PyTorchKR Papers

“Image Classification”

총 18,403편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2310.03827

Integrating Audio-Visual Features for Multimodal Deepfake Detection

Deepfakes are AI-generated media in which an image or video has been digitally modified. The advancements made in deepfake technology have led to privacy and security issues. Most deepfake detection techniques rely on the detection of a single modality. Existing methods for audio-visual detection do not always surpass that of the analysis based on single modalities. Therefore, this paper proposes an audio-visual-based method for deepfake detection, which integrates fine-grained deepfake identification with binary classification. We categorize the samples into four types by combining labels specific to each single modality. This method enhances the detection under intra-domain and cross-domain testing.

arXiv:2312.09533

Adversarial Robustness on Image Classification with $k$-means

In this paper we explore the challenges and strategies for enhancing the robustness of $k$-means clustering algorithms against adversarial manipulations. We evaluate the vulnerability of clustering algorithms to adversarial attacks, emphasising the associated security risks. Our study investigates the impact of incremental attack strength on training, introduces the concept of transferability between supervised and unsupervised models, and highlights the sensitivity of unsupervised models to sample distributions. We additionally introduce and evaluate an adversarial training method that improves testing performance in adversarial scenarios, and we highlight the importance of various parameters in the proposed training method, such as continuous learning, centroid initialisation, and adversarial step-count.

arXiv:2409.14413

Real-time Detection and Auto focusing of Beam Profiles from Silicon Photonics Gratings using YOLO model

When observing the chip-to-free-space light beams from silicon photonics (SiPh) to free-space, manual adjustment of camera lens is often required to obtain a focused image of the light beams. In this letter, we demonstrated an auto-focusing system based on you-only-look-once (YOLO) model. The trained YOLO model exhibits high classification accuracy of 99.7% and high confidence level >0.95 when detecting light beams from SiPh gratings. A video demonstration of real-time light beam detection, real-time computation of beam width, and auto focusing of light beams are also included.

arXiv:2505.20149

Improvement Strategies for Few-Shot Learning in OCT Image Classification of Rare Retinal Diseases

This paper focuses on using few-shot learning to improve the accuracy of classifying OCT diagnosis images with major and rare classes. We used the GAN-based augmentation strategy as a baseline and introduced several novel methods to further enhance our model. The proposed strategy contains U-GAT-IT for improving the generative part and uses the data balance technique to narrow down the skew of accuracy between all categories. The best model obtained was built with CBAM attention mechanism and fine-tuned InceptionV3, and achieved an overall accuracy of 97.85%, representing a significant improvement over the original baseline.

arXiv:1904.05629

Detecting Repeating Objects using Patch Correlation Analysis

In this paper we describe a new method for detecting and counting a repeating object in an image. While the method relies on a fairly sophisticated deformable part model, unlike existing techniques it estimates the model parameters in an unsupervised fashion thus alleviating the need for a user-annotated training data and avoiding the associated specificity. This automatic fitting process is carried out by exploiting the recurrence of small image patches associated with the repeating object and analyzing their spatial correlation. The analysis allows us to reject outlier patches, recover the visual and shape parameters of the part model, and detect the object instances efficiently. In order to achieve a practical system which is able to cope with diverse images, we describe a simple and intuitive active-learning procedure that updates the object classification by querying the user on very few carefully chosen marginal classifications. Evaluation of the new method against the state-of-the-art techniques demonstrates its ability to achieve higher accuracy through a better user experience.

arXiv:1904.08764

Deep Learning Fundus Image Analysis for Diabetic Retinopathy and Macular Edema Grading

Diabetes is a globally prevalent disease that can cause visible microvascular complications such as diabetic retinopathy and macular edema in the human eye retina, the images of which are today used for manual disease screening. This labor-intensive task could greatly benefit from automatic detection using deep learning technique. Here we present a deep learning system that identifies referable diabetic retinopathy comparably or better than presented in the previous studies, although we use only a small fraction of images (<1/4) in training but are aided with higher image resolutions. We also provide novel results for five different screening and clinical grading systems for diabetic retinopathy and macular edema classification, including results for accurately classifying images according to clinical five-grade diabetic retinopathy and four-grade diabetic macular edema scales. These results suggest, that a deep learning system could increase the cost-effectiveness of screening while attaining higher than recommended performance, and that the system could be applied in clinical examinations requiring finer grading.

arXiv:1908.04008공식 코드 · Papers with Code

Instance Enhancement Batch Normalization: an Adaptive Regulator of Batch Noise

Batch Normalization (BN)(Ioffe and Szegedy 2015) normalizes the features of an input image via statistics of a batch of images and hence BN will bring the noise to the gradient of the training loss. Previous works indicate that the noise is important for the optimization and generalization of deep neural networks, but too much noise will harm the performance of networks. In our paper, we offer a new point of view that self-attention mechanism can help to regulate the noise by enhancing instance-specific information to obtain a better regularization effect. Therefore, we propose an attention-based BN called Instance Enhancement Batch Normalization (IEBN) that recalibrates the information of each channel by a simple linear transformation. IEBN has a good capacity of regulating noise and stabilizing network training to improve generalization even in the presence of two kinds of noise attacks during training. Finally, IEBN outperforms BN with only a light parameter increment in image classification tasks for different network structures and benchmark datasets.

arXiv:2006.05548

3D Point Cloud Feature Explanations Using Gradient-Based Methods

Explainability is an important factor to drive user trust in the use of neural networks for tasks with material impact. However, most of the work done in this area focuses on image analysis and does not take into account 3D data. We extend the saliency methods that have been shown to work on image data to deal with 3D data. We analyse the features in point clouds and voxel spaces and show that edges and corners in 3D data are deemed as important features while planar surfaces are deemed less important. The approach is model-agnostic and can provide useful information about learnt features. Driven by the insight that 3D data is inherently sparse, we visualise the features learnt by a voxel-based classification network and show that these features are also sparse and can be pruned relatively easily, leading to more efficient neural networks. Our results show that the Voxception-ResNet model can be pruned down to 5\% of its parameters with negligible loss in accuracy.

arXiv:2102.01381

Generalized Facial Manipulation Detection with Edge Region Feature Extraction

This paper presents a generalized and robust face manipulation detection method based on the edge region features appearing in images. Most contemporary face synthesis processes include color awkwardness reduction but damage the natural fingerprint in the edge region. In addition, these color correction processes do not proceed in the non-face background region. We also observe that the synthesis process does not consider the natural properties of the image appearing in the time domain. Considering these observations, we propose a facial forensic framework that utilizes pixel-level color features appearing in the edge region of the whole image. Furthermore, our framework includes a 3D-CNN classification model that interprets the extracted color features spatially and temporally. Unlike other existing studies, we conduct authenticity determination by considering all features extracted from multiple frames within one video. Through extensive experiments, including real-world scenarios to evaluate generalized detection ability, we show that our framework outperforms state-of-the-art facial manipulation detection technologies in terms of accuracy and robustness.

arXiv:2108.09112공식 코드 · Papers with Code

Continual Learning for Image-Based Camera Localization

For several emerging technologies such as augmented reality, autonomous driving and robotics, visual localization is a critical component. Directly regressing camera pose/3D scene coordinates from the input image using deep neural networks has shown great potential. However, such methods assume a stationary data distribution with all scenes simultaneously available during training. In this paper, we approach the problem of visual localization in a continual learning setup -- whereby the model is trained on scenes in an incremental manner. Our results show that similar to the classification domain, non-stationary data induces catastrophic forgetting in deep networks for visual localization. To address this issue, a strong baseline based on storing and replaying images from a fixed buffer is proposed. Furthermore, we propose a new sampling method based on coverage score (Buff-CS) that adapts the existing sampling strategies in the buffering process to the problem of visual localization. Results demonstrate consistent improvements over standard buffering methods on two challenging datasets -- 7Scenes, 12Scenes, and also 19Scenes by combining the former scenes.

arXiv:2109.11839

Frequency Pooling: Shift-Equivalent and Anti-Aliasing Downsampling

Convolution utilizes a shift-equivalent prior of images, thus leading to great success in image processing tasks. However, commonly used poolings in convolutional neural networks (CNNs), such as max-pooling, average-pooling, and strided-convolution, are not shift-equivalent. Thus, the shift-equivalence of CNNs is destroyed when convolutions and poolings are stacked. Moreover, anti-aliasing is another essential property of poolings from the perspective of signal processing. However, recent poolings are neither shift-equivalent nor anti-aliasing. To address this issue, we propose a new pooling method that is shift-equivalent and anti-aliasing, named frequency pooling. Frequency pooling first transforms the features into the frequency domain, and then removes the frequency components beyond the Nyquist frequency. Finally, it transforms the features back to the spatial domain. We prove that frequency pooling is shift-equivalent and anti-aliasing based on the property of Fourier transform and Nyquist frequency. Experiments on image classification show that frequency pooling improves accuracy and robustness with respect to the shifts of CNNs.

arXiv:2203.13639

Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustness

Neural architectures based on attention such as vision transformers are revolutionizing image recognition. Their main benefit is that attention allows reasoning about all parts of a scene jointly. In this paper, we show how the global reasoning of (scaled) dot-product attention can be the source of a major vulnerability when confronted with adversarial patch attacks. We provide a theoretical understanding of this vulnerability and relate it to an adversary's ability to misdirect the attention of all queries to a single key token under the control of the adversarial patch. We propose novel adversarial objectives for crafting adversarial patches which target this vulnerability explicitly. We show the effectiveness of the proposed patch attacks on popular image classification (ViTs and DeiTs) and object detection models (DETR). We find that adversarial patches occupying 0.5% of the input can lead to robust accuracies as low as 0% for ViT on ImageNet, and reduce the mAP of DETR on MS COCO to less than 3%.

arXiv:2205.08836

Large Neural Networks Learning from Scratch with Very Few Data and without Explicit Regularization

Recent findings have shown that highly over-parameterized Neural Networks generalize without pretraining or explicit regularization. It is achieved with zero training error, i.e., complete over-fitting by memorizing the training data. This is surprising, since it is completely against traditional machine learning wisdom. In our empirical study we fortify these findings in the domain of fine-grained image classification. We show that very large Convolutional Neural Networks with millions of weights do learn with only a handful of training samples and without image augmentation, explicit regularization or pretraining. We train the architectures ResNet018, ResNet101 and VGG19 on subsets of the difficult benchmark datasets Caltech101, CUB_200_2011, FGVCAircraft, Flowers102 and StanfordCars with 100 classes and more, perform a comprehensive comparative study and draw implications for the practical application of CNNs. Finally, we show that a randomly initialized VGG19 with 140 million weights learns to distinguish airplanes and motorbikes with up to 95% accuracy using only 20 training samples per class.

arXiv:2209.05661공식 코드 · Papers with Code

Unsupervised representation learning with recognition-parametrised probabilistic models

We introduce a new approach to probabilistic unsupervised learning based on the recognition-parametrised model (RPM): a normalised semi-parametric hypothesis class for joint distributions over observed and latent variables. Under the key assumption that observations are conditionally independent given latents, the RPM combines parametric prior and observation-conditioned latent distributions with non-parametric observation marginals. This approach leads to a flexible learnt recognition model capturing latent dependence between observations, without the need for an explicit, parametric generative model. The RPM admits exact maximum-likelihood learning for discrete latents, even for powerful neural-network-based recognition. We develop effective approximations applicable in the continuous-latent case. Experiments demonstrate the effectiveness of the RPM on high-dimensional data, learning image classification from weak indirect supervision; direct image-level latent Dirichlet allocation; and recognition-parametrised Gaussian process factor analysis (RP-GPFA) applied to multi-factorial spatiotemporal datasets. The RPM provides a powerful framework to discover meaningful latent structure underlying observational data, a function critical to both animal and artificial intelligence.

arXiv:2306.17332공식 코드 · Papers with Code

Designing Stable Neural Networks using Convex Analysis and ODEs

Motivated by classical work on the numerical integration of ordinary differential equations we present a ResNet-styled neural network architecture that encodes non-expansive (1-Lipschitz) operators, as long as the spectral norms of the weights are appropriately constrained. This is to be contrasted with the ordinary ResNet architecture which, even if the spectral norms of the weights are constrained, has a Lipschitz constant that, in the worst case, grows exponentially with the depth of the network. Further analysis of the proposed architecture shows that the spectral norms of the weights can be further constrained to ensure that the network is an averaged operator, making it a natural candidate for a learned denoiser in Plug-and-Play algorithms. Using a novel adaptive way of enforcing the spectral norm constraints, we show that, even with these constraints, it is possible to train performant networks. The proposed architecture is applied to the problem of adversarially robust image classification, to image denoising, and finally to the inverse problem of deblurring.

arXiv:2403.15113

Set-membership target search and tracking within an unknown cluttered area using cooperating UAVs equipped with vision systems

This paper addresses the problem of target search and tracking using a fleet of cooperating UAVs evolving in some unknown region of interest containing an a priori unknown number of moving ground targets. Each drone is equipped with an embedded Computer Vision System (CVS), providing an image with labeled pixels and a depth map of the observed part of its environment. Moreover, a box containing the corresponding pixels in the image frame is available when a UAV identifies a target. Hypotheses regarding information provided by the pixel classification, depth map construction, and target identification algorithms are proposed to allow its exploitation by set-membership approaches. A set-membership target location estimator is developed using the information provided by the CVS. Each UAV evaluates sets guaranteed to contain the location of the identified targets and a set possibly containing the locations of targets still to be identified. Then, each UAV uses these sets to search and track targets cooperatively.

arXiv:2408.08855공식 코드 · Papers with Code

DPA: Dual Prototypes Alignment for Unsupervised Adaptation of Vision-Language Models

Vision-language models (VLMs), e.g., CLIP, have shown remarkable potential in zero-shot image classification. However, adapting these models to new domains remains challenging, especially in unsupervised settings where labeled data is unavailable. Recent research has proposed pseudo-labeling approaches to adapt CLIP in an unsupervised manner using unlabeled target data. Nonetheless, these methods struggle due to noisy pseudo-labels resulting from the misalignment between CLIP's visual and textual representations. This study introduces DPA, an unsupervised domain adaptation method for VLMs. DPA introduces the concept of dual prototypes, acting as distinct classifiers, along with the convex combination of their outputs, thereby leading to accurate pseudo-label construction. Next, it ranks pseudo-labels to facilitate robust self-training, particularly during early training. Finally, it addresses visual-textual misalignment by aligning textual prototypes with image prototypes to further improve the adaptation performance. Experiments on 13 downstream vision tasks demonstrate that DPA significantly outperforms zero-shot CLIP and the state-of-the-art unsupervised adaptation baselines.

arXiv:2411.15076v4eess.IV

RankByGene: 교차 모달 순위 일관성을 통한 유전자 유도 조직병리학 표현 학습

RankByGene: Gene-Guided Histopathology Representation Learning Through Cross-Modal Ranking Consistency

공간 전사체학(spatial transcriptomics, ST)은 조직 내 유전자 발현을 매핑하여 필수적인 공간적 맥락을 제공하며, 세포 이질성과 조직 구조에 대한 상세한 연구를 가능하게 한다. 그러나 ST 데이터를 조직학(histology) 이미지와 정렬하는 것은 고유한 공간 왜곡과 모달리티별 변이로 인해 어려움이 있다. 기존 방법은 대부분 직접 정렬에 의존하는데, 이는 복잡한 교차 모달 관계를 포착하지 못하는 경우가 많다. 이러한 한계를 해결하기 위해, 순위 기반 정렬 손실을 사용하여 유전자와 이미지 특징을 정렬하고, 모달리티 간 상대적 유사성을 보존하며 견고한 다중 스케일 정렬을 가능하게 하는 새로운 프레임워크를 제안한다. 정렬의 안정성을 더욱 높이기 위해, 교사-학생 네트워크 구조를 갖춘 자기 지도 지식 증류를 사용하며, 이는 교차 모달 정렬 과정에서 이미지 표현 표류(image-representation drift)를 방지하는 모달 내 안정성 정규화기 역할을 한다. 유전자 발현 예측, 슬라이드 수준 분류, 생존 분석을 아우르는 7개 공개 데이터셋에 대한 광범위한 실험은 본 방법의 효과를 보여 주며, 기존 방법 대비 정렬 및 예측 성능이 개선되었음을 나타낸다. 코드는 https://github.com/winston52/RankByGene 에서 이용할 수 있다.

arXiv:2412.16334

DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment

Self-supervised visual foundation models produce powerful embeddings that achieve remarkable performance on a wide range of downstream tasks. However, unlike vision-language models such as CLIP, self-supervised visual features are not readily aligned with language, hindering their adoption in open-vocabulary tasks. Our method, named dino.txt, unlocks this new ability for DINOv2, a widely used self-supervised visual encoder. We build upon the LiT training strategy, which trains a text encoder to align with a frozen vision model but leads to unsatisfactory results on dense tasks. We propose several key ingredients to improve performance on both global and dense tasks, such as concatenating the [CLS] token with the patch average to train the alignment and curating data using both text and image modalities. With these, we successfully train a CLIP-like model with only a fraction of the computational cost compared to CLIP while achieving state-of-the-art results in zero-shot classification and open-vocabulary semantic segmentation.

arXiv:2502.19949공식 코드 · Papers with Code

Machine-learning for photoplethysmography analysis: Benchmarking feature, image, and signal-based approaches

Photoplethysmography (PPG) is a widely used non-invasive physiological sensing technique, suitable for various clinical applications. Such clinical applications are increasingly supported by machine learning methods, raising the question of the most appropriate input representation and model choice. Comprehensive comparisons, in particular across different input representations, are scarce. We address this gap in the research landscape by a comprehensive benchmarking study covering three kinds of input representations, interpretable features, image representations and raw waveforms, across prototypical regression and classification use cases: blood pressure and atrial fibrillation prediction. In both cases, the best results are achieved by deep neural networks operating on raw time series as input representations. Within this model class, best results are achieved by modern convolutional neural networks (CNNs). but depending on the task setup, shallow CNNs are often also very competitive. We envision that these results will be insightful for researchers to guide their choice on machine learning tasks for PPG data, even beyond the use cases presented in this work.