PyTorchKR Papers

“Image Classification”

총 5,746편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2310.08854공식 코드 · Papers with Code

Rank-DETR for High Quality Object Detection

Modern detection transformers (DETRs) use a set of object queries to predict a list of bounding boxes, sort them by their classification confidence scores, and select the top-ranked predictions as the final detection results for the given input image. A highly performant object detector requires accurate ranking for the bounding box predictions. For DETR-based detectors, the top-ranked bounding boxes suffer from less accurate localization quality due to the misalignment between classification scores and localization accuracy, thus impeding the construction of high-quality detectors. In this work, we introduce a simple and highly performant DETR-based object detector by proposing a series of rank-oriented designs, combinedly called Rank-DETR. Our key contributions include: (i) a rank-oriented architecture design that can prompt positive predictions and suppress the negative ones to ensure lower false positive rates, as well as (ii) a rank-oriented loss function and matching cost design that prioritizes predictions of more accurate localization accuracy during ranking to boost the AP under high IoU thresholds. We apply our method to improve the recent SOTA methods (e.g., H-DETR and DINO-DETR) and report strong COCO object detection results when using different backbones such as ResNet-$50$, Swin-T, and Swin-L, demonstrating the effectiveness of our approach. Code is available at \url{https://github.com/LeapLabTHU/Rank-DETR}.

arXiv:1807.03342공식 코드 · Papers with Code

PCL: Proposal Cluster Learning for Weakly Supervised Object Detection

Weakly Supervised Object Detection (WSOD), using only image-level annotations to train object detectors, is of growing importance in object recognition. In this paper, we propose a novel deep network for WSOD. Unlike previous networks that transfer the object detection problem to an image classification problem using Multiple Instance Learning (MIL), our strategy generates proposal clusters to learn refined instance classifiers by an iterative process. The proposals in the same cluster are spatially adjacent and associated with the same object. This prevents the network from concentrating too much on parts of objects instead of whole objects. We first show that instances can be assigned object or background labels directly based on proposal clusters for instance classifier refinement, and then show that treating each cluster as a small new bag yields fewer ambiguities than the directly assigning label method. The iterative instance classifier refinement is implemented online using multiple streams in convolutional neural networks, where the first is an MIL network and the others are for instance classifier refinement supervised by the preceding one. Experiments are conducted on the PASCAL VOC, ImageNet detection, and MS-COCO benchmarks for WSOD. Results show that our method outperforms the previous state of the art significantly.

arXiv:2311.02747공식 코드 · Papers with Code

Attention Modules Improve Image-Level Anomaly Detection for Industrial Inspection: A DifferNet Case Study

Within (semi-)automated visual industrial inspection, learning-based approaches for assessing visual defects, including deep neural networks, enable the processing of otherwise small defect patterns in pixel size on high-resolution imagery. The emergence of these often rarely occurring defect patterns explains the general need for labeled data corpora. To alleviate this issue and advance the current state of the art in unsupervised visual inspection, this work proposes a DifferNet-based solution enhanced with attention modules: AttentDifferNet. It improves image-level detection and classification capabilities on three visual anomaly detection datasets for industrial inspection: InsPLAD-fault, MVTec AD, and Semiconductor Wafer. In comparison to the state of the art, AttentDifferNet achieves improved results, which are, in turn, highlighted throughout our quali-quantitative study. Our quantitative evaluation shows an average improvement - compared to DifferNet - of 1.77 +/- 0.25 percentage points in overall AUROC considering all three datasets, reaching SOTA results in InsPLAD-fault, an industrial inspection in-the-wild dataset. As our variants to AttentDifferNet show great prospects in the context of currently investigated approaches, a baseline is formulated, emphasizing the importance of attention for industrial anomaly detection both in the wild and in controlled environments.

arXiv:2406.17438공식 코드 · Papers with Code

Implicit-Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes

Neural implicit functions have demonstrated significant importance in various areas such as computer vision, graphics. Their advantages include the ability to represent complex shapes and scenes with high fidelity, smooth interpolation capabilities, and continuous representations. Despite these benefits, the development and analysis of implicit functions have been limited by the lack of comprehensive datasets and the substantial computational resources required for their implementation and evaluation. To address these challenges, we introduce "Implicit-Zoo": a large-scale dataset requiring thousands of GPU training days designed to facilitate research and development in this field. Our dataset includes diverse 2D and 3D scenes, such as CIFAR-10, ImageNet-1K, and Cityscapes for 2D image tasks, and the OmniObject3D dataset for 3D vision tasks. We ensure high quality through strict checks, refining or filtering out low-quality data. Using Implicit-Zoo, we showcase two immediate benefits as it enables to: (1) learn token locations for transformer models; (2) directly regress 3D cameras poses of 2D images with respect to NeRF models. This in turn leads to an improved performance in all three task of image classification, semantic segmentation, and 3D pose regression, thereby unlocking new avenues for research.

arXiv:2208.07196공식 코드 · Papers with Code

Determining HEDP Foams' Quality with Multi-View Deep Learning Classification

High energy density physics (HEDP) experiments commonly involve a dynamic wave-front propagating inside a low-density foam. This effect affects its density and hence, its transparency. A common problem in foam production is the creation of defective foams. Accurate information on their dimension and homogeneity is required to classify the foams' quality. Therefore, those parameters are being characterized using a 3D-measuring laser confocal microscope. For each foam, five images are taken: two 2D images representing the top and bottom surface foam planes and three images of side cross-sections from 3D scannings. An expert has to do the complicated, harsh, and exhausting work of manually classifying the foam's quality through the image set and only then determine whether the foam can be used in experiments or not. Currently, quality has two binary levels of normal vs. defective. At the same time, experts are commonly required to classify a sub-class of normal-defective, i.e., foams that are defective but might be sufficient for the needed experiment. This sub-class is problematic due to inconclusive judgment that is primarily intuitive. In this work, we present a novel state-of-the-art multi-view deep learning classification model that mimics the physicist's perspective by automatically determining the foams' quality classification and thus aids the expert. Our model achieved 86\% accuracy on upper and lower surface foam planes and 82\% on the entire set, suggesting interesting heuristics to the problem. A significant added value in this work is the ability to regress the foam quality instead of binary deduction and even explain the decision visually. The source code used in this work, as well as other relevant sources, are available at: https://github.com/Scientific-Computing-Lab-NRCN/Multi-View-Foams.git

arXiv:2307.04390공식 코드 · Papers with Code

CT-based Subchondral Bone Microstructural Analysis in Knee Osteoarthritis via MR-Guided Distillation Learning

Background: MR-based subchondral bone effectively predicts knee osteoarthritis. However, its clinical application is limited by the cost and time of MR. Purpose: We aim to develop a novel distillation-learning-based method named SRRD for subchondral bone microstructural analysis using easily-acquired CT images, which leverages paired MR images to enhance the CT-based analysis model during training. Materials and Methods: Knee joint images of both CT and MR modalities were collected from October 2020 to May 2021. Firstly, we developed a GAN-based generative model to transform MR images into CT images, which was used to establish the anatomical correspondence between the two modalities. Next, we obtained numerous patches of subchondral bone regions of MR images, together with their trabecular parameters (BV / TV, Tb. Th, Tb. Sp, Tb. N) from the corresponding CT image patches via regression. The distillation-learning technique was used to train the regression model and transfer MR structural information to the CT-based model. The regressed trabecular parameters were further used for knee osteoarthritis classification. Results: A total of 80 participants were evaluated. CT-based regression results of trabecular parameters achieved intra-class correlation coefficients (ICCs) of 0.804, 0.773, 0.711, and 0.622 for BV / TV, Tb. Th, Tb. Sp, and Tb. N, respectively. The use of distillation learning significantly improved the performance of the CT-based knee osteoarthritis classification method using the CNN approach, yielding an AUC score of 0.767 (95% CI, 0.681-0.853) instead of 0.658 (95% CI, 0.574-0.742) (p<.001). Conclusions: The proposed SRRD method showed high reliability and validity in MR-CT registration, regression, and knee osteoarthritis classification, indicating the feasibility of subchondral bone microstructural analysis based on CT images.

arXiv:2205.08576공식 코드 · Papers with Code

Label-Efficient Self-Supervised Federated Learning for Tackling Data Heterogeneity in Medical Imaging

The collection and curation of large-scale medical datasets from multiple institutions is essential for training accurate deep learning models, but privacy concerns often hinder data sharing. Federated learning (FL) is a promising solution that enables privacy-preserving collaborative learning among different institutions, but it generally suffers from performance deterioration due to heterogeneous data distributions and a lack of quality labeled data. In this paper, we present a robust and label-efficient self-supervised FL framework for medical image analysis. Our method introduces a novel Transformer-based self-supervised pre-training paradigm that pre-trains models directly on decentralized target task datasets using masked image modeling, to facilitate more robust representation learning on heterogeneous data and effective knowledge transfer to downstream models. Extensive empirical results on simulated and real-world medical imaging non-IID federated datasets show that masked image modeling with Transformers significantly improves the robustness of models against various degrees of data heterogeneity. Notably, under severe data heterogeneity, our method, without relying on any additional pre-training data, achieves an improvement of 5.06%, 1.53% and 4.58% in test accuracy on retinal, dermatology and chest X-ray classification compared to the supervised baseline with ImageNet pre-training. In addition, we show that our federated self-supervised pre-training methods yield models that generalize better to out-of-distribution data and perform more effectively when fine-tuning with limited labeled data, compared to existing FL algorithms. The code is available at https://github.com/rui-yan/SSL-FL.

arXiv:2403.08157공식 코드 · Papers with Code

Multiscale Low-Frequency Memory Network for Improved Feature Extraction in Convolutional Neural Networks

Deep learning and Convolutional Neural Networks (CNNs) have driven major transformations in diverse research areas. However, their limitations in handling low-frequency information present obstacles in certain tasks like interpreting global structures or managing smooth transition images. Despite the promising performance of transformer structures in numerous tasks, their intricate optimization complexities highlight the persistent need for refined CNN enhancements using limited resources. Responding to these complexities, we introduce a novel framework, the Multiscale Low-Frequency Memory (MLFM) Network, with the goal to harness the full potential of CNNs while keeping their complexity unchanged. The MLFM efficiently preserves low-frequency information, enhancing performance in targeted computer vision tasks. Central to our MLFM is the Low-Frequency Memory Unit (LFMU), which stores various low-frequency data and forms a parallel channel to the core network. A key advantage of MLFM is its seamless compatibility with various prevalent networks, requiring no alterations to their original core structure. Testing on ImageNet demonstrated substantial accuracy improvements in multiple 2D CNNs, including ResNet, MobileNet, EfficientNet, and ConvNeXt. Furthermore, we showcase MLFM's versatility beyond traditional image classification by successfully integrating it into image-to-image translation tasks, specifically in semantic segmentation networks like FCN and U-Net. In conclusion, our work signifies a pivotal stride in the journey of optimizing the efficacy and efficiency of CNNs with limited resources. This research builds upon the existing CNN foundations and paves the way for future advancements in computer vision. Our codes are available at https://github.com/AlphaWuSeu/ MLFM.

arXiv:2405.19746공식 코드 · Papers with Code

DenseSeg: Joint Learning for Semantic Segmentation and Landmark Detection Using Dense Image-to-Shape Representation

Purpose: Semantic segmentation and landmark detection are fundamental tasks of medical image processing, facilitating further analysis of anatomical objects. Although deep learning-based pixel-wise classification has set a new-state-of-the-art for segmentation, it falls short in landmark detection, a strength of shape-based approaches. Methods: In this work, we propose a dense image-to-shape representation that enables the joint learning of landmarks and semantic segmentation by employing a fully convolutional architecture. Our method intuitively allows the extraction of arbitrary landmarks due to its representation of anatomical correspondences. We benchmark our method against the state-of-the-art for semantic segmentation (nnUNet), a shape-based approach employing geometric deep learning and a convolutional neural network-based method for landmark detection. Results: We evaluate our method on two medical dataset: one common benchmark featuring the lungs, heart, and clavicle from thorax X-rays, and another with 17 different bones in the paediatric wrist. While our method is on pair with the landmark detection baseline in the thorax setting (error in mm of $2.6\pm0.9$ vs $2.7\pm0.9$), it substantially surpassed it in the more complex wrist setting ($1.1\pm0.6$ vs $1.9\pm0.5$). Conclusion: We demonstrate that dense geometric shape representation is beneficial for challenging landmark detection tasks and outperforms previous state-of-the-art using heatmap regression. While it does not require explicit training on the landmarks themselves, allowing for the addition of new landmarks without necessitating retraining.}

arXiv:2109.13069공식 코드 · Papers with Code

Cluster Attack: Query-based Adversarial Attacks on Graphs with Graph-Dependent Priors

While deep neural networks have achieved great success in graph analysis, recent work has shown that they are vulnerable to adversarial attacks. Compared with adversarial attacks on image classification, performing adversarial attacks on graphs is more challenging because of the discrete and non-differential nature of the adjacent matrix for a graph. In this work, we propose Cluster Attack -- a Graph Injection Attack (GIA) on node classification, which injects fake nodes into the original graph to degenerate the performance of graph neural networks (GNNs) on certain victim nodes while affecting the other nodes as little as possible. We demonstrate that a GIA problem can be equivalently formulated as a graph clustering problem; thus, the discrete optimization problem of the adjacency matrix can be solved in the context of graph clustering. In particular, we propose to measure the similarity between victim nodes by a metric of Adversarial Vulnerability, which is related to how the victim nodes will be affected by the injected fake node, and to cluster the victim nodes accordingly. Our attack is performed in a practical and unnoticeable query-based black-box manner with only a few nodes on the graphs that can be accessed. Theoretical analysis and extensive experiments demonstrate the effectiveness of our method by fooling the node classifiers with only a small number of queries.

arXiv:2409.03901공식 코드 · Papers with Code

Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT Models

This study focuses on identifying the most effective pre-trained model for land use classification in onboard satellite processing, emphasizing achieving high accuracy, computational efficiency, and robustness against noisy data conditions commonly encountered during satellite-based inference. Through extensive experimentation, we compare the performance of traditional CNN-based, ResNet-based, and various pre-trained vision Transformer models. Our findings demonstrate that pre-trained Vision Transformer (ViT) models, particularly MobileViTV2 and EfficientViT-M2, outperform models trained from scratch in terms of accuracy and efficiency. These models achieve high performance with reduced computational requirements and exhibit greater resilience during inference under noisy conditions. While MobileViTV2 has excelled on clean validation data, EfficientViT-M2 has proved more robust when handling noise, making it the most suitable model for onboard satellite EO tasks. Our experimental results demonstrate that EfficientViT-M2 is the optimal choice for reliable and efficient RS-IC in satellite operations, achieving 98.76 % of accuracy, precision, and recall. Precisely, EfficientViT-M2 delivers the highest performance across all metrics, excels in training efficiency (1,000s) and inference time (10s), and demonstrates greater robustness (overall robustness score of 0.79). Consequently, EfficientViT-M2 consumes 63.93 % less power than MobileViTV2 (79.23 W) and 73.26 % less power than SwinTransformer (108.90 W). This highlights its significant advantage in energy efficiency.

arXiv:2410.20302공식 코드 · Papers with Code

Sequential Large Language Model-Based Hyper-parameter Optimization

This study introduces SLLMBO, an innovative framework leveraging large language models (LLMs) for hyperparameter optimization (HPO), incorporating dynamic search space adaptability, enhanced parameter space exploitation, and a novel LLM-tree-structured parzen estimator (LLM-TPE) sampler. By addressing limitations in recent fully LLM-based methods and traditional bayesian optimization (BO), SLLMBO achieves more robust optimization. This comprehensive benchmarking evaluates multiple LLMs, including GPT-3.5-Turbo, GPT-4o, Claude-Sonnet-3.5, and Gemini-1.5-Flash, extending prior work and establishing SLLMBO as the first framework to benchmark a diverse set of LLMs for HPO. By integrating LLMs' established strengths in parameter initialization with the exploitation abilities demonstrated in this study, alongside TPE's exploration capabilities, the LLM-TPE sampler achieves a balanced exploration-exploitation trade-off, reduces API costs, and mitigates premature early stoppings for more effective parameter searches. Across 14 tabular tasks in classification and regression, the LLM-TPE sampler outperformed fully LLM-based methods and achieved superior results over BO methods in 9 tasks. Testing early stopping in budget-constrained scenarios demonstrated competitive performance, indicating that LLM-based methods generally benefit from extended iterations for optimal results. This work lays the foundation for future research exploring open-source LLMs, reproducibility of LLM results in HPO, and benchmarking SLLMBO on complex datasets, such as image classification, segmentation, and machine translation.

arXiv:2003.13964공식 코드 · Papers with Code

Regularizing Class-wise Predictions via Self-knowledge Distillation

Deep neural networks with millions of parameters may suffer from poor generalization due to overfitting. To mitigate the issue, we propose a new regularization method that penalizes the predictive distribution between similar samples. In particular, we distill the predictive distribution between different samples of the same label during training. This results in regularizing the dark knowledge (i.e., the knowledge on wrong predictions) of a single network (i.e., a self-knowledge distillation) by forcing it to produce more meaningful and consistent predictions in a class-wise manner. Consequently, it mitigates overconfident predictions and reduces intra-class variations. Our experimental results on various image classification tasks demonstrate that the simple yet powerful method can significantly improve not only the generalization ability but also the calibration performance of modern convolutional neural networks.

arXiv:2201.12961공식 코드 · Papers with Code

Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations

Existing techniques for model inversion typically rely on hard-to-tune regularizers, such as total variation or feature regularization, which must be individually calibrated for each network in order to produce adequate images. In this work, we introduce Plug-In Inversion, which relies on a simple set of augmentations and does not require excessive hyper-parameter tuning. Under our proposed augmentation-based scheme, the same set of augmentation hyper-parameters can be used for inverting a wide range of image classification models, regardless of input dimensions or the architecture. We illustrate the practicality of our approach by inverting Vision Transformers (ViTs) and Multi-Layer Perceptrons (MLPs) trained on the ImageNet dataset, tasks which to the best of our knowledge have not been successfully accomplished by any previous works.

arXiv:2502.14424v4stat.ML공식 코드 · Papers with Code

생성 학습을 표현 학습으로 확장하기: 분포 매칭 관점의 자기지도 전이학습

Bringing Generative Learning to Representation Learning: Self-Supervised Transfer Learning as Distribution Matching

대부분의 자기지도학습(self-supervised learning) 목적 함수는 표현 붕괴(collapse)를 방지하지만, 목표 표현의 확률 법칙(representation law)은 명시하지 않은 채 남겨둡니다. 본 논문에서는 표현 학습을 분포 매칭(Distribution Matching, DM)으로 정식화하여, 인코더가 유도하는 분포가 명시적인 기하학적 기준 분포(reference law)와 일치하도록 증강 불변(augmentation-invariant) 인코더를 학습합니다. 기준 분포는 학습된 표현 분포가 어떤 형태를 띠어야 하는지 명시하며, 별도로 선택된 불일치도(discrepancy) 척도는 이 목표로부터의 편차를 어떻게 측정할지 결정합니다. 본 연구에서는 말로우스 거리(Mallows distance)를 사용합니다. DM 프레임워크는 방향의 역관계를 드러냅니다. 즉, 생성 학습이 다루기 쉬운 기준 분포를 데이터로 매핑하는 반면, 표현 학습은 데이터를 설계된 기준 분포로 매핑합니다. 본 연구는 모집단 목적 함수를 클래스 중심 분리 및 분류(classification) 오차와 연결하고, 비점근적 신경 시브(neural-sieve) 보장을 증명합니다. 시뮬레이션 및 이미지 벤치마크 결과는 다양체 정류(manifold rectification), 미세 구조 보존, 그리고 서로 다른 레이블 공간 간의 전이(transfer) 성능을 보여줍니다.

arXiv:2102.01955공식 코드 · Papers with Code

Predictive coding feedback results in perceived illusory contours in a recurrent neural network

Modern feedforward convolutional neural networks (CNNs) can now solve some computer vision tasks at super-human levels. However, these networks only roughly mimic human visual perception. One difference from human vision is that they do not appear to perceive illusory contours (e.g. Kanizsa squares) in the same way humans do. Physiological evidence from visual cortex suggests that the perception of illusory contours could involve feedback connections. Would recurrent feedback neural networks perceive illusory contours like humans? In this work we equip a deep feedforward convolutional network with brain-inspired recurrent dynamics. The network was first pretrained with an unsupervised reconstruction objective on a natural image dataset, to expose it to natural object contour statistics. Then, a classification decision layer was added and the model was finetuned on a form discrimination task: squares vs. randomly oriented inducer shapes (no illusory contour). Finally, the model was tested with the unfamiliar ''illusory contour'' configuration: inducer shapes oriented to form an illusory square. Compared with feedforward baselines, the iterative ''predictive coding'' feedback resulted in more illusory contours being classified as physical squares. The perception of the illusory contour was measurable in the luminance profile of the image reconstructions produced by the model, demonstrating that the model really ''sees'' the illusion. Ablation studies revealed that natural image pretraining and feedback error correction are both critical to the perception of the illusion. Finally we validated our conclusions in a deeper network (VGG): adding the same predictive coding feedback dynamics again leads to the perception of illusory contours.

arXiv:2103.00738공식 코드 · Papers with Code

FPS-Net: A Convolutional Fusion Network for Large-Scale LiDAR Point Cloud Segmentation

Scene understanding based on LiDAR point cloud is an essential task for autonomous cars to drive safely, which often employs spherical projection to map 3D point cloud into multi-channel 2D images for semantic segmentation. Most existing methods simply stack different point attributes/modalities (e.g. coordinates, intensity, depth, etc.) as image channels to increase information capacity, but ignore distinct characteristics of point attributes in different image channels. We design FPS-Net, a convolutional fusion network that exploits the uniqueness and discrepancy among the projected image channels for optimal point cloud segmentation. FPS-Net adopts an encoder-decoder structure. Instead of simply stacking multiple channel images as a single input, we group them into different modalities to first learn modality-specific features separately and then map the learned features into a common high-dimensional feature space for pixel-level fusion and learning. Specifically, we design a residual dense block with multiple receptive fields as a building block in the encoder which preserves detailed information in each modality and learns hierarchical modality-specific and fused features effectively. In the FPS-Net decoder, we use a recurrent convolution block likewise to hierarchically decode fused features into output space for pixel-level classification. Extensive experiments conducted on two widely adopted point cloud datasets show that FPS-Net achieves superior semantic segmentation as compared with state-of-the-art projection-based methods. In addition, the proposed modality fusion idea is compatible with typical projection-based methods and can be incorporated into them with consistent performance improvements.

arXiv:2211.11158공식 코드 · Papers with Code

Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification

Concept Bottleneck Models (CBM) are inherently interpretable models that factor model decisions into human-readable concepts. They allow people to easily understand why a model is failing, a critical feature for high-stakes applications. CBMs require manually specified concepts and often under-perform their black box counterparts, preventing their broad adoption. We address these shortcomings and are first to show how to construct high-performance CBMs without manual specification of similar accuracy to black box models. Our approach, Language Guided Bottlenecks (LaBo), leverages a language model, GPT-3, to define a large space of possible bottlenecks. Given a problem domain, LaBo uses GPT-3 to produce factual sentences about categories to form candidate concepts. LaBo efficiently searches possible bottlenecks through a novel submodular utility that promotes the selection of discriminative and diverse information. Ultimately, GPT-3's sentential concepts can be aligned to images using CLIP, to form a bottleneck layer. Experiments demonstrate that LaBo is a highly effective prior for concepts important to visual recognition. In the evaluation with 11 diverse datasets, LaBo bottlenecks excel at few-shot classification: they are 11.7% more accurate than black box linear probes at 1 shot and comparable with more data. Overall, LaBo demonstrates that inherently interpretable models can be widely applied at similar, or better, performance than black box approaches.

arXiv:2303.13496공식 코드 · Papers with Code

The effectiveness of MAE pre-pretraining for billion-scale pretraining

This paper revisits the standard pretrain-then-finetune paradigm used in computer vision for visual recognition tasks. Typically, state-of-the-art foundation models are pretrained using large scale (weakly) supervised datasets with billions of images. We introduce an additional pre-pretraining stage that is simple and uses the self-supervised MAE technique to initialize the model. While MAE has only been shown to scale with the size of models, we find that it scales with the size of the training dataset as well. Thus, our MAE-based pre-pretraining scales with both model and data size making it applicable for training foundation models. Pre-pretraining consistently improves both the model convergence and the downstream transfer performance across a range of model scales (millions to billions of parameters), and dataset sizes (millions to billions of images). We measure the effectiveness of pre-pretraining on 10 different visual recognition tasks spanning image classification, video recognition, object detection, low-shot classification and zero-shot recognition. Our largest model achieves new state-of-the-art results on iNaturalist-18 (91.7%), ImageNet-ReaL (91.1%), 1-shot ImageNet-1k (63.6%), and zero-shot transfer on Food-101 (96.2%). Our study reveals that model initialization plays a significant role, even for web-scale pretraining with billions of images, and our models are available publicly.

arXiv:2412.16955공식 코드 · Papers with Code

NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors

With the advancement of deep learning, object detectors (ODs) with various architectures have achieved significant success in complex scenarios like autonomous driving. Previous adversarial attacks against ODs have been focused on designing customized attacks targeting their specific structures (e.g., NMS and RPN), yielding some results but simultaneously constraining their scalability. Moreover, most efforts against ODs stem from image-level attacks originally designed for classification tasks, resulting in redundant computations and disturbances in object-irrelevant areas (e.g., background). Consequently, how to design a model-agnostic efficient attack to comprehensively evaluate the vulnerabilities of ODs remains challenging and unresolved. In this paper, we propose NumbOD, a brand-new spatial-frequency fusion attack against various ODs, aimed at disrupting object detection within images. We directly leverage the features output by the OD without relying on its internal structures to craft adversarial examples. Specifically, we first design a dual-track attack target selection strategy to select high-quality bounding boxes from OD outputs for targeting. Subsequently, we employ directional perturbations to shift and compress predicted boxes and change classification results to deceive ODs. Additionally, we focus on manipulating the high-frequency components of images to confuse ODs' attention on critical objects, thereby enhancing the attack efficiency. Our extensive experiments on nine ODs and two datasets show that NumbOD achieves powerful attack performance and high stealthiness.