PyTorchKR Papers

최신 논문

총 10,163편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2202.06268공식 코드 · Papers with Code

BViT: Broad Attention based Vision Transformer

Recent works have demonstrated that transformer can achieve promising performance in computer vision, by exploiting the relationship among image patches with self-attention. While they only consider the attention in a single feature layer, but ignore the complementarity of attention in different levels. In this paper, we propose the broad attention to improve the performance by incorporating the attention relationship of different layers for vision transformer, which is called BViT. The broad attention is implemented by broad connection and parameter-free attention. Broad connection of each transformer layer promotes the transmission and integration of information for BViT. Without introducing additional trainable parameters, parameter-free attention jointly focuses on the already available attention information in different layers for extracting useful information and building their relationship. Experiments on image classification tasks demonstrate that BViT delivers state-of-the-art accuracy of 74.8\%/81.6\% top-1 accuracy on ImageNet with 5M/22M parameters. Moreover, we transfer BViT to downstream object recognition benchmarks to achieve 98.9\% and 89.9\% on CIFAR10 and CIFAR100 respectively that exceed ViT with fewer parameters. For the generalization test, the broad attention in Swin Transformer and T2T-ViT also bring an improvement of more than 1\%. To sum up, broad attention is promising to promote the performance of attention based models. Code and pre-trained models are available at https://github.com/DRL-CASIA/Broad_ViT.

arXiv:2202.06174공식 코드 · Papers with Code

Source-Free Progressive Graph Learning for Open-Set Domain Adaptation

Open-set domain adaptation (OSDA) has gained considerable attention in many visual recognition tasks. However, most existing OSDA approaches are limited due to three main reasons, including: (1) the lack of essential theoretical analysis of generalization bound, (2) the reliance on the coexistence of source and target data during adaptation, and (3) failing to accurately estimate the uncertainty of model predictions. We propose a Progressive Graph Learning (PGL) framework that decomposes the target hypothesis space into the shared and unknown subspaces, and then progressively pseudo-labels the most confident known samples from the target domain for hypothesis adaptation. Moreover, we tackle a more realistic source-free open-set domain adaptation (SF-OSDA) setting that makes no assumption about the coexistence of source and target domains, and introduce a balanced pseudo-labeling (BP-L) strategy in a two-stage framework, namely SF-PGL. Different from PGL that applies a class-agnostic constant threshold for all target samples for pseudo-labeling, the SF-PGL model uniformly selects the most confident target instances from each category at a fixed ratio. The confidence thresholds in each class are regarded as the 'uncertainty' of learning the semantic information, which are then used to weigh the classification loss in the adaptation step. We conducted unsupervised and semi-supervised OSDA and SF-OSDA experiments on the benchmark image classification and action recognition datasets. Additionally, we find that balanced pseudo-labeling plays a significant role in improving calibration, which makes the trained model less prone to over-confident or under-confident predictions on the target data. Source code is available at https://github.com/Luoyadan/SF-PGL.

arXiv:2202.06076공식 코드 · Papers with Code

Indication as Prior Knowledge for Multimodal Disease Classification in Chest Radiographs with Transformers

When a clinician refers a patient for an imaging exam, they include the reason (e.g. relevant patient history, suspected disease) in the scan request; this appears as the indication field in the radiology report. The interpretation and reporting of the image are substantially influenced by this request text, steering the radiologist to focus on particular aspects of the image. We use the indication field to drive better image classification, by taking a transformer network which is unimodally pre-trained on text (BERT) and fine-tuning it for multimodal classification of a dual image-text input. We evaluate the method on the MIMIC-CXR dataset, and present ablation studies to investigate the effect of the indication field on the classification performance. The experimental results show our approach achieves 87.8 average micro AUROC, outperforming the state-of-the-art methods for unimodal (84.4) and multimodal (86.0) classification. Our code is available at https://github.com/jacenkow/mmbt.

arXiv:2202.06767

Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark

Vision-Language Pre-training (VLP) models have shown remarkable performance on various downstream tasks. Their success heavily relies on the scale of pre-trained cross-modal datasets. However, the lack of large-scale datasets and benchmarks in Chinese hinders the development of Chinese VLP models and broader multilingual applications. In this work, we release a large-scale Chinese cross-modal dataset named Wukong, which contains 100 million Chinese image-text pairs collected from the web. Wukong aims to benchmark different multi-modal pre-training methods to facilitate the VLP research and community development. Furthermore, we release a group of models pre-trained with various image encoders (ViT-B/ViT-L/SwinT) and also apply advanced pre-training techniques into VLP such as locked-image text tuning, token-wise similarity in contrastive learning, and reduced-token interaction. Extensive experiments and a benchmarking of different downstream tasks including a new largest human-verified image-text test dataset are also provided. Experiments show that Wukong can serve as a promising Chinese pre-training dataset and benchmark for different cross-modal learning methods. For the zero-shot image classification task on 10 datasets, $Wukong_{ViT-L}$ achieves an average accuracy of 73.03%. For the image-text retrieval task, it achieves a mean recall of 71.6% on AIC-ICC which is 12.9% higher than WenLan 2.0. Also, our Wukong models are benchmarked on downstream tasks with other variants on multiple datasets, e.g., Flickr8K-CN, Flickr-30K-CN, COCO-CN, et al. More information can be referred to: https://wukong-dataset.github.io/wukong-dataset/.

arXiv:2202.05798공식 코드 · Papers with Code

The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention

Linear layers in neural networks (NNs) trained by gradient descent can be expressed as a key-value memory system which stores all training datapoints and the initial weights, and produces outputs using unnormalised dot attention over the entire training experience. While this has been technically known since the 1960s, no prior work has effectively studied the operations of NNs in such a form, presumably due to prohibitive time and space complexities and impractical model sizes, all of them growing linearly with the number of training patterns which may get very large. However, this dual formulation offers a possibility of directly visualising how an NN makes use of training patterns at test time, by examining the corresponding attention weights. We conduct experiments on small scale supervised image classification tasks in single-task, multi-task, and continual learning settings, as well as language modelling, and discuss potentials and limits of this view for better understanding and interpreting how NNs exploit training patterns. Our code is public.

arXiv:2202.05613공식 코드 · Papers with Code

CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning

Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance. Sample re-weighting methods are popularly used to alleviate this data bias issue. Most current methods, however, require to manually pre-specify the weighting schemes as well as their additional hyper-parameters relying on the characteristics of the investigated problem and training data. This makes them fairly hard to be generally applied in practical scenarios, due to their significant complexities and inter-class variations of data bias situations. To address this issue, we propose a meta-model capable of adaptively learning an explicit weighting scheme directly from data. Specifically, by seeing each training class as a separate learning task, our method aims to extract an explicit weighting function with sample loss and task/class feature as input, and sample weight as output, expecting to impose adaptively varying weighting schemes to different sample classes based on their own intrinsic bias characteristics. Synthetic and real data experiments substantiate the capability of our method on achieving proper weighting schemes in various data bias cases, like the class imbalance, feature-independent and dependent label noise scenarios, and more complicated bias scenarios beyond conventional cases. Besides, the task-transferability of the learned weighting scheme is also substantiated, by readily deploying the weighting function learned on relatively smaller-scale CIFAR-10 dataset on much larger-scale full WebVision dataset. A performance gain can be readily achieved compared with previous SOAT ones without additional hyper-parameter tuning and meta gradient descent step. The general availability of our method for multiple robust deep learning issues, including partial-label learning, semi-supervised learning and selective classification, has also been validated.

arXiv:2202.05492공식 코드 · Papers with Code

Entroformer: A Transformer-based Entropy Model for Learned Image Compression

One critical component in lossy deep image compression is the entropy model, which predicts the probability distribution of the quantized latent representation in the encoding and decoding modules. Previous works build entropy models upon convolutional neural networks which are inefficient in capturing global dependencies. In this work, we propose a novel transformer-based entropy model, termed Entroformer, to capture long-range dependencies in probability distribution estimation effectively and efficiently. Different from vision transformers in image classification, the Entroformer is highly optimized for image compression, including a top-k self-attention and a diamond relative position encoding. Meanwhile, we further expand this architecture with a parallel bidirectional context model to speed up the decoding process. The experiments show that the Entroformer achieves state-of-the-art performance on image compression while being time-efficient.

arXiv:2202.05491

Exemplar-free Online Continual Learning

Targeted for real world scenarios, online continual learning aims to learn new tasks from sequentially available data under the condition that each data is observed only once by the learner. Though recent works have made remarkable achievements by storing part of learned task data as exemplars for knowledge replay, the performance is greatly relied on the size of stored exemplars while the storage consumption is a significant constraint in continual learning. In addition, storing exemplars may not always be feasible for certain applications due to privacy concerns. In this work, we propose a novel exemplar-free method by leveraging nearest-class-mean (NCM) classifier where the class mean is estimated during training phase on all data seen so far through online mean update criteria. We focus on image classification task and conduct extensive experiments on benchmark datasets including CIFAR-100 and Food-1k. The results demonstrate that our method without using any exemplar outperforms state-of-the-art exemplar-based approaches with large margins under standard protocol (20 exemplars per class) and is able to achieve competitive performance even with larger exemplar size (100 exemplars per class).

논문 ID: document/9197689

Fuzzy Pooling

Convolutional Neural Networks (CNNs) are artificial learning systems typically based on two operations: convolution, which implements feature extraction through filtering, and pooling, which implements dimensionality reduction. The impact of pooling in the classification performance of the CNNs has been highlighted in several previous works, and a variety of alternative pooling operators have been proposed. However, only a few of them tackle with the uncertainty that is naturally propagated from the input layer to the feature maps of the hidden layers through convolutions. In this paper we present a novel pooling operation based on (type-1) fuzzy sets to cope with the local imprecision of the feature maps, and we investigate its performance in the context of image classification. Fuzzy pooling is performed by fuzzification, aggregation and defuzzification of feature map neighborhoods. It is used for the construction of a fuzzy pooling layer that can be applied as a drop-in replacement of the current, crisp, pooling layers of CNN architectures. Several experiments using publicly available datasets show that the proposed approach can enhance the classification performance of a CNN. A comparative evaluation shows that it outperforms state-of-the-art pooling approaches.

arXiv:2202.05152

Feature-level augmentation to improve robustness of deep neural networks to affine transformations

Recent studies revealed that convolutional neural networks do not generalize well to small image transformations, e.g. rotations by a few degrees or translations of a few pixels. To improve the robustness to such transformations, we propose to introduce data augmentation at intermediate layers of the neural architecture, in addition to the common data augmentation applied on the input images. By introducing small perturbations to activation maps (features) at various levels, we develop the capacity of the neural network to cope with such transformations. We conduct experiments on three image classification benchmarks (Tiny ImageNet, Caltech-256 and Food-101), considering two different convolutional architectures (ResNet-18 and DenseNet-121). When compared with two state-of-the-art stabilization methods, the empirical results show that our approach consistently attains the best trade-off between accuracy and mean flip rate.

arXiv:2202.04942

Spherical Transformer

Using convolutional neural networks for 360images can induce sub-optimal performance due to distortions entailed by a planar projection. The distortion gets deteriorated when a rotation is applied to the 360image. Thus, many researches based on convolutions attempt to reduce the distortions to learn accurate representation. In contrast, we leverage the transformer architecture to solve image classification problems for 360images. Using the proposed transformer for 360images has two advantages. First, our method does not require the erroneous planar projection process by sampling pixels from the sphere surface. Second, our sampling method based on regular polyhedrons makes low rotation equivariance errors, because specific rotations can be reduced to permutations of faces. In experiments, we validate our network on two aspects, as follows. First, we show that using a transformer with highly uniform sampling methods can help reduce the distortion. Second, we demonstrate that the transformer architecture can achieve rotation equivariance on specific rotations. We compare our method to other state-of-the-art algorithms using the SPH-MNIST, SPH-CIFAR, and SUN360 datasets and show that our method is competitive with other methods.

arXiv:2202.04844공식 코드 · Papers with Code

Multi-relation Message Passing for Multi-label Text Classification

A well-known challenge associated with the multi-label classification problem is modelling dependencies between labels. Most attempts at modelling label dependencies focus on co-occurrences, ignoring the valuable information that can be extracted by detecting label subsets that rarely occur together. For example, consider customer product reviews; a product probably would not simultaneously be tagged by both "recommended" (i.e., reviewer is happy and recommends the product) and "urgent" (i.e., the review suggests immediate action to remedy an unsatisfactory experience). Aside from the consideration of positive and negative dependencies, the direction of a relationship should also be considered. For a multi-label image classification problem, the "ship" and "sea" labels have an obvious dependency, but the presence of the former implies the latter much more strongly than the other way around. These examples motivate the modelling of multiple types of bi-directional relationships between labels. In this paper, we propose a novel method, entitled Multi-relation Message Passing (MrMP), for the multi-label classification problem. Experiments on benchmark multi-label text classification datasets show that the MrMP module yields similar or superior performance compared to state-of-the-art methods. The approach imposes only minor additional computational and memory overheads.

arXiv:2202.05167공식 코드 · Papers with Code

Class Distance Weighted Cross-Entropy Loss for Ulcerative Colitis Severity Estimation

In scoring systems used to measure the endoscopic activity of ulcerative colitis, such as Mayo endoscopic score or Ulcerative Colitis Endoscopic Index Severity, levels increase with severity of the disease activity. Such relative ranking among the scores makes it an ordinal regression problem. On the other hand, most studies use categorical cross-entropy loss function to train deep learning models, which is not optimal for the ordinal regression problem. In this study, we propose a novel loss function, class distance weighted cross-entropy (CDW-CE), that respects the order of the classes and takes the distance of the classes into account in calculation of the cost. Experimental evaluations show that models trained with CDW-CE outperform the models trained with conventional categorical cross-entropy and other commonly used loss functions which are designed for the ordinal regression problems. In addition, the class activation maps of models trained with CDW-CE loss are more class-discriminative and they are found to be more reasonable by the domain experts.

arXiv:2202.04251

Improving greedy core-set configurations for active learning with uncertainty-scaled distances

We scale perceived distances of the core-set algorithm by a factor of uncertainty and search for low-confidence configurations, finding significant improvements in sample efficiency across CIFAR10/100 and SVHN image classification, especially in larger acquisition sizes. We show the necessity of our modifications and explain how the improvement is due to a probabilistic quadratic speed-up in the convergence of core-set loss, under assumptions about the relationship of model uncertainty and misclassification.

arXiv:2202.04298공식 코드 · Papers with Code

Image Difference Captioning with Pre-training and Contrastive Learning

The Image Difference Captioning (IDC) task aims to describe the visual differences between two similar images with natural language. The major challenges of this task lie in two aspects: 1) fine-grained visual differences that require learning stronger vision and language association and 2) high-cost of manual annotations that leads to limited supervised data. To address these challenges, we propose a new modeling framework following the pre-training-finetuning paradigm. Specifically, we design three self-supervised tasks and contrastive learning strategies to align visual differences and text descriptions at a fine-grained level. Moreover, we propose a data expansion strategy to utilize extra cross-task supervision information, such as data for fine-grained image classification, to alleviate the limitation of available supervised IDC data. Extensive experiments on two IDC benchmark datasets, CLEVR-Change and Birds-to-Words, demonstrate the effectiveness of the proposed modeling framework. The codes and models will be released at https://github.com/yaolinli/IDC.

arXiv:2202.04291공식 코드 · Papers with Code

L2B: Learning to Bootstrap Robust Models for Combating Label Noise

Deep neural networks have shown great success in representation learning. However, when learning with noisy labels (LNL), they can easily overfit and fail to generalize to new data. This paper introduces a simple and effective method, named Learning to Bootstrap (L2B), which enables models to bootstrap themselves using their own predictions without being adversely affected by erroneous pseudo-labels. It achieves this by dynamically adjusting the importance weight between real observed and generated labels, as well as between different samples through meta-learning. Unlike existing instance reweighting methods, the key to our method lies in a new, versatile objective that enables implicit relabeling concurrently, leading to significant improvements without incurring additional costs. L2B offers several benefits over the baseline methods. It yields more robust models that are less susceptible to the impact of noisy labels by guiding the bootstrapping procedure more effectively. It better exploits the valuable information contained in corrupted instances by adapting the weights of both instances and labels. Furthermore, L2B is compatible with existing LNL methods and delivers competitive results spanning natural and medical imaging tasks including classification and segmentation under both synthetic and real-world noise. Extensive experiments demonstrate that our method effectively mitigates the challenges of noisy labels, often necessitating few to no validation samples, and is well generalized to other tasks such as image segmentation. This not only positions it as a robust complement to existing LNL techniques but also underscores its practical applicability. The code and models are available at https://github.com/yuyinzhou/l2b.

arXiv:2202.04181공식 코드 · Papers with Code

TransformNet: Self-supervised representation learning through predicting geometric transformations

Deep neural networks need a big amount of training data, while in the real world there is a scarcity of data available for training purposes. To resolve this issue unsupervised methods are used for training with limited data. In this report, we describe the unsupervised semantic feature learning approach for recognition of the geometric transformation applied to the input data. The basic concept of our approach is that if someone is unaware of the objects in the images, he/she would not be able to quantitatively predict the geometric transformation that was applied to them. This self supervised scheme is based on pretext task and the downstream task. The pretext classification task to quantify the geometric transformations should force the CNN to learn high-level salient features of objects useful for image classification. In our baseline model, we define image rotations by multiples of 90 degrees. The CNN trained on this pretext task will be used for the classification of images in the CIFAR-10 dataset as a downstream task. we run the baseline method using various models, including ResNet, DenseNet, VGG-16, and NIN with a varied number of rotations in feature extracting and fine-tuning settings. In extension of this baseline model we experiment with transformations other than rotation in pretext task. We compare performance of selected models in various settings with different transformations applied to images,various data augmentation techniques as well as using different optimizers. This series of different type of experiments will help us demonstrate the recognition accuracy of our self-supervised model when applied to a downstream task of classification.

arXiv:2202.03987

Data Consistency for Weakly Supervised Learning

In many applications, training machine learning models involves using large amounts of human-annotated data. Obtaining precise labels for the data is expensive. Instead, training with weak supervision provides a low-cost alternative. We propose a novel weak supervision algorithm that processes noisy labels, i.e., weak signals, while also considering features of the training data to produce accurate labels for training. Our method searches over classifiers of the data representation to find plausible labelings. We call this paradigm data consistent weak supervision. A key facet of our framework is that we are able to estimate labels for data examples low or no coverage from the weak supervision. In addition, we make no assumptions about the joint distribution of the weak signals and true labels of the data. Instead, we use weak signals and the data features to solve a constrained optimization that enforces data consistency among the labels we generate. Empirical evaluation of our method on different datasets shows that it significantly outperforms state-of-the-art weak supervision methods on both text and image classification tasks.

arXiv:2202.03760공식 코드 · Papers with Code

Modeling Structure with Undirected Neural Networks

Neural networks are powerful function estimators, leading to their status as a paradigm of choice for modeling structured data. However, unlike other structured representations that emphasize the modularity of the problem -- e.g., factor graphs -- neural networks are usually monolithic mappings from inputs to outputs, with a fixed computation order. This limitation prevents them from capturing different directions of computation and interaction between the modeled variables. In this paper, we combine the representational strengths of factor graphs and of neural networks, proposing undirected neural networks (UNNs): a flexible framework for specifying computations that can be performed in any order. For particular choices, our proposed models subsume and extend many existing architectures: feed-forward, recurrent, self-attention networks, auto-encoders, and networks with implicit layers. We demonstrate the effectiveness of undirected neural architectures, both unstructured and structured, on a range of tasks: tree-constrained dependency parsing, convolutional image classification, and sequence completion with attention. By varying the computation order, we show how a single UNN can be used both as a classifier and a prototype generator, and how it can fill in missing parts of an input sequence, making them a promising field for further research.

arXiv:2202.03555공식 코드 · Papers with Code

data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language

While the general idea of self-supervised learning is identical across modalities, the actual algorithms and objectives differ widely because they were developed with a single modality in mind. To get us closer to general self-supervised learning, we present data2vec, a framework that uses the same learning method for either speech, NLP or computer vision. The core idea is to predict latent representations of the full input data based on a masked view of the input in a self-distillation setup using a standard Transformer architecture. Instead of predicting modality-specific targets such as words, visual tokens or units of human speech which are local in nature, data2vec predicts contextualized latent representations that contain information from the entire input. Experiments on the major benchmarks of speech recognition, image classification, and natural language understanding demonstrate a new state of the art or competitive performance to predominant approaches.