PyTorchKR Papers

“Image Classification”

총 18,403편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:1412.1123

DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection

Contour detection has been a fundamental component in many image segmentation and object detection systems. Most previous work utilizes low-level features such as texture or saliency to detect contours and then use them as cues for a higher-level task such as object detection. However, we claim that recognizing objects and predicting contours are two mutually related tasks. Contrary to traditional approaches, we show that we can invert the commonly established pipeline: instead of detecting contours with low-level cues for a higher-level recognition task, we exploit object-related features as high-level cues for contour detection. We achieve this goal by means of a multi-scale deep network that consists of five convolutional layers and a bifurcated fully-connected sub-network. The section from the input layer to the fifth convolutional layer is fixed and directly lifted from a pre-trained network optimized over a large-scale object classification task. This section of the network is applied to four different scales of the image input. These four parallel and identical streams are then attached to a bifurcated sub-network consisting of two independently-trained branches. One branch learns to predict the contour likelihood (with a classification objective) whereas the other branch is trained to learn the fraction of human labelers agreeing about the contour presence at a given point (with a regression criterion). We show that without any feature engineering our multi-scale deep learning approach achieves state-of-the-art results in contour detection.

arXiv:2011.12506

Using Radiomics as Prior Knowledge for Thorax Disease Classification and Localization in Chest X-rays

Chest X-ray becomes one of the most common medical diagnoses due to its noninvasiveness. The number of chest X-ray images has skyrocketed, but reading chest X-rays still have been manually performed by radiologists, which creates huge burnouts and delays. Traditionally, radiomics, as a subfield of radiology that can extract a large number of quantitative features from medical images, demonstrates its potential to facilitate medical imaging diagnosis before the deep learning era. In this paper, we develop an end-to-end framework, ChexRadiNet, that can utilize the radiomics features to improve the abnormality classification performance. Specifically, ChexRadiNet first applies a light-weight but efficient triplet-attention mechanism to classify the chest X-rays and highlight the abnormal regions. Then it uses the generated class activation map to extract radiomic features, which further guides our model to learn more robust image features. After a number of iterations and with the help of radiomic features, our framework can converge to more accurate image regions. We evaluate the ChexRadiNet framework using three public datasets: NIH ChestX-ray, CheXpert, and MIMIC-CXR. We find that ChexRadiNet outperforms the state-of-the-art on both disease detection (0.843 in AUC) and localization (0.679 in T(IoU) = 0.1). We will make the code publicly available at https://github.com/bionlplab/lung_disease_detection_amia2021, with the hope that this method can facilitate the development of automatic systems with a higher-level understanding of the radiological world.

arXiv:2209.14169공식 코드 · Papers with Code

CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention

Contrastive Language-Image Pre-training (CLIP) has been shown to learn visual representations with great transferability, which achieves promising accuracy for zero-shot classification. To further improve its downstream performance, existing works propose additional learnable modules upon CLIP and fine-tune them by few-shot training sets. However, the resulting extra training cost and data requirement severely hinder the efficiency for model deployment and knowledge transfer. In this paper, we introduce a free-lunch enhancement method, CALIP, to boost CLIP's zero-shot performance via a parameter-free Attention module. Specifically, we guide visual and textual representations to interact with each other and explore cross-modal informative features via attention. As the pre-training has largely reduced the embedding distances between two modalities, we discard all learnable parameters in the attention and bidirectionally update the multi-modal features, enabling the whole process to be parameter-free and training-free. In this way, the images are blended with textual-aware signals and the text representations become visual-guided for better adaptive zero-shot alignment. We evaluate CALIP on various benchmarks of 14 datasets for both 2D image and 3D point cloud few-shot classification, showing consistent zero-shot performance improvement over CLIP. Based on that, we further insert a small number of linear layers in CALIP's attention module and verify our robustness under the few-shot settings, which also achieves leading performance compared to existing methods. Those extensive experiments demonstrate the superiority of our approach for efficient enhancement of CLIP.

arXiv:2611.13849v1cs.CV

위성 사전학습은 하나가 아니다: 장면 분류를 위한 범용 및 지구 관측 파운데이션 모델의 짝지은 비교 연구

Satellite Pretraining Is Not One Thing: A Matched-Pair Study of Generic and Earth-Observation Foundation Models for Scene Classification

지리공간 파운데이션 모델은 위성 및 항공 영상으로 사전학습되지만, 이러한 인코더가 적은 레이블의 토지 이용/토지 피복 매핑에서 강력한 범용 인코더를 능가하는지는 여전히 불분명하다. 기존 비교가 사전학습 데이터를 분리해 다룬 경우가 드물기 때문이다. 우리는 목적 함수와 아키텍처를 공유하는 지구 관측(EO) 인코더와 범용 인코더의 다섯 쌍(DINO/SatDINO, DINOv3/DINOv3-SAT, MAE/SatMAE, MAE/Scale-MAE, CLIP/RemoteCLIP)을, 다섯 개의 RGB 장면 분류 데이터셋(0.06-30 m GSD)에 대한 14개 고정 인코더 벤치마크 내에서 연구한다. 고유 전처리를 사용하여, 짝지은 이미지별 유의성 검정을 활용해 여섯 가지 저레이블 분할에서 k-NN, 선형 및 어텐티브 프로브와 이미지 검색을 평가한다. EO 사전학습은 일률적으로 유익하지 않다. 대부분의 데이터셋과 지표에서 세 쌍(SatDINO, Scale-MAE, RemoteCLIP; 후자는 보지 못한 데이터셋에서만 평가)은 유의하게 향상시키고 두 쌍은 유의하게 악화시키며(선형 프로브: DINOv3-SAT는 최대 22.5포인트, SatMAE는 최대 8.8포인트), 동일한 fMoW-RGB 영상으로 사전학습된 두 MAE에서도 상반된 결과가 나타난다. 이러한 효과는 패치 토큰 풀링과 어텐티브 프로빙에 대해 견고하고, 작은 인공 객체에 집중되며, 레이블이 1-5%일 때 가장 크다. 인코더 전반에서 고정된 임베딩의 실루엣 점수는 k-NN 정확도와 검색 mAP를 거의 완벽하게 예측한다(다섯 개 데이터셋 중 네 개에서 Spearman $ρ\geq 0.96$). 따라서 위성 영상 사전학습은 신뢰할 만한 선택 기준이 아니며, 후보 체크포인트는 대상 데이터에서 검증되어야 한다.

arXiv:2009.13364

RS-MetaNet: Deep meta metric learning for few-shot remote sensing scene classification

Training a modern deep neural network on massive labeled samples is the main paradigm in solving the scene classification problem for remote sensing, but learning from only a few data points remains a challenge. Existing methods for few-shot remote sensing scene classification are performed in a sample-level manner, resulting in easy overfitting of learned features to individual samples and inadequate generalization of learned category segmentation surfaces. To solve this problem, learning should be organized at the task level rather than the sample level. Learning on tasks sampled from a task family can help tune learning algorithms to perform well on new tasks sampled in that family. Therefore, we propose a simple but effective method, called RS-MetaNet, to resolve the issues related to few-shot remote sensing scene classification in the real world. On the one hand, RS-MetaNet raises the level of learning from the sample to the task by organizing training in a meta way, and it learns to learn a metric space that can well classify remote sensing scenes from a series of tasks. We also propose a new loss function, called Balance Loss, which maximizes the generalization ability of the model to new samples by maximizing the distance between different categories, providing the scenes in different categories with better linear segmentation planes while ensuring model fit. The experimental results on three open and challenging remote sensing datasets, UCMerced\_LandUse, NWPU-RESISC45, and Aerial Image Data, demonstrate that our proposed RS-MetaNet method achieves state-of-the-art results in cases where there are only 1-20 labeled samples.

arXiv:1912.00578

Exposing and Correcting the Gender Bias in Image Captioning Datasets and Models

The task of image captioning implicitly involves gender identification. However, due to the gender bias in data, gender identification by an image captioning model suffers. Also, the gender-activity bias, owing to the word-by-word prediction, influences other words in the caption prediction, resulting in the well-known problem of label bias. In this work, we investigate gender bias in the COCO captioning dataset and show that it engenders not only from the statistical distribution of genders with contexts but also from the flawed annotation by the human annotators. We look at the issues created by this bias in the trained models. We propose a technique to get rid of the bias by splitting the task into 2 subtasks: gender-neutral image captioning and gender classification. By this decoupling, the gender-context influence can be eradicated. We train the gender-neutral image captioning model, which gives comparable results to a gendered model even when evaluating against a dataset that possesses a similar bias as the training data. Interestingly, the predictions by this model on images with no humans, are also visibly different from the one trained on gendered captions. We train gender classifiers using the available bounding box and mask-based annotations for the person in the image. This allows us to get rid of the context and focus on the person to predict the gender. By substituting the genders into the gender-neutral captions, we get the final gendered predictions. Our predictions achieve similar performance to a model trained with gender, and at the same time are devoid of gender bias. Finally, our main result is that on an anti-stereotypical dataset, our model outperforms a popular image captioning model which is trained with gender.

arXiv:2105.06499

Improved Algorithms for Agnostic Pool-based Active Classification

We consider active learning for binary classification in the agnostic pool-based setting. The vast majority of works in active learning in the agnostic setting are inspired by the CAL algorithm where each query is uniformly sampled from the disagreement region of the current version space. The sample complexity of such algorithms is described by a quantity known as the disagreement coefficient which captures both the geometry of the hypothesis space as well as the underlying probability space. To date, the disagreement coefficient has been justified by minimax lower bounds only, leaving the door open for superior instance dependent sample complexities. In this work we propose an algorithm that, in contrast to uniform sampling over the disagreement region, solves an experimental design problem to determine a distribution over examples from which to request labels. We show that the new approach achieves sample complexity bounds that are never worse than the best disagreement coefficient-based bounds, but in specific cases can be dramatically smaller. From a practical perspective, the proposed algorithm requires no hyperparameters to tune (e.g., to control the aggressiveness of sampling), and is computationally efficient by means of assuming access to an empirical risk minimization oracle (without any constraints). Empirically, we demonstrate that our algorithm is superior to state of the art agnostic active learning algorithms on image classification datasets.

arXiv:2402.09962공식 코드 · Papers with Code

ViGEO: an Assessment of Vision GNNs in Earth Observation

Satellite missions and Earth Observation (EO) systems represent fundamental assets for environmental monitoring and the timely identification of catastrophic events, long-term monitoring of both natural resources and human-made assets, such as vegetation, water bodies, forests as well as buildings. Different EO missions enables the collection of information on several spectral bandwidths, such as MODIS, Sentinel-1 and Sentinel-2. Thus, given the recent advances of machine learning, computer vision and the availability of labeled data, researchers demonstrated the feasibility and the precision of land-use monitoring systems and remote sensing image classification through the use of deep neural networks. Such systems may help domain experts and governments in constant environmental monitoring, enabling timely intervention in case of catastrophic events (e.g., forest wildfire in a remote area). Despite the recent advances in the field of computer vision, many works limit their analysis on Convolutional Neural Networks (CNNs) and, more recently, to vision transformers (ViTs). Given the recent successes of Graph Neural Networks (GNNs) on non-graph data, such as time-series and images, we investigate the performances of a recent Vision GNN architecture (ViG) applied to the task of land cover classification. The experimental results show that ViG achieves state-of-the-art performances in multiclass and multilabel classification contexts, surpassing both ViT and ResNet on large-scale benchmarks.

arXiv:2405.10825

Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities

Large language models (LLMs) have received considerable attention recently due to their outstanding comprehension and reasoning capabilities, leading to great progress in many fields. The advancement of LLM techniques also offers promising opportunities to automate many tasks in the telecommunication (telecom) field. After pre-training and fine-tuning, LLMs can perform diverse downstream tasks based on human instructions, paving the way to artificial general intelligence (AGI)-enabled 6G. Given the great potential of LLM technologies, this work aims to provide a comprehensive overview of LLM-enabled telecom networks. In particular, we first present LLM fundamentals, including model architecture, pre-training, fine-tuning, inference and utilization, model evaluation, and telecom deployment. Then, we introduce LLM-enabled key techniques and telecom applications in terms of generation, classification, optimization, and prediction problems. Specifically, the LLM-enabled generation applications include telecom domain knowledge, code, and network configuration generation. After that, the LLM-based classification applications involve network security, text, image, and traffic classification problems. Moreover, multiple LLM-enabled optimization techniques are introduced, such as automated reward function design for reinforcement learning and verbal reinforcement learning. Furthermore, for LLM-aided prediction problems, we discussed time-series prediction models and multi-modality prediction problems for telecom. Finally, we highlight the challenges and identify the future directions of LLM-enabled telecom networks.

arXiv:2411.08530

Efficient Whole Slide Image Classification through Fisher Vector Representation

The advancement of digital pathology, particularly through computational analysis of whole slide images (WSI), is poised to significantly enhance diagnostic precision and efficiency. However, the large size and complexity of WSIs make it difficult to analyze and classify them using computers. This study introduces a novel method for WSI classification by automating the identification and examination of the most informative patches, thus eliminating the need to process the entire slide. Our method involves two-stages: firstly, it extracts only a few patches from the WSIs based on their pathological significance; and secondly, it employs Fisher vectors (FVs) for representing features extracted from these patches, which is known for its robustness in capturing fine-grained details. This approach not only accentuates key pathological features within the WSI representation but also significantly reduces computational overhead, thus making the process more efficient and scalable. We have rigorously evaluated the proposed method across multiple datasets to benchmark its performance against comprehensive WSI analysis and contemporary weakly-supervised learning methodologies. The empirical results indicate that our focused analysis of select patches, combined with Fisher vector representation, not only aligns with, but at times surpasses, the classification accuracy of standard practices. Moreover, this strategy notably diminishes computational load and resource expenditure, thereby establishing an efficient and precise framework for WSI analysis in the realm of digital pathology.

arXiv:2502.11323공식 코드 · Papers with Code

A statistical theory of overfitting for imbalanced classification

Classification with imbalanced data is a common challenge in data analysis, where certain classes (minority classes) account for a small fraction of the training data compared with other classes (majority classes). Classical statistical theory based on large-sample asymptotics and finite-sample corrections is often ineffective for high-dimensional data, leaving many overfitting phenomena in empirical machine learning unexplained. In this paper, we develop a statistical theory for high-dimensional imbalanced classification by investigating support vector machines and logistic regression. We find that dimensionality induces truncation or skewing effects on the logit distribution, which we characterize via a variational problem under high-dimensional asymptotics. In particular, for linearly separable data generated from a two-component Gaussian mixture model, the logits from each class follow a normal distribution $\mathsf{N}(0,1)$ on the testing set, but asymptotically follow a rectified normal distribution $\max\{\kappa, \mathsf{N}(0,1)\}$ on the training set -- which is a pervasive phenomenon we verified on tabular data, image data, and text data. This phenomenon explains why the minority class is more severely affected by overfitting. Further, we show that margin rebalancing, which incorporates class sizes into the loss function, is crucial for mitigating the accuracy drop for the minority class. Our theory also provides insights into the effects of overfitting on calibration and other uncertain quantification measures.

arXiv:1805.07258

Neural Network Compression using Transform Coding and Clustering

With the deployment of neural networks on mobile devices and the necessity of transmitting neural networks over limited or expensive channels, the file size of the trained model was identified as bottleneck. In this paper, we propose a codec for the compression of neural networks which is based on transform coding for convolutional and dense layers and on clustering for biases and normalizations. By using this codec, we achieve average compression factors between 7.9-9.3 while the accuracy of the compressed networks for image classification decreases only by 1%-2%, respectively.

arXiv:2005.10045공식 코드 · Papers with Code

Sparse data to structured imageset transformation

Machine learning problems involving sparse datasets may benefit from the use of convolutional neural networks if the numbers of samples and features are very large. Such datasets are increasingly more frequently encountered in a variety of different domains. We convert such datasets to imagesets while attempting to give each image structure that is amenable for use with convolutional neural networks. Experimental results on two publicly available, sparse datasets show that the approach can boost classification performance compared to other methods, which may be attributed to the formation of visually distinguishable shapes on the resultant images.

arXiv:2205.00142공식 코드 · Papers with Code

Multimodal Representation Learning With Text and Images

In recent years, multimodal AI has seen an upward trend as researchers are integrating data of different types such as text, images, speech into modelling to get the best results. This project leverages multimodal AI and matrix factorization techniques for representation learning, on text and image data simultaneously, thereby employing the widely used techniques of Natural Language Processing (NLP) and Computer Vision. The learnt representations are evaluated using downstream classification and regression tasks. The methodology adopted can be extended beyond the scope of this project as it uses Auto-Encoders for unsupervised representation learning.

arXiv:2609.22333v1cs.CV

설명 가능한 AI(XAI) 기반 하이퍼스펙트럴 이미지 분류를 위한 차원 축소

Dimensionality reduction for AI based hyperspectral image classification based on XAI

본 연구는 인공지능(AI) 기반 차원 축소를 활용하여 목재 재활용 공정에서 소재 재활용이 제한적인 문제를 다룬다. 본 연구는 RGB 채널을 넘어 200개 이상의 분광 채널을 갖는 다중 채널 하이퍼스펙트럴 이미징(HSI)에 합성곱 신경망(CNN)을 적용하는 방법을 탐구한다. 이러한 맥락에서 차원 축소는 AI 시스템의 학습과 추론을 위한 특징 공간을 간소화하는 것을 의미한다. 설명 가능한 AI(XAI) 기법에 초점을 맞춘 본 논문은 더 폭넓은 연구 이니셔티브에 기여하며, 목재 재활용 공정의 지속가능성과 효율성을 향상시키는 솔루션 프레임워크를 제시한다.

arXiv:1612.05360

FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics

Electron microscopic connectomics is an ambitious research direction with the goal of studying comprehensive brain connectivity maps by using high-throughput, nano-scale microscopy. One of the main challenges in connectomics research is developing scalable image analysis algorithms that require minimal user intervention. Recently, deep learning has drawn much attention in computer vision because of its exceptional performance in image classification tasks. For this reason, its application to connectomic analyses holds great promise, as well. In this paper, we introduce a novel deep neural network architecture, FusionNet, for the automatic segmentation of neuronal structures in connectomics data. FusionNet leverages the latest advances in machine learning, such as semantic segmentation and residual neural networks, with the novel introduction of summation-based skip connections to allow a much deeper network architecture for a more accurate segmentation. We demonstrate the performance of the proposed method by comparing it with state-of-the-art electron microscopy (EM) segmentation methods from the ISBI EM segmentation challenge. We also show the segmentation results on two different tasks including cell membrane and cell body segmentation and a statistical analysis of cell morphology.

arXiv:1906.10400

Brain MR Image Segmentation in Small Dataset with Adversarial Defense and Task Reorganization

Medical image segmentation is challenging especially in dealing with small dataset of 3D MR images. Encoding the variation of brain anatomical struc-tures from individual subjects cannot be easily achieved, which is further chal-lenged by only a limited number of well labeled subjects for training. In this study, we aim to address the issue of brain MR image segmentation in small da-taset. First, concerning the limited number of training images, we adopt adver-sarial defense to augment the training data and therefore increase the robustness of the network. Second, inspired by the prior knowledge of neural anatomies, we reorganize the segmentation tasks of different regions into several groups in a hierarchical way. Third, the task reorganization extends to the semantic level, as we incorporate an additional object-level classification task to contribute high-order visual features toward the pixel-level segmentation task. In experiments we validate our method by segmenting gray matter, white matter, and several major regions on a challenge dataset. The proposed method with only seven subjects for training can achieve 84.46% of Dice score in the onsite test set.

arXiv:2001.03444공식 코드 · Papers with Code

Improving Image Autoencoder Embeddings with Perceptual Loss

Autoencoders are commonly trained using element-wise loss. However, element-wise loss disregards high-level structures in the image which can lead to embeddings that disregard them as well. A recent improvement to autoencoders that helps alleviate this problem is the use of perceptual loss. This work investigates perceptual loss from the perspective of encoder embeddings themselves. Autoencoders are trained to embed images from three different computer vision datasets using perceptual loss based on a pretrained model as well as pixel-wise loss. A host of different predictors are trained to perform object positioning and classification on the datasets given the embedded images as input. The two kinds of losses are evaluated by comparing how the predictors performed with embeddings from the differently trained autoencoders. The results show that, in the image domain, the embeddings generated by autoencoders trained with perceptual loss enable more accurate predictions than those trained with element-wise loss. Furthermore, the results show that, on the task of object positioning of a small-scale feature, perceptual loss can improve the results by a factor 10. The experimental setup is available online: https://github.com/guspih/Perceptual-Autoencoders

arXiv:2308.10984

Debiasing Counterfactuals In the Presence of Spurious Correlations

Deep learning models can perform well in complex medical imaging classification tasks, even when basing their conclusions on spurious correlations (i.e. confounders), should they be prevalent in the training dataset, rather than on the causal image markers of interest. This would thereby limit their ability to generalize across the population. Explainability based on counterfactual image generation can be used to expose the confounders but does not provide a strategy to mitigate the bias. In this work, we introduce the first end-to-end training framework that integrates both (i) popular debiasing classifiers (e.g. distributionally robust optimization (DRO)) to avoid latching onto the spurious correlations and (ii) counterfactual image generation to unveil generalizable imaging markers of relevance to the task. Additionally, we propose a novel metric, Spurious Correlation Latching Score (SCLS), to quantify the extent of the classifier reliance on the spurious correlation as exposed by the counterfactual images. Through comprehensive experiments on two public datasets (with the simulated and real visual artifacts), we demonstrate that the debiasing method: (i) learns generalizable markers across the population, and (ii) successfully ignores spurious correlations and focuses on the underlying disease pathology.

arXiv:2501.01392공식 코드 · Papers with Code

ProjectedEx: Enhancing Generation in Explainable AI for Prostate Cancer

Prostate cancer, a growing global health concern, necessitates precise diagnostic tools, with Magnetic Resonance Imaging (MRI) offering high-resolution soft tissue imaging that significantly enhances diagnostic accuracy. Recent advancements in explainable AI and representation learning have significantly improved prostate cancer diagnosis by enabling automated and precise lesion classification. However, existing explainable AI methods, particularly those based on frameworks like generative adversarial networks (GANs), are predominantly developed for natural image generation, and their application to medical imaging often leads to suboptimal performance due to the unique characteristics and complexity of medical image. To address these challenges, our paper introduces three key contributions. First, we propose ProjectedEx, a generative framework that provides interpretable, multi-attribute explanations, effectively linking medical image features to classifier decisions. Second, we enhance the encoder module by incorporating feature pyramids, which enables multiscale feedback to refine the latent space and improves the quality of generated explanations. Additionally, we conduct comprehensive experiments on both the generator and classifier, demonstrating the clinical relevance and effectiveness of ProjectedEx in enhancing interpretability and supporting the adoption of AI in medical settings. Code will be released at https://github.com/Richardqiyi/ProjectedEx