PyTorchKR Papers

최신 논문

총 10,165편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2211.01777

Evaluating a Synthetic Image Dataset Generated with Stable Diffusion

We generate synthetic images with the "Stable Diffusion" image generation model using the Wordnet taxonomy and the definitions of concepts it contains. This synthetic image database can be used as training data for data augmentation in machine learning applications, and it is used to investigate the capabilities of the Stable Diffusion model. Analyses show that Stable Diffusion can produce correct images for a large number of concepts, but also a large variety of different representations. The results show differences depending on the test concepts considered and problems with very specific concepts. These evaluations were performed using a vision transformer model for image classification.

arXiv:2211.01770

Exploring Explainability Methods for Graph Neural Networks

With the growing use of deep learning methods, particularly graph neural networks, which encode intricate interconnectedness information, for a variety of real tasks, there is a necessity for explainability in such settings. In this paper, we demonstrate the applicability of popular explainability approaches on Graph Attention Networks (GAT) for a graph-based super-pixel image classification task. We assess the qualitative and quantitative performance of these techniques on three different datasets and describe our findings. The results shed a fresh light on the notion of explainability in GNNs, particularly GATs.

arXiv:2211.01335공식 코드 · Papers with Code

Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese

The tremendous success of CLIP (Radford et al., 2021) has promoted the research and application of contrastive learning for vision-language pretraining. In this work, we construct a large-scale dataset of image-text pairs in Chinese, where most data are retrieved from publicly available datasets, and we pretrain Chinese CLIP models on the new dataset. We develop 5 Chinese CLIP models of multiple sizes, spanning from 77 to 958 million parameters. Furthermore, we propose a two-stage pretraining method, where the model is first trained with the image encoder frozen and then trained with all parameters being optimized, to achieve enhanced model performance. Our comprehensive experiments demonstrate that Chinese CLIP can achieve the state-of-the-art performance on MUGE, Flickr30K-CN, and COCO-CN in the setups of zero-shot learning and finetuning, and it is able to achieve competitive performance in zero-shot image classification based on the evaluation on the ELEVATER benchmark (Li et al., 2022). We have released our codes, models, and demos in https://github.com/OFA-Sys/Chinese-CLIP

arXiv:2211.00937공식 코드 · Papers with Code

WITT: A Wireless Image Transmission Transformer for Semantic Communications

In this paper, we aim to redesign the vision Transformer (ViT) as a new backbone to realize semantic image transmission, termed wireless image transmission transformer (WITT). Previous works build upon convolutional neural networks (CNNs), which are inefficient in capturing global dependencies, resulting in degraded end-to-end transmission performance especially for high-resolution images. To tackle this, the proposed WITT employs Swin Transformers as a more capable backbone to extract long-range information. Different from ViTs in image classification tasks, WITT is highly optimized for image transmission while considering the effect of the wireless channel. Specifically, we propose a spatial modulation module to scale the latent representations according to channel state information, which enhances the ability of a single model to deal with various channel conditions. As a result, extensive experiments verify that our WITT attains better performance for different image resolutions, distortion metrics, and channel conditions. The code is available at https://github.com/KeYang8/WITT.

arXiv:2211.00683

Reduce, Reuse, Recycle: Improving Training Efficiency with Distillation

Methods for improving the efficiency of deep network training (i.e. the resources required to achieve a given level of model quality) are of immediate benefit to deep learning practitioners. Distillation is typically used to compress models or improve model quality, but it's unclear if distillation actually improves training efficiency. Can the quality improvements of distillation be converted into training speed-ups, or do they simply increase final model quality with no resource savings? We conducted a series of experiments to investigate whether and how distillation can be used to accelerate training using ResNet-50 trained on ImageNet and BERT trained on C4 with a masked language modeling objective and evaluated on GLUE, using common enterprise hardware (8x NVIDIA A100). We found that distillation can speed up training by up to 1.96x in ResNet-50 trained on ImageNet and up to 1.42x on BERT when evaluated on GLUE. Furthermore, distillation for BERT yields optimal results when it is only performed for the first 20-50% of training. We also observed that training with distillation is almost always more efficient than training without distillation, even when using the poorest-quality model as a teacher, in both ResNet-50 and BERT. Finally, we found that it's possible to gain the benefit of distilling from an ensemble of teacher models, which has O(n) runtime cost, by randomly sampling a single teacher from the pool of teacher models on each step, which only has a O(1) runtime cost. Taken together, these results show that distillation can substantially improve training efficiency in both image classification and language modeling, and that a few simple optimizations to distillation protocols can further enhance these efficiency improvements.

arXiv:2211.00227

Transfer Learning with Kernel Methods

Transfer learning refers to the process of adapting a model trained on a source task to a target task. While kernel methods are conceptually and computationally simple machine learning models that are competitive on a variety of tasks, it has been unclear how to perform transfer learning for kernel methods. In this work, we propose a transfer learning framework for kernel methods by projecting and translating the source model to the target task. We demonstrate the effectiveness of our framework in applications to image classification and virtual drug screening. In particular, we show that transferring modern kernels trained on large-scale image datasets can result in substantial performance increase as compared to using the same kernel trained directly on the target task. In addition, we show that transfer-learned kernels allow a more accurate prediction of the effect of drugs on cancer cell lines. For both applications, we identify simple scaling laws that characterize the performance of transfer-learned kernels as a function of the number of target examples. We explain this phenomenon in a simplified linear setting, where we are able to derive the exact scaling laws. By providing a simple and effective transfer learning framework for kernel methods, our work enables kernel methods trained on large datasets to be easily adapted to a variety of downstream target tasks.

arXiv:2211.00168공식 코드 · Papers with Code

Improving Fairness in Image Classification via Sketching

Fairness is a fundamental requirement for trustworthy and human-centered Artificial Intelligence (AI) system. However, deep neural networks (DNNs) tend to make unfair predictions when the training data are collected from different sub-populations with different attributes (i.e. color, sex, age), leading to biased DNN predictions. We notice that such a troubling phenomenon is often caused by data itself, which means that bias information is encoded to the DNN along with the useful information (i.e. class information, semantic information). Therefore, we propose to use sketching to handle this phenomenon. Without losing the utility of data, we explore the image-to-sketching methods that can maintain useful semantic information for the target classification while filtering out the useless bias information. In addition, we design a fair loss to further improve the model fairness. We evaluate our method through extensive experiments on both general scene dataset and medical scene dataset. Our results show that the desired image-to-sketching method improves model fairness and achieves satisfactory results among state-of-the-art.

arXiv:2211.00113

SAGE: Saliency-Guided Mixup with Optimal Rearrangements

Data augmentation is a key element for training accurate models by reducing overfitting and improving generalization. For image classification, the most popular data augmentation techniques range from simple photometric and geometrical transformations, to more complex methods that use visual saliency to craft new training examples. As augmentation methods get more complex, their ability to increase the test accuracy improves, yet, such methods become cumbersome, inefficient and lead to poor out-of-domain generalization, as we show in this paper. This motivates a new augmentation technique that allows for high accuracy gains while being simple, efficient (i.e., minimal computation overhead) and generalizable. To this end, we introduce Saliency-Guided Mixup with Optimal Rearrangements (SAGE), which creates new training examples by rearranging and mixing image pairs using visual saliency as guidance. By explicitly leveraging saliency, SAGE promotes discriminative foreground objects and produces informative new images useful for training. We demonstrate on CIFAR-10 and CIFAR-100 that SAGE achieves better or comparable performance to the state of the art while being more efficient. Additionally, evaluations in the out-of-distribution setting, and few-shot learning on mini-ImageNet, show that SAGE achieves improved generalization performance without trading off robustness.

arXiv:2210.16371공식 코드 · Papers with Code

Distributed Black-box Attack: Do Not Overestimate Black-box Attacks

Black-box adversarial attacks can fool image classifiers into misclassifying images without requiring access to model structure and weights. Recent studies have reported attack success rates of over 95% with less than 1,000 queries. The question then arises of whether black-box attacks have become a real threat against IoT devices that rely on cloud APIs to achieve image classification. To shed some light on this, note that prior research has primarily focused on increasing the success rate and reducing the number of queries. However, another crucial factor for black-box attacks against cloud APIs is the time required to perform the attack. This paper applies black-box attacks directly to cloud APIs rather than to local models, thereby avoiding mistakes made in prior research that applied the perturbation before image encoding and pre-processing. Further, we exploit load balancing to enable distributed black-box attacks that can reduce the attack time by a factor of about five for both local search and gradient estimation methods.

arXiv:2210.17357공식 코드 · Papers with Code

L-GreCo: Layerwise-Adaptive Gradient Compression for Efficient and Accurate Deep Learning

Data-parallel distributed training of deep neural networks (DNN) has gained very widespread adoption, but can still experience communication bottlenecks. To address this issue, entire families of compression mechanisms have been developed, including quantization, sparsification, and low-rank approximation, some of which are seeing significant practical adoption. Despite this progress, almost all known compression schemes apply compression uniformly across DNN layers, although layers are heterogeneous in terms of parameter count and their impact on model accuracy. In this work, we provide a general framework for adapting the degree of compression across the model's layers dynamically during training, improving the overall compression, while leading to substantial speedups, without sacrificing accuracy. Our framework, called L-GreCo, is based on an adaptive algorithm, which automatically picks the optimal compression parameters for model layers guaranteeing the best compression ratio while satisfying an error constraint. Extensive experiments over image classification and language modeling tasks shows that L-GreCo is effective across all existing families of compression methods, and achieves up to 2.5$\times$ training speedup and up to 5$\times$ compression improvement over efficient implementations of existing approaches, while recovering full accuracy. Moreover, L-GreCo is complementary to existing adaptive algorithms, improving their compression ratio by 50% and practical throughput by 66%.

arXiv:2210.16940공식 코드 · Papers with Code

FI-ODE: Certifiably Robust Forward Invariance in Neural ODEs

Forward invariance is a long-studied property in control theory that is used to certify that a dynamical system stays within some pre-specified set of states for all time, and also admits robustness guarantees (e.g., the certificate holds under perturbations). We propose a general framework for training and provably certifying robust forward invariance in Neural ODEs. We apply this framework to provide certified safety in robust continuous control. To our knowledge, this is the first instance of training Neural ODE policies with such non-vacuous certified guarantees. In addition, we explore the generality of our framework by using it to certify adversarial robustness for image classification.

arXiv:2210.17322

Generative Negative Text Replay for Continual Vision-Language Pretraining

Vision-language pre-training (VLP) has attracted increasing attention recently. With a large amount of image-text pairs, VLP models trained with contrastive loss have achieved impressive performance in various tasks, especially the zero-shot generalization on downstream datasets. In practical applications, however, massive data are usually collected in a streaming fashion, requiring VLP models to continuously integrate novel knowledge from incoming data and retain learned knowledge. In this work, we focus on learning a VLP model with sequential chunks of image-text pair data. To tackle the catastrophic forgetting issue in this multi-modal continual learning setting, we first introduce pseudo text replay that generates hard negative texts conditioned on the training images in memory, which not only better preserves learned knowledge but also improves the diversity of negative samples in the contrastive loss. Moreover, we propose multi-modal knowledge distillation between images and texts to align the instance-wise prediction between old and new models. We incrementally pre-train our model on both the instance and class incremental splits of the Conceptual Caption dataset, and evaluate the model on zero-shot image classification and image-text retrieval tasks. Our method consistently outperforms the existing baselines with a large margin, which demonstrates its superiority. Notably, we realize an average performance boost of $4.60\%$ on image-classification downstream datasets for the class incremental split.

arXiv:2210.17141

Studying inductive biases in image classification task

Recently, self-attention (SA) structures became popular in computer vision fields. They have locally independent filters and can use large kernels, which contradicts the previously popular convolutional neural networks (CNNs). CNNs success was attributed to the hard-coded inductive biases of locality and spatial invariance. However, recent studies have shown that inductive biases in CNNs are too restrictive. On the other hand, the relative position encodings, similar to depthwise (DW) convolution, are necessary for the local SA networks, which indicates that the SA structures are not entirely spatially variant. Hence, we would like to determine which part of inductive biases contributes to the success of the local SA structures. To do so, we introduced context-aware decomposed attention (CADA), which decomposes attention maps into multiple trainable base kernels and accumulates them using context-aware (CA) parameters. This way, we could identify the link between the CNNs and SA networks. We conducted ablation studies using the ResNet50 applied to the ImageNet classification task. DW convolution could have a large locality without increasing computational costs compared to CNNs, but the accuracy saturates with larger kernels. CADA follows this characteristic of locality. We showed that context awareness was the crucial property; however, large local information was not necessary to construct CA parameters. Even though no spatial invariance makes training difficult, more relaxed spatial invariance gave better accuracy than strict spatial invariance. Also, additional strong spatial invariance through relative position encoding was preferable. We extended these experiments to filters for downsampling and showed that locality bias is more critical for downsampling but can remove the strong locality bias using relaxed spatial invariance.

arXiv:2210.16914공식 코드 · Papers with Code

FatNet: High Resolution Kernels for Classification Using Fully Convolutional Optical Neural Networks

This paper describes the transformation of a traditional in-silico classification network into an optical fully convolutional neural network with high-resolution feature maps and kernels. When using the free-space 4f system to accelerate the inference speed of neural networks, higher resolutions of feature maps and kernels can be used without the loss in frame rate. We present FatNet for the classification of images, which is more compatible with free-space acceleration than standard convolutional classifiers. It neglects the standard combination of convolutional feature extraction and classifier dense layers by performing both in one fully convolutional network. This approach takes full advantage of the parallelism in the 4f free-space system and performs fewer conversions between electronics and optics by reducing the number of channels and increasing the resolution, making the network faster in optics than off-the-shelf networks. To demonstrate the capabilities of FatNet, it trained with the CIFAR100 dataset on GPU and the simulator of the 4f system, then compared the results against ResNet-18. The results show 8.2 times fewer convolution operations at the cost of only 6% lower accuracy compared to the original network. These are promising results for the approach of training deep learning with high-resolution kernels in the direction towards the upcoming optics era.

arXiv:2210.16485

IM: An R-Package for Computation of Image Moments and Moment Invariants

Moment invariants are well-established and effective shape descriptors for image classification. In this report, we introduce a package for R-language, named IM, that implements the calculation of moments for images and allows the reconstruction of images from moments within an object-oriented framework. Several types of moments may be computed using the IM library, including discrete and continuous Chebyshev, Gegenbauer, Legendre, Krawtchouk, dual Hahn, generalized pseudo-Zernike, Fourier-Mellin, and radial harmonic Fourier moments. In addition, custom bivariate types of moments can be calculated using combinations of two different types of polynomials. A method of polar transformation of pixel coordinates is used to provide an approximate invariance to rotation for moments that are orthogonal over a rectangle. The different types of polynomials used to calculate moments are discussed in this report, as well as comparisons of reconstruction and running time. Examples of image classification using image moments are provided.

arXiv:2210.15786공식 코드 · Papers with Code

Poisson Reweighted Laplacian Uncertainty Sampling for Graph-based Active Learning

We show that uncertainty sampling is sufficient to achieve exploration versus exploitation in graph-based active learning, as long as the measure of uncertainty properly aligns with the underlying model and the model properly reflects uncertainty in unexplored regions. In particular, we use a recently developed algorithm, Poisson ReWeighted Laplace Learning (PWLL) for the classifier and we introduce an acquisition function designed to measure uncertainty in this graph-based classifier that identifies unexplored regions of the data. We introduce a diagonal perturbation in PWLL which produces exponential localization of solutions, and controls the exploration versus exploitation tradeoff in active learning. We use the well-posed continuum limit of PWLL to rigorously analyze our method, and present experimental results on a number of graph-based image classification problems.

arXiv:2210.16101

A Generic Shared Attention Mechanism for Various Backbone Neural Networks

The self-attention mechanism has emerged as a critical component for improving the performance of various backbone neural networks. However, current mainstream approaches individually incorporate newly designed self-attention modules (SAMs) into each layer of the network for granted without fully exploiting their parameters' potential. This leads to suboptimal performance and increased parameter consumption as the network depth increases. To improve this paradigm, in this paper, we first present a counterintuitive but inherent phenomenon: SAMs tend to produce strongly correlated attention maps across different layers, with an average Pearson correlation coefficient of up to 0.85. Inspired by this inherent observation, we propose Dense-and-Implicit Attention (DIA), which directly shares SAMs across layers and employs a long short-term memory module to calibrate and bridge the highly correlated attention maps of different layers, thus improving the parameter utilization efficiency of SAMs. This design of DIA is also consistent with the neural network's dynamical system perspective. Through extensive experiments, we demonstrate that our simple yet effective DIA can consistently enhance various network backbones, including ResNet, Transformer, and UNet, across tasks such as image classification, object detection, and image generation using diffusion models.

arXiv:2210.16074

Improving Chest X-Ray Classification by RNN-based Patient Monitoring

Chest X-Ray imaging is one of the most common radiological tools for detection of various pathologies related to the chest area and lung function. In a clinical setting, automated assessment of chest radiographs has the potential of assisting physicians in their decision making process and optimize clinical workflows, for example by prioritizing emergency patients. Most work analyzing the potential of machine learning models to classify chest X-ray images focuses on vision methods processing and predicting pathologies for one image at a time. However, many patients undergo such a procedure multiple times during course of a treatment or during a single hospital stay. The patient history, that is previous images and especially the corresponding diagnosis contain useful information that can aid a classification system in its prediction. In this study, we analyze how information about diagnosis can improve CNN-based image classification models by constructing a novel dataset from the well studied CheXpert dataset of chest X-rays. We show that a model trained on additional patient history information outperforms a model trained without the information by a significant margin. We provide code to replicate the dataset creation and model training.

arXiv:2210.15972공식 코드 · Papers with Code

Contextual Learning in Fourier Complex Field for VHR Remote Sensing Images

Very high-resolution (VHR) remote sensing (RS) image classification is the fundamental task for RS image analysis and understanding. Recently, transformer-based models demonstrated outstanding potential for learning high-order contextual relationships from natural images with general resolution (224x224 pixels) and achieved remarkable results on general image classification tasks. However, the complexity of the naive transformer grows quadratically with the increase in image size, which prevents transformer-based models from VHR RS image (500x500 pixels) classification and other computationally expensive downstream tasks. To this end, we propose to decompose the expensive self-attention (SA) into real and imaginary parts via discrete Fourier transform (DFT) and therefore propose an efficient complex self-attention (CSA) mechanism. Benefiting from the conjugated symmetric property of DFT, CSA is capable to model the high-order contextual information with less than half computations of naive SA. To overcome the gradient explosion in Fourier complex field, we replace the Softmax function with the carefully designed Logmax function to normalize the attention map of CSA and stabilize the gradient propagation. By stacking various layers of CSA blocks, we propose the Fourier Complex Transformer (FCT) model to learn global contextual information from VHR aerial images following the hierarchical manners. Universal experiments conducted on commonly used RS classification data sets demonstrate the effectiveness and efficiency of FCT, especially on very high-resolution RS images.

arXiv:2210.15943

Grafting Vision Transformers

Vision Transformers (ViTs) have recently become the state-of-the-art across many computer vision tasks. In contrast to convolutional networks (CNNs), ViTs enable global information sharing even within shallow layers of a network, i.e., among high-resolution features. However, this perk was later overlooked with the success of pyramid architectures such as Swin Transformer, which show better performance-complexity trade-offs. In this paper, we present a simple and efficient add-on component (termed GrafT) that considers global dependencies and multi-scale information throughout the network, in both high- and low-resolution features alike. It has the flexibility of branching out at arbitrary depths and shares most of the parameters and computations of the backbone. GrafT shows consistent gains over various well-known models which includes both hybrid and pure Transformer types, both homogeneous and pyramid structures, and various self-attention methods. In particular, it largely benefits mobile-size models by providing high-level semantics. On the ImageNet-1k dataset, GrafT delivers +3.9%, +1.4%, and +1.9% top-1 accuracy improvement to DeiT-T, Swin-T, and MobileViT-XXS, respectively. Our code and models will be made available.