PyTorchKR Papers

최신 논문

총 10,165편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2303.10343

Supervision Interpolation via LossMix: Generalizing Mixup for Object Detection and Beyond

The success of data mixing augmentations in image classification tasks has been well-received. However, these techniques cannot be readily applied to object detection due to challenges such as spatial misalignment, foreground/background distinction, and plurality of instances. To tackle these issues, we first introduce a novel conceptual framework called Supervision Interpolation (SI), which offers a fresh perspective on interpolation-based augmentations by relaxing and generalizing Mixup. Based on SI, we propose LossMix, a simple yet versatile and effective regularization that enhances the performance and robustness of object detectors and more. Our key insight is that we can effectively regularize the training on mixed data by interpolating their loss errors instead of ground truth labels. Empirical results on the PASCAL VOC and MS COCO datasets demonstrate that LossMix can consistently outperform state-of-the-art methods widely adopted for detection. Furthermore, by jointly leveraging LossMix with unsupervised domain adaptation, we successfully improve existing approaches and set a new state of the art for cross-domain object detection.

논문 ID: document/1002482

Local Window Attention Transformer for Polarimetric SAR Image Classification

Convolutional neural networks (CNNs) have recently found great attention in image classification since deep CNNs have exhibited excellent performance in computer vision. Owing to their immense success, of late, scientists are exploring the functionality of transformers in Earth observation applications. Nevertheless, the primary issue with transformers is that they demand significantly more training data than CNN classifiers. Thus, the use of these transformers in remote sensing is considered challenging, notably in utilizing polarimetric SAR (PolSAR) data, due to the insufficient number of existing labeled data. In this letter, we develop and propose a vision transformer-based framework that utilizes 3D and 2D CNNs as feature extractors and, in addition, local window attention for the effective classification of PolSAR data. Extensive experimental results demonstrated that the developed model PolSARFormer obtained better classification accuracy than the state-of-the-art vision Swin Transformer and FNet algorithms. The PolSARFormer outperformed the Swin Transformer and FNet by the margin of 5.86% and 17.63%, in terms of average accuracy in the San Francisco data benchmark. Moreover , the results over the Flevoland dataset illustrated that the PolSARFormer exceeds several other algorithms, including the ResNet (97.49%), Swin Transformer (96.54%), FNet (95.28%), 2D CNN (94.57%), and AlexNet (91.83%), with a kappa index of 99.30%. The code will be made available publicly at https://github.com/aj1365/PolSARFormer.

arXiv:2303.11098공식 코드 · Papers with Code

Understanding the Role of the Projector in Knowledge Distillation

In this paper we revisit the efficacy of knowledge distillation as a function matching and metric learning problem. In doing so we verify three important design decisions, namely the normalisation, soft maximum function, and projection layers as key ingredients. We theoretically show that the projector implicitly encodes information on past examples, enabling relational gradients for the student. We then show that the normalisation of representations is tightly coupled with the training dynamics of this projector, which can have a large impact on the students performance. Finally, we show that a simple soft maximum function can be used to address any significant capacity gap problems. Experimental results on various benchmark datasets demonstrate that using these insights can lead to superior or comparable performance to state-of-the-art knowledge distillation techniques, despite being much more computationally efficient. In particular, we obtain these results across image classification (CIFAR100 and ImageNet), object detection (COCO2017), and on more difficult distillation objectives, such as training data efficient transformers, whereby we attain a 77.2% top-1 accuracy with DeiT-Ti on ImageNet. Code and models are publicly available.

arXiv:2303.10049공식 코드 · Papers with Code

Uncertainty-informed Mutual Learning for Joint Medical Image Classification and Segmentation

Classification and segmentation are crucial in medical image analysis as they enable accurate diagnosis and disease monitoring. However, current methods often prioritize the mutual learning features and shared model parameters, while neglecting the reliability of features and performances. In this paper, we propose a novel Uncertainty-informed Mutual Learning (UML) framework for reliable and interpretable medical image analysis. Our UML introduces reliability to joint classification and segmentation tasks, leveraging mutual learning with uncertainty to improve performance. To achieve this, we first use evidential deep learning to provide image-level and pixel-wise confidences. Then, an Uncertainty Navigator Decoder is constructed for better using mutual features and generating segmentation results. Besides, an Uncertainty Instructor is proposed to screen reliable masks for classification. Overall, UML could produce confidence estimation in features and performance for each link (classification and segmentation). The experiments on the public datasets demonstrate that our UML outperforms existing methods in terms of both accuracy and robustness. Our UML has the potential to explore the development of more reliable and explainable medical image analysis models. We will release the codes for reproduction after acceptance.

arXiv:2303.09728공식 코드 · Papers with Code

The Cascaded Forward Algorithm for Neural Network Training

Backpropagation algorithm has been widely used as a mainstream learning procedure for neural networks in the past decade, and has played a significant role in the development of deep learning. However, there exist some limitations associated with this algorithm, such as getting stuck in local minima and experiencing vanishing/exploding gradients, which have led to questions about its biological plausibility. To address these limitations, alternative algorithms to backpropagation have been preliminarily explored, with the Forward-Forward (FF) algorithm being one of the most well-known. In this paper we propose a new learning framework for neural networks, namely Cascaded Forward (CaFo) algorithm, which does not rely on BP optimization as that in FF. Unlike FF, our framework directly outputs label distributions at each cascaded block, which does not require generation of additional negative samples and thus leads to a more efficient process at both training and testing. Moreover, in our framework each block can be trained independently, so it can be easily deployed into parallel acceleration systems. The proposed method is evaluated on four public image classification benchmarks, and the experimental results illustrate significant improvement in prediction accuracy in comparison with the baseline.

arXiv:2303.09350

Unsupervised domain adaptation by learning using privileged information

Successful unsupervised domain adaptation is guaranteed only under strong assumptions such as covariate shift and overlap between input domains. The latter is often violated in high-dimensional applications like image classification which, despite this limitation, continues to serve as inspiration and benchmark for algorithm development. In this work, we show that training-time access to side information in the form of auxiliary variables can help relax restrictions on input variables and increase the sample efficiency of learning at the cost of collecting a richer variable set. As this information is assumed available only during training, not in deployment, we call this problem unsupervised domain adaptation by learning using privileged information (DALUPI). To solve this problem, we propose a simple two-stage learning algorithm, inspired by our analysis of the expected error in the target domain, and a practical end-to-end variant for image classification. We propose three evaluation tasks based on classification of entities in photos and anomalies in medical images with different types of available privileged information (binary attributes and single or multiple regions of interest). We demonstrate across these tasks that using privileged information in learning can reduce errors in domain transfer compared to baselines, be robust to spurious correlations in the source domain, and increase sample efficiency.

arXiv:2303.08944

Agnostic Multi-Robust Learning Using ERM

A fundamental problem in robust learning is asymmetry: a learner needs to correctly classify every one of exponentially-many perturbations that an adversary might make to a test-time natural example. In contrast, the attacker only needs to find one successful perturbation. Xiang et al.[2022] proposed an algorithm that in the context of patch attacks for image classification, reduces the effective number of perturbations from an exponential to a polynomial number of perturbations and learns using an ERM oracle. However, to achieve its guarantee, their algorithm requires the natural examples to be robustly realizable. This prompts the natural question; can we extend their approach to the non-robustly-realizable case where there is no classifier with zero robust error? Our first contribution is to answer this question affirmatively by reducing this problem to a setting in which an algorithm proposed by Feige et al.[2015] can be applied, and in the process extend their guarantees. Next, we extend our results to a multi-group setting and introduce a novel agnostic multi-robust learning problem where the goal is to learn a predictor that achieves low robust loss on a (potentially) rich collection of subgroups.

arXiv:2303.09165공식 코드 · Papers with Code

A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation

Deep learning in computer vision has achieved great success with the price of large-scale labeled training data. However, exhaustive data annotation is impracticable for each task of all domains of interest, due to high labor costs and unguaranteed labeling accuracy. Besides, the uncontrollable data collection process produces non-IID training and test data, where undesired duplication may exist. All these nuisances may hinder the verification of typical theories and exposure to new findings. To circumvent them, an alternative is to generate synthetic data via 3D rendering with domain randomization. We in this work push forward along this line by doing profound and extensive research on bare supervised learning and downstream domain adaptation. Specifically, under the well-controlled, IID data setting enabled by 3D rendering, we systematically verify the typical, important learning insights, e.g., shortcut learning, and discover the new laws of various data regimes and network architectures in generalization. We further investigate the effect of image formation factors on generalization, e.g., object scale, material texture, illumination, camera viewpoint, and background in a 3D scene. Moreover, we use the simulation-to-reality adaptation as a downstream task for comparing the transferability between synthetic and real data when used for pre-training, which demonstrates that synthetic data pre-training is also promising to improve real test results. Lastly, to promote future research, we develop a new large-scale synthetic-to-real benchmark for image classification, termed S2RDA, which provides more significant challenges for transfer from simulation to reality. The code and datasets are available at https://github.com/huitangtang/On_the_Utility_of_Synthetic_Data.

arXiv:2303.09105공식 코드 · Papers with Code

Rethinking Model Ensemble in Transfer-based Adversarial Attacks

It is widely recognized that deep learning models lack robustness to adversarial examples. An intriguing property of adversarial examples is that they can transfer across different models, which enables black-box attacks without any knowledge of the victim model. An effective strategy to improve the transferability is attacking an ensemble of models. However, previous works simply average the outputs of different models, lacking an in-depth analysis on how and why model ensemble methods can strongly improve the transferability. In this paper, we rethink the ensemble in adversarial attacks and define the common weakness of model ensemble with two properties: 1) the flatness of loss landscape; and 2) the closeness to the local optimum of each model. We empirically and theoretically show that both properties are strongly correlated with the transferability and propose a Common Weakness Attack (CWA) to generate more transferable adversarial examples by promoting these two properties. Experimental results on both image classification and object detection tasks validate the effectiveness of our approach to improving the adversarial transferability, especially when attacking adversarially trained models. We also successfully apply our method to attack a black-box large vision-language model -- Google's Bard, showing the practical effectiveness. Code is available at \url{https://github.com/huanranchen/AdversarialAttacks}.

arXiv:2303.09035공식 코드 · Papers with Code

Extracting the Brain-like Representation by an Improved Self-Organizing Map for Image Classification

Backpropagation-based supervised learning has achieved great success in computer vision tasks. However, its biological plausibility is always controversial. Recently, the bio-inspired Hebbian learning rule (HLR) has received extensive attention. Self-Organizing Map (SOM) uses the competitive HLR to establish connections between neurons, obtaining visual features in an unsupervised way. Although the representation of SOM neurons shows some brain-like characteristics, it is still quite different from the neuron representation in the human visual cortex. This paper proposes an improved SOM with multi-winner, multi-code, and local receptive field, named mlSOM. We observe that the neuron representation of mlSOM is similar to the human visual cortex. Furthermore, mlSOM shows a sparse distributed representation of objects, which has also been found in the human inferior temporal area. In addition, experiments show that mlSOM achieves better classification accuracy than the original SOM and other state-of-the-art HLR-based methods. The code is accessible at https://github.com/JiaHongZ/mlSOM.

arXiv:2303.09005

Conditional Synthetic Food Image Generation

Generative Adversarial Networks (GAN) have been widely investigated for image synthesis based on their powerful representation learning ability. In this work, we explore the StyleGAN and its application of synthetic food image generation. Despite the impressive performance of GAN for natural image generation, food images suffer from high intra-class diversity and inter-class similarity, resulting in overfitting and visual artifacts for synthetic images. Therefore, we aim to explore the capability and improve the performance of GAN methods for food image generation. Specifically, we first choose StyleGAN3 as the baseline method to generate synthetic food images and analyze the performance. Then, we identify two issues that can cause performance degradation on food images during the training phase: (1) inter-class feature entanglement during multi-food classes training and (2) loss of high-resolution detail during image downsampling. To address both issues, we propose to train one food category at a time to avoid feature entanglement and leverage image patches cropped from high-resolution datasets to retain fine details. We evaluate our method on the Food-101 dataset and show improved quality of generated synthetic food images compared with the baseline. Finally, we demonstrate the great potential of improving the performance of downstream tasks, such as food image classification by including high-quality synthetic training samples in the data augmentation.

논문 ID: 3161.35483

Semantic Structure Enhanced Contrastive Adversarial Hash Network for Cross-media Representation Learning

Deep cross-media hashing technology provides an efficient cross-media representation learning solution for cross-media search. However, the existing methods do not consider both fine-grained semantic features and semantic structures to mine implicit cross-media semantic associations, which leads to weaker semantic discrimination and consistency for cross-media representation. To tackle this problem, we propose a novel semantic structure enhanced contrastive adversarial hash network for cross-media representation learning (SCAHN). Firstly, in order to capture more fine-grained cross-media semantic associations, a fine-grained cross-media attention feature learning network is constructed, thus the learned saliency features of different modalities are more conducive to cross-media semantic alignment and fusion. Secondly, for further improving learning ability of implicit cross-media semantic associations, a semantic label association graph is constructed, and the graph convolutional network is utilized to mine the implicit semantic structures, thus guiding learning of discriminative features of different modalities. Thirdly, a cross-media and intra-media contrastive adversarial representation learning mechanism is proposed to further enhance the semantic discriminativeness of different modal representations, and a dual-way adversarial learning strategy is developed to maximize cross-media semantic associations, so as to obtain cross-media unified representations with stronger discriminativeness and semantic consistency preserving power. Extensive experiments on several cross-media benchmark datasets demonstrate that the proposed SCAHN outperforms the state-of-the-art methods.

arXiv:2303.08720

Practicality of generalization guarantees for unsupervised domain adaptation with neural networks

Understanding generalization is crucial to confidently engineer and deploy machine learning models, especially when deployment implies a shift in the data domain. For such domain adaptation problems, we seek generalization bounds which are tractably computable and tight. If these desiderata can be reached, the bounds can serve as guarantees for adequate performance in deployment. However, in applications where deep neural networks are the models of choice, deriving results which fulfill these remains an unresolved challenge; most existing bounds are either vacuous or has non-estimable terms, even in favorable conditions. In this work, we evaluate existing bounds from the literature with potential to satisfy our desiderata on domain adaptation image classification tasks, where deep neural networks are preferred. We find that all bounds are vacuous and that sample generalization terms account for much of the observed looseness, especially when these terms interact with measures of domain shift. To overcome this and arrive at the tightest possible results, we combine each bound with recent data-dependent PAC-Bayes analysis, greatly improving the guarantees. We find that, when domain overlap can be assumed, a simple importance weighting extension of previous work provides the tightest estimable bound. Finally, we study which terms dominate the bounds and identify possible directions for further improvement.

arXiv:2303.08360공식 코드 · Papers with Code

Knowledge Distillation from Single to Multi Labels: an Empirical Study

Knowledge distillation (KD) has been extensively studied in single-label image classification. However, its efficacy for multi-label classification remains relatively unexplored. In this study, we firstly investigate the effectiveness of classical KD techniques, including logit-based and feature-based methods, for multi-label classification. Our findings indicate that the logit-based method is not well-suited for multi-label classification, as the teacher fails to provide inter-category similarity information or regularization effect on student model's training. Moreover, we observe that feature-based methods struggle to convey compact information of multiple labels simultaneously. Given these limitations, we propose that a suitable dark knowledge should incorporate class-wise information and be highly correlated with the final classification results. To address these issues, we introduce a novel distillation method based on Class Activation Maps (CAMs), which is both effective and straightforward to implement. Across a wide range of settings, CAMs-based distillation consistently outperforms other methods.

arXiv:2303.08817공식 코드 · Papers with Code

DeepMIM: Deep Supervision for Masked Image Modeling

Deep supervision, which involves extra supervisions to the intermediate features of a neural network, was widely used in image classification in the early deep learning era since it significantly reduces the training difficulty and eases the optimization like avoiding gradient vanish over the vanilla training. Nevertheless, with the emergence of normalization techniques and residual connection, deep supervision in image classification was gradually phased out. In this paper, we revisit deep supervision for masked image modeling (MIM) that pre-trains a Vision Transformer (ViT) via a mask-and-predict scheme. Experimentally, we find that deep supervision drives the shallower layers to learn more meaningful representations, accelerates model convergence, and expands attention diversities. Our approach, called DeepMIM, significantly boosts the representation capability of each layer. In addition, DeepMIM is compatible with many MIM models across a range of reconstruction targets. For instance, using ViT-B, DeepMIM on MAE achieves 84.2 top-1 accuracy on ImageNet, outperforming MAE by +0.6. By combining DeepMIM with a stronger tokenizer CLIP, our model achieves state-of-the-art performance on various downstream tasks, including image classification (85.6 top-1 accuracy on ImageNet-1K, outperforming MAE-CLIP by +0.8), object detection (52.8 APbox on COCO) and semantic segmentation (53.1 mIoU on ADE20K). Code and models are available at https://github.com/OliverRensu/DeepMIM.

arXiv:2303.08810공식 코드 · Papers with Code

BiFormer: Vision Transformer with Bi-Level Routing Attention

As the core building block of vision transformers, attention is a powerful tool to capture long-range dependency. However, such power comes at a cost: it incurs a huge computation burden and heavy memory footprint as pairwise token interaction across all spatial locations is computed. A series of works attempt to alleviate this problem by introducing handcrafted and content-agnostic sparsity into attention, such as restricting the attention operation to be inside local windows, axial stripes, or dilated windows. In contrast to these approaches, we propose a novel dynamic sparse attention via bi-level routing to enable a more flexible allocation of computations with content awareness. Specifically, for a query, irrelevant key-value pairs are first filtered out at a coarse region level, and then fine-grained token-to-token attention is applied in the union of remaining candidate regions (\ie, routed regions). We provide a simple yet effective implementation of the proposed bi-level routing attention, which utilizes the sparsity to save both computation and memory while involving only GPU-friendly dense matrix multiplications. Built with the proposed bi-level routing attention, a new general vision transformer, named BiFormer, is then presented. As BiFormer attends to a small subset of relevant tokens in a \textbf{query adaptive} manner without distraction from other irrelevant ones, it enjoys both good performance and high computational efficiency, especially in dense prediction tasks. Empirical results across several computer vision tasks such as image classification, object detection, and semantic segmentation verify the effectiveness of our design. Code is available at \url{https://github.com/rayleizhu/BiFormer}.

arXiv:2303.08685공식 코드 · Papers with Code

Making Vision Transformers Efficient from A Token Sparsification View

The quadratic computational complexity to the number of tokens limits the practical applications of Vision Transformers (ViTs). Several works propose to prune redundant tokens to achieve efficient ViTs. However, these methods generally suffer from (i) dramatic accuracy drops, (ii) application difficulty in the local vision transformer, and (iii) non-general-purpose networks for downstream tasks. In this work, we propose a novel Semantic Token ViT (STViT), for efficient global and local vision transformers, which can also be revised to serve as backbone for downstream tasks. The semantic tokens represent cluster centers, and they are initialized by pooling image tokens in space and recovered by attention, which can adaptively represent global or local semantic information. Due to the cluster properties, a few semantic tokens can attain the same effect as vast image tokens, for both global and local vision transformers. For instance, only 16 semantic tokens on DeiT-(Tiny,Small,Base) can achieve the same accuracy with more than 100% inference speed improvement and nearly 60% FLOPs reduction; on Swin-(Tiny,Small,Base), we can employ 16 semantic tokens in each window to further speed it up by around 20% with slight accuracy increase. Besides great success in image classification, we also extend our method to video recognition. In addition, we design a STViT-R(ecover) network to restore the detailed spatial information based on the STViT, making it work for downstream tasks, which is powerless for previous token sparsification methods. Experiments demonstrate that our method can achieve competitive results compared to the original networks in object detection and instance segmentation, with over 30% FLOPs reduction for backbone. Code is available at http://github.com/changsn/STViT-R

arXiv:2303.08678

Visual Prompt Based Personalized Federated Learning

As a popular paradigm of distributed learning, personalized federated learning (PFL) allows personalized models to improve generalization ability and robustness by utilizing knowledge from all distributed clients. Most existing PFL algorithms tackle personalization in a model-centric way, such as personalized layer partition, model regularization, and model interpolation, which all fail to take into account the data characteristics of distributed clients. In this paper, we propose a novel PFL framework for image classification tasks, dubbed pFedPT, that leverages personalized visual prompts to implicitly represent local data distribution information of clients and provides that information to the aggregation model to help with classification tasks. Specifically, in each round of pFedPT training, each client generates a local personalized prompt related to local data distribution. Then, the local model is trained on the input composed of raw data and a visual prompt to learn the distribution information contained in the prompt. During model testing, the aggregated model obtains prior knowledge of the data distributions based on the prompts, which can be seen as an adaptive fine-tuning of the aggregation model to improve model performances on different clients. Furthermore, the visual prompt can be added as an orthogonal method to implement personalization on the client for existing FL methods to boost their performance. Experiments on the CIFAR10 and CIFAR100 datasets show that pFedPT outperforms several state-of-the-art (SOTA) PFL algorithms by a large margin in various settings.

arXiv:2303.08446공식 코드 · Papers with Code

Task-specific Fine-tuning via Variational Information Bottleneck for Weakly-supervised Pathology Whole Slide Image Classification

While Multiple Instance Learning (MIL) has shown promising results in digital Pathology Whole Slide Image (WSI) classification, such a paradigm still faces performance and generalization problems due to challenges in high computational costs on Gigapixel WSIs and limited sample size for model training. To deal with the computation problem, most MIL methods utilize a frozen pretrained model from ImageNet to obtain representations first. This process may lose essential information owing to the large domain gap and hinder the generalization of model due to the lack of image-level training-time augmentations. Though Self-supervised Learning (SSL) proposes viable representation learning schemes, the improvement of the downstream task still needs to be further explored in the conversion from the task-agnostic features of SSL to the task-specifics under the partial label supervised learning. To alleviate the dilemma of computation cost and performance, we propose an efficient WSI fine-tuning framework motivated by the Information Bottleneck theory. The theory enables the framework to find the minimal sufficient statistics of WSI, thus supporting us to fine-tune the backbone into a task-specific representation only depending on WSI-level weak labels. The WSI-MIL problem is further analyzed to theoretically deduce our fine-tuning method. Our framework is evaluated on five pathology WSI datasets on various WSI heads. The experimental results of our fine-tuned representations show significant improvements in both accuracy and generalization compared with previous works. Source code will be available at https://github.com/invoker-LL/WSI-finetuning.

arXiv:2303.08207

Is forgetting less a good inductive bias for forward transfer?

One of the main motivations of studying continual learning is that the problem setting allows a model to accrue knowledge from past tasks to learn new tasks more efficiently. However, recent studies suggest that the key metric that continual learning algorithms optimize, reduction in catastrophic forgetting, does not correlate well with the forward transfer of knowledge. We believe that the conclusion previous works reached is due to the way they measure forward transfer. We argue that the measure of forward transfer to a task should not be affected by the restrictions placed on the continual learner in order to preserve knowledge of previous tasks. Instead, forward transfer should be measured by how easy it is to learn a new task given a set of representations produced by continual learning on previous tasks. Under this notion of forward transfer, we evaluate different continual learning algorithms on a variety of image classification benchmarks. Our results indicate that less forgetful representations lead to a better forward transfer suggesting a strong correlation between retaining past information and learning efficiency on new tasks. Further, we found less forgetful representations to be more diverse and discriminative compared to their forgetful counterparts.