry pixels of the mid-frame with the sharp pixels of the adjacent video frames. Therefore, mainstream methods align the adjacent frames based on the estimated optical flows and fuse the alignment frames for restoration. However, these methods sometimes generate unsatisfactory results because they rarely consider the blur levels of pixels, which may introduce blurry pixels from video frames. Actually, not all the pixels in the video frames are sharp and beneficial for deblurring. To address this problem, we propose the spatio-temporal deformable attention network (STDANet) for video delurring, which extracts the information of sharp pixels by considering the pixel-wise blur levels of the video frames. Specifically, STDANet is an encoder-decoder network combined with the motion estimator and spatio-temporal deformable attention (STDA) module, where motion estimator predicts coarse optical flows that are used as base offsets to find the corresponding sharp pixels in STDA module. Experimental results indicate that the proposed STDANet performs favorably against state-of-the-art methods on the GoPro, DVD, and BSD datasets.

arXiv:2207.10774공식 코드 · Papers with Code

Focused Decoding Enables 3D Anatomical Detection by Transformers

Detection Transformers represent end-to-end object detection approaches based on a Transformer encoder-decoder architecture, exploiting the attention mechanism for global relation modeling. Although Detection Transformers deliver results on par with or even superior to their highly optimized CNN-based counterparts operating on 2D natural images, their success is closely coupled to access to a vast amount of training data. This, however, restricts the feasibility of employing Detection Transformers in the medical domain, as access to annotated data is typically limited. To tackle this issue and facilitate the advent of medical Detection Transformers, we propose a novel Detection Transformer for 3D anatomical structure detection, dubbed Focused Decoder. Focused Decoder leverages information from an anatomical region atlas to simultaneously deploy query anchors and restrict the cross-attention's field of view to regions of interest, which allows for a precise focus on relevant anatomical structures. We evaluate our proposed approach on two publicly available CT datasets and demonstrate that Focused Decoder not only provides strong detection results and thus alleviates the need for a vast amount of annotated data but also exhibits exceptional and highly intuitive explainability of results via attention weights. Our code is available at https://github.com/bwittmann/transoar.