PyTorchKR Papers

“Image Classification”

총 18,351편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2205.13331공식 코드 · Papers with Code

TransBoost: Improving the Best ImageNet Performance using Deep Transduction

This paper deals with deep transductive learning, and proposes TransBoost as a procedure for fine-tuning any deep neural model to improve its performance on any (unlabeled) test set provided at training time. TransBoost is inspired by a large margin principle and is efficient and simple to use. Our method significantly improves the ImageNet classification performance on a wide range of architectures, such as ResNets, MobileNetV3-L, EfficientNetB0, ViT-S, and ConvNext-T, leading to state-of-the-art transductive performance. Additionally we show that TransBoost is effective on a wide variety of image classification datasets. The implementation of TransBoost is provided at: https://github.com/omerb01/TransBoost .

arXiv:2211.13352

Improving dermatology classifiers across populations using images generated by large diffusion models

Dermatological classification algorithms developed without sufficiently diverse training data may generalize poorly across populations. While intentional data collection and annotation offer the best means for improving representation, new computational approaches for generating training data may also aid in mitigating the effects of sampling bias. In this paper, we show that DALL$\cdot$E 2, a large-scale text-to-image diffusion model, can produce photorealistic images of skin disease across skin types. Using the Fitzpatrick 17k dataset as a benchmark, we demonstrate that augmenting training data with DALL$\cdot$E 2-generated synthetic images improves classification of skin disease overall and especially for underrepresented groups.

arXiv:2309.03237

Federated Learning Over Images: Vertical Decompositions and Pre-Trained Backbones Are Difficult to Beat

We carefully evaluate a number of algorithms for learning in a federated environment, and test their utility for a variety of image classification tasks. We consider many issues that have not been adequately considered before: whether learning over data sets that do not have diverse sets of images affects the results; whether to use a pre-trained feature extraction "backbone"; how to evaluate learner performance (we argue that classification accuracy is not enough), among others. Overall, across a wide variety of settings, we find that vertically decomposing a neural network seems to give the best results, and outperforms more standard reconciliation-used methods.

arXiv:2408.12275

Whole Slide Image Classification of Salivary Gland Tumours

This work shows promising results using multiple instance learning on salivary gland tumours in classifying cancers on whole slide images. Utilising CTransPath as a patch-level feature extractor and CLAM as a feature aggregator, an F1 score of over 0.88 and AUROC of 0.92 are obtained for detecting cancer in whole slide images.

arXiv:1611.04413

Automatic discovery of discriminative parts as a quadratic assignment problem

Part-based image classification consists in representing categories by small sets of discriminative parts upon which a representation of the images is built. This paper addresses the question of how to automatically learn such parts from a set of labeled training images. The training of parts is cast as a quadratic assignment problem in which optimal correspondences between image regions and parts are automatically learned. The paper analyses different assignment strategies and thoroughly evaluates them on two public datasets: Willow actions and MIT 67 scenes. State-of-the art results are obtained on these datasets.

arXiv:1809.00085

A Simplified Approach to Deep Learning for Image Segmentation

Leaping into the rapidly developing world of deep learning is an exciting and sometimes confusing adventure. All of the advice and tutorials available can be hard to organize and work through, especially when training specific models on specific datasets, different from those originally used to train the network. In this short guide, we aim to walk the reader through the techniques that we have used to successfully train two deep neural networks for pixel-wise classification, including some data management and augmentation approaches for working with image data that may be insufficiently annotated or relatively homogenous.

arXiv:2109.15092

Robust Multi-Domain Mitosis Detection

Domain variability is a common bottle neck in developing generalisable algorithms for various medical applications. Motivated by the observation that the domain variability of the medical images is to some extent compact, we propose to learn a target representative feature space through unpaired image to image translation (CycleGAN). We comprehensively evaluate the performanceand usefulness by utilising the transformation to mitosis detection with candidate proposal and classification. This work presents a simple yet effective multi-step mitotic figure detection algorithm developed as a baseline for the MIDOG challenge. On the preliminary test set, the algorithm scoresan F1 score of 0.52.

arXiv:1811.01287

Towards Sparse Hierarchical Graph Classifiers

Recent advances in representation learning on graphs, mainly leveraging graph convolutional networks, have brought a substantial improvement on many graph-based benchmark tasks. While novel approaches to learning node embeddings are highly suitable for node classification and link prediction, their application to graph classification (predicting a single label for the entire graph) remains mostly rudimentary, typically using a single global pooling step to aggregate node features or a hand-designed, fixed heuristic for hierarchical coarsening of the graph structure. An important step towards ameliorating this is differentiable graph coarsening---the ability to reduce the size of the graph in an adaptive, data-dependent manner within a graph neural network pipeline, analogous to image downsampling within CNNs. However, the previous prominent approach to pooling has quadratic memory requirements during training and is therefore not scalable to large graphs. Here we combine several recent advances in graph neural network design to demonstrate that competitive hierarchical graph classification results are possible without sacrificing sparsity. Our results are verified on several established graph classification benchmarks, and highlight an important direction for future research in graph-based neural networks.

arXiv:2008.12873공식 코드 · Papers with Code

Background Splitting: Finding Rare Classes in a Sea of Background

We focus on the real-world problem of training accurate deep models for image classification of a small number of rare categories. In these scenarios, almost all images belong to the background category in the dataset (>95% of the dataset is background). We demonstrate that both standard fine-tuning approaches and state-of-the-art approaches for training on imbalanced datasets do not produce accurate deep models in the presence of this extreme imbalance. Our key observation is that the extreme imbalance due to the background category can be drastically reduced by leveraging visual knowledge from an existing pre-trained model. Specifically, the background category is "split" into smaller and more coherent pseudo-categories during training using a pre-trained model. We incorporate background splitting into an image classification model by adding an auxiliary loss that learns to mimic the predictions of the existing, pre-trained image classification model. Note that this process is automatic and requires no additional manual labels. The auxiliary loss regularizes the feature representation of the shared network trunk by requiring it to discriminate between previously homogeneous background instances and reduces overfitting to the small number of rare category positives. We also show that BG splitting can be combined with other background imbalance methods to further improve performance. We evaluate our method on a modified version of the iNaturalist dataset where only a small subset of rare category labels are available during training (all other images are labeled as background). By jointly learning to recognize ImageNet categories and selected iNaturalist categories, our approach yields performance that is 42.3 mAP points higher than a fine-tuning baseline when 99.98% of the data is background, and 8.3 mAP points higher than SotA baselines when 98.30% of the data is background.

arXiv:2009.08891

AdderSR: Towards Energy Efficient Image Super-Resolution

This paper studies the single image super-resolution problem using adder neural networks (AdderNet). Compared with convolutional neural networks, AdderNet utilizing additions to calculate the output features thus avoid massive energy consumptions of conventional multiplications. However, it is very hard to directly inherit the existing success of AdderNet on large-scale image classification to the image super-resolution task due to the different calculation paradigm. Specifically, the adder operation cannot easily learn the identity mapping, which is essential for image processing tasks. In addition, the functionality of high-pass filters cannot be ensured by AdderNet. To this end, we thoroughly analyze the relationship between an adder operation and the identity mapping and insert shortcuts to enhance the performance of SR models using adder networks. Then, we develop a learnable power activation for adjusting the feature distribution and refining details. Experiments conducted on several benchmark models and datasets demonstrate that, our image super-resolution models using AdderNet can achieve comparable performance and visual quality to that of their CNN baselines with an about 2$\times$ reduction on the energy consumption.

arXiv:2405.10004공식 코드 · Papers with Code

ROCOv2: Radiology Objects in COntext Version 2, an Updated Multimodal Image Dataset

Automated medical image analysis systems often require large amounts of training data with high quality labels, which are difficult and time consuming to generate. This paper introduces Radiology Object in COntext version 2 (ROCOv2), a multimodal dataset consisting of radiological images and associated medical concepts and captions extracted from the PMC Open Access subset. It is an updated version of the ROCO dataset published in 2018, and adds 35,705 new images added to PMC since 2018. It further provides manually curated concepts for imaging modalities with additional anatomical and directional concepts for X-rays. The dataset consists of 79,789 images and has been used, with minor modifications, in the concept detection and caption prediction tasks of ImageCLEFmedical Caption 2023. The dataset is suitable for training image annotation models based on image-caption pairs, or for multi-label image classification using Unified Medical Language System (UMLS) concepts provided with each image. In addition, it can serve for pre-training of medical domain models, and evaluation of deep learning models for multi-task learning.

arXiv:2601.15891v4cs.CV

RadJEPA: 결합 임베딩 예측 아키텍처(Joint Embedding Predictive Architecture)를 활용한 흉부 X선 영상용 영상의학 인코더

RadJEPA: Radiology Encoder for Chest X-Rays via Joint Embedding Predictive Architecture

비전-언어 사전학습은 의료 영상 표현 학습의 발전을 이끌어 왔지만, 짝지어진 이미지-텍스트 데이터에 의존하며 임상 서술에 내재한 보고 편향(reporting bias)을 물려받을 수 있습니다. 본 연구는 언어를 사용하지 않는 예측적 사전학습으로도 영상의학 판독문 생성에 효과적으로 전이되는 이미지 인코더를 만들 수 있는지 살펴봅니다. RadJEPA는 I-JEPA를 흉부 X선에 맞게 적용한 모델로, 레이블이 없는 약 84만 장의 방사선 영상에 대해 잠재 공간에서 컨텍스트로부터 타깃을 예측하는 방식으로 사전학습되었습니다. 우리의 주된 기여는 이 언어 비의존 인코더를 판독문 생성에 적용해 수행한 폭넓은 실증 평가입니다. 구체적으로, 고정(frozen)된 이미지 인코더를 학습 가능한 2층 프로젝터 및 언어 디코더와 결합하고, 이를 기존의 네 가지 비전-언어 백본에도 대체하여 넣어 평가했습니다. MIMIC-CXR와 IU-Xray 전반에서 RadJEPA는 어휘(lexical), 엔티티-관계(entity-relation), 임상 레이블 지표에서 평가 대상인 이미지 단독 및 이미지-텍스트 베이스라인과 동등하거나 그 이상의 성능을 보였습니다. MIMIC만 사용한 통제된 비교는 예측 목적 함수가 도메인 특화 사전학습을 넘어서는 기여를 한다는 근거를 제공하며, 더 넓은 범위의 비교에는 사전학습 데이터, 모델 용량, 입력 해상도의 차이도 함께 반영되어 있습니다. 보완적인 분류 및 분할(segmentation) 실험을 통해 판독문 생성 이외의 과제로의 전이 성능도 평가했습니다.

arXiv:2012.06917

Assessing The Importance Of Colours For CNNs In Object Recognition

Humans rely heavily on shapes as a primary cue for object recognition. As secondary cues, colours and textures are also beneficial in this regard. Convolutional neural networks (CNNs), an imitation of biological neural networks, have been shown to exhibit conflicting properties. Some studies indicate that CNNs are biased towards textures whereas, another set of studies suggests shape bias for a classification task. However, they do not discuss the role of colours, implying its possible humble role in the task of object recognition. In this paper, we empirically investigate the importance of colours in object recognition for CNNs. We are able to demonstrate that CNNs often rely heavily on colour information while making a prediction. Our results show that the degree of dependency on colours tend to vary from one dataset to another. Moreover, networks tend to rely more on colours if trained from scratch. Pre-training can allow the model to be less colour dependent. To facilitate these findings, we follow the framework often deployed in understanding role of colours in object recognition for humans. We evaluate a model trained with congruent images (images in original colours eg. red strawberries) on congruent, greyscale, and incongruent images (images in unnatural colours eg. blue strawberries). We measure and analyse network's predictive performance (top-1 accuracy) under these different stylisations. We utilise standard datasets of supervised image classification and fine-grained image classification in our experiments.

arXiv:2308.04956

Improved Cryo-EM Pose Estimation and 3D Classification through Latent-Space Disentanglement

Due to the extremely low signal-to-noise ratio (SNR) and unknown poses (projection angles and image shifts) in cryo-electron microscopy (cryo-EM) experiments, reconstructing 3D volumes from 2D images is very challenging. In addition to these challenges, heterogeneous cryo-EM reconstruction requires conformational classification. In popular cryo-EM reconstruction algorithms, poses and conformation classification labels must be predicted for every input cryo-EM image, which can be computationally costly for large datasets. An emerging class of methods adopted the amortized inference approach. In these methods, only a subset of the input dataset is needed to train neural networks for the estimation of poses and conformations. Once trained, these neural networks can make pose/conformation predictions and 3D reconstructions at low cost for the entire dataset during inference. Unfortunately, when facing heterogeneous reconstruction tasks, it is hard for current amortized-inference-based methods to effectively estimate the conformational distribution and poses from entangled latent variables. Here, we propose a self-supervised variational autoencoder architecture called "HetACUMN" based on amortized inference. We employed an auxiliary conditional pose prediction task by inverting the order of encoder-decoder to explicitly enforce the disentanglement of conformation and pose predictions. Results on simulated datasets show that HetACUMN generated more accurate conformational classifications than other amortized or non-amortized methods. Furthermore, we show that HetACUMN is capable of performing heterogeneous 3D reconstructions of a real experimental dataset.

arXiv:2308.08192

Automatic Vision-Based Parking Slot Detection and Occupancy Classification

Parking guidance information (PGI) systems are used to provide information to drivers about the nearest parking lots and the number of vacant parking slots. Recently, vision-based solutions started to appear as a cost-effective alternative to standard PGI systems based on hardware sensors mounted on each parking slot. Vision-based systems provide information about parking occupancy based on images taken by a camera that is recording a parking lot. However, such systems are challenging to develop due to various possible viewpoints, weather conditions, and object occlusions. Most notably, they require manual labeling of parking slot locations in the input image which is sensitive to camera angle change, replacement, or maintenance. In this paper, the algorithm that performs Automatic Parking Slot Detection and Occupancy Classification (APSD-OC) solely on input images is proposed. Automatic parking slot detection is based on vehicle detections in a series of parking lot images upon which clustering is applied in bird's eye view to detect parking slots. Once the parking slots positions are determined in the input image, each detected parking slot is classified as occupied or vacant using a specifically trained ResNet34 deep classifier. The proposed approach is extensively evaluated on well-known publicly available datasets (PKLot and CNRPark+EXT), showing high efficiency in parking slot detection and robustness to the presence of illegal parking or passing vehicles. Trained classifier achieves high accuracy in parking slot occupancy classification.

arXiv:2111.06754공식 코드 · Papers with Code

Monte Carlo dropout increases model repeatability

The integration of artificial intelligence into clinical workflows requires reliable and robust models. Among the main features of robustness is repeatability. Much attention is given to classification performance without assessing the model repeatability, leading to the development of models that turn out to be unusable in practice. In this work, we evaluate the repeatability of four model types on images from the same patient that were acquired during the same visit. We study the performance of binary, multi-class, ordinal, and regression models on three medical image analysis tasks: cervical cancer screening, breast density estimation, and retinopathy of prematurity classification. Moreover, we assess the impact of sampling Monte Carlo dropout predictions at test time on classification performance and repeatability. Leveraging Monte Carlo predictions significantly increased repeatability for all tasks on the binary, multi-class, and ordinal models leading to an average reduction of the 95% limits of agreement by 17% points.

arXiv:2203.12147

3D-EDM: Early Detection Model for 3D-Printer Faults

With the advent of 3D printers in different price ranges and sizes, they are no longer just for professionals. However, it is still challenging to use a 3D printer perfectly. Especially, in the case of the Fused Deposition Method, it is very difficult to perform with accurate calibration. Previous studies have suggested that these problems can be detected using sensor data and image data with machine learning methods. However, there are difficulties to apply the proposed method due to extra installation of additional sensors. Considering actual use in the future, we focus on generating the lightweight early detection model with easily collectable data. Proposed early detection model through Convolutional Neural Network shows significant fault classification accuracy with 96.72% for the binary classification task, and 93.38% for multi-classification task respectively. By this research, we hope that general users of 3D printers can use the printer accurately.

arXiv:2212.04951

EEG-NeXt: A Modernized ConvNet for The Classification of Cognitive Activity from EEG

One of the main challenges in electroencephalogram (EEG) based brain-computer interface (BCI) systems is learning the subject/session invariant features to classify cognitive activities within an end-to-end discriminative setting. We propose a novel end-to-end machine learning pipeline, EEG-NeXt, which facilitates transfer learning by: i) aligning the EEG trials from different subjects in the Euclidean-space, ii) tailoring the techniques of deep learning for the scalograms of EEG signals to capture better frequency localization for low-frequency, longer-duration events, and iii) utilizing pretrained ConvNeXt (a modernized ResNet architecture which supersedes state-of-the-art (SOTA) image classification models) as the backbone network via adaptive finetuning. On publicly available datasets (Physionet Sleep Cassette and BNCI2014001) we benchmark our method against SOTA via cross-subject validation and demonstrate improved accuracy in cognitive activity classification along with better generalizability across cohorts.

arXiv:2506.06342

Uncertainty-Aware Multi-view Arrhythmia Classification from ECG

We propose a deep neural architecture that performs uncertainty-aware multi-view classification of arrhythmia from ECG. Our method learns two different views (1D and 2D) of single-lead ECG to capture different types of information. We use a fusion technique to reduce the conflict between the different views caused by noise and artifacts in ECG data, thus incorporating uncertainty to obtain stronger final predictions. Our framework contains the following three modules (1) a time-series module to learn the morphological features from ECG; (2) an image-space learning module to learn the spatiotemporal features; and (3) the uncertainty-aware fusion module to fuse the information from the two different views. Experimental results on two real-world datasets demonstrate that our framework not only improves the performance on arrhythmia classification compared to the state-of-the-art but also shows better robustness to noise and artifacts present in ECG.

arXiv:2205.12268공식 코드 · Papers with Code

Wavelet Feature Maps Compression for Image-to-Image CNNs

Convolutional Neural Networks (CNNs) are known for requiring extensive computational resources, and quantization is among the best and most common methods for compressing them. While aggressive quantization (i.e., less than 4-bits) performs well for classification, it may cause severe performance degradation in image-to-image tasks such as semantic segmentation and depth estimation. In this paper, we propose Wavelet Compressed Convolution (WCC) -- a novel approach for high-resolution activation maps compression integrated with point-wise convolutions, which are the main computational cost of modern architectures. To this end, we use an efficient and hardware-friendly Haar-wavelet transform, known for its effectiveness in image compression, and define the convolution on the compressed activation map. We experiment with various tasks that benefit from high-resolution input. By combining WCC with light quantization, we achieve compression rates equivalent to 1-4bit activation quantization with relatively small and much more graceful degradation in performance. Our code is available at https://github.com/BGUCompSci/WaveletCompressedConvolution.