PyTorchKR Papers

“Image Classification”

총 18,403편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2112.03052공식 코드 · Papers with Code

Scaling Up Influence Functions

We address efficient calculation of influence functions for tracking predictions back to the training data. We propose and analyze a new approach to speeding up the inverse Hessian calculation based on Arnoldi iteration. With this improvement, we achieve, to the best of our knowledge, the first successful implementation of influence functions that scales to full-size (language and vision) Transformer models with several hundreds of millions of parameters. We evaluate our approach on image classification and sequence-to-sequence tasks with tens to a hundred of millions of training examples. Our code will be available at https://github.com/google-research/jax-influence.

arXiv:2308.01621공식 코드 · Papers with Code

A Novel Convolutional Neural Network Architecture with a Continuous Symmetry

This paper introduces a new Convolutional Neural Network (ConvNet) architecture inspired by a class of partial differential equations (PDEs) called quasi-linear hyperbolic systems. With comparable performance on the image classification task, it allows for the modification of the weights via a continuous group of symmetry. This is a significant shift from traditional models where the architecture and weights are essentially fixed. We wish to promote the (internal) symmetry as a new desirable property for a neural network, and to draw attention to the PDE perspective in analyzing and interpreting ConvNets in the broader Deep Learning community.

arXiv:2308.04018

Improving Performance of Semi-Supervised Learning by Adversarial Attacks

Semi-supervised learning (SSL) algorithm is a setup built upon a realistic assumption that access to a large amount of labeled data is tough. In this study, we present a generalized framework, named SCAR, standing for Selecting Clean samples with Adversarial Robustness, for improving the performance of recent SSL algorithms. By adversarially attacking pre-trained models with semi-supervision, our framework shows substantial advances in classifying images. We introduce how adversarial attacks successfully select high-confident unlabeled data to be labeled with current predictions. On CIFAR10, three recent SSL algorithms with SCAR result in significantly improved image classification.

arXiv:2309.17144

Prototype Generation: Robust Feature Visualisation for Data Independent Interpretability

We introduce Prototype Generation, a stricter and more robust form of feature visualisation for model-agnostic, data-independent interpretability of image classification models. We demonstrate its ability to generate inputs that result in natural activation paths, countering previous claims that feature visualisation algorithms are untrustworthy due to the unnatural internal activations. We substantiate these claims by quantitatively measuring similarity between the internal activations of our generated prototypes and natural images. We also demonstrate how the interpretation of generated prototypes yields important insights, highlighting spurious correlations and biases learned by models which quantitative methods over test-sets cannot identify.

arXiv:2403.17014

Contrastive Learning for Regression on Hyperspectral Data

Contrastive learning has demonstrated great effectiveness in representation learning especially for image classification tasks. However, there is still a shortage in the studies targeting regression tasks, and more specifically applications on hyperspectral data. In this paper, we propose a contrastive learning framework for the regression tasks for hyperspectral data. To this end, we provide a collection of transformations relevant for augmenting hyperspectral data, and investigate contrastive learning for regression. Experiments on synthetic and real hyperspectral datasets show that the proposed framework and transformations significantly improve the performance of regression models, achieving better scores than other state-of-the-art transformations.

arXiv:2406.10322공식 코드 · Papers with Code

LieRE: Generalizing Rotary Position Encodings

While Rotary Position Embeddings (RoPE) for large language models have become widely adopted, their application for other modalities has been slower. Here, we introduce Lie group Relative position Encodings (LieRE) that goes beyond RoPE in supporting n-dimensional inputs. We evaluate the performance of LieRE on 2D and 3D image classification tasks and observe that LieRE leads to marked relative improvements in performance (up to 9.7% for 2D and up to 25.5% for 3D), training efficiency (3.5x reduction), data efficiency (30%) compared to the baselines of DeiT III, RoPE-Mixed and Vision-Llama. https://github.com/Stanford-AIMI/LieRE

arXiv:2103.09382공식 코드 · Papers with Code

SPICE: Semantic Pseudo-labeling for Image Clustering

The similarity among samples and the discrepancy between clusters are two crucial aspects of image clustering. However, current deep clustering methods suffer from the inaccurate estimation of either feature similarity or semantic discrepancy. In this paper, we present a Semantic Pseudo-labeling-based Image ClustEring (SPICE) framework, which divides the clustering network into a feature model for measuring the instance-level similarity and a clustering head for identifying the cluster-level discrepancy. We design two semantics-aware pseudo-labeling algorithms, prototype pseudo-labeling, and reliable pseudo-labeling, which enable accurate and reliable self-supervision over clustering. Without using any ground-truth label, we optimize the clustering network in three stages: 1) train the feature model through contrastive learning to measure the instance similarity, 2) train the clustering head with the prototype pseudo-labeling algorithm to identify cluster semantics, and 3) jointly train the feature model and clustering head with the reliable pseudo-labeling algorithm to improve the clustering performance. Extensive experimental results demonstrate that SPICE achieves significant improvements (~10%) over existing methods and establishes the new state-of-the-art clustering results on six image benchmark datasets in terms of three popular metrics. Importantly, SPICE significantly reduces the gap between unsupervised and fully-supervised classification; e.g., there is only a 2% (91.8% vs 93.8%) accuracy difference on CIFAR-10. Our code has been made publically available at https://github.com/niuchuangnn/SPICE.

arXiv:2203.11876공식 코드 · Papers with Code

Open-Vocabulary DETR with Conditional Matching

Open-vocabulary object detection, which is concerned with the problem of detecting novel objects guided by natural language, has gained increasing attention from the community. Ideally, we would like to extend an open-vocabulary detector such that it can produce bounding box predictions based on user inputs in form of either natural language or exemplar image. This offers great flexibility and user experience for human-computer interaction. To this end, we propose a novel open-vocabulary detector based on DETR -- hence the name OV-DETR -- which, once trained, can detect any object given its class name or an exemplar image. The biggest challenge of turning DETR into an open-vocabulary detector is that it is impossible to calculate the classification cost matrix of novel classes without access to their labeled images. To overcome this challenge, we formulate the learning objective as a binary matching one between input queries (class name or exemplar image) and the corresponding objects, which learns useful correspondence to generalize to unseen queries during testing. For training, we choose to condition the Transformer decoder on the input embeddings obtained from a pre-trained vision-language model like CLIP, in order to enable matching for both text and image queries. With extensive experiments on LVIS and COCO datasets, we demonstrate that our OV-DETR -- the first end-to-end Transformer-based open-vocabulary detector -- achieves non-trivial improvements over current state of the arts.

arXiv:2611.12345v1cs.CV

TMT: 텍스트 유도 모달리티 지식 전이를 통한 CLIP의 적외선 영상 적응

TMT: Adapting CLIP to Infrared Imagery via Text-Derived Modality Knowledge Transfer

CLIP과 같은 비전-언어 모델은 다양한 컴퓨터 비전 과제에서 강력한 성능을 달성하지만, 대규모 사전 학습이 가시광선 데이터에 의해 지배되기 때문에 적외선(IR) 영상에 대한 이미지-텍스트 정렬은 신뢰성이 낮다. 적외선-텍스트 레이블링의 높은 비용 때문에, 본 연구는 짝지어진 적외선-가시광선 이미지만으로 CLIP을 IR에 적응시키는 방법을 탐구하며, 이는 장면 내용과 CLIP의 이미지-텍스트 정렬을 보존하면서 모달리티 특유의 지식을 고려해야 한다. 이를 위해 텍스트로 정의된 적외선-가시광선 방향과 짝지어진 IR-가시광선 이미지의 지도를 통해 CLIP의 이미지 인코더를 적응시키는 TMT(Text-Derived Modality Knowledge Transfer)를 제안한다. 먼저, 모달리티 차이가 대응하는 텍스트 임베딩으로 기술될 수 있음을 발견하였고, 따라서 텍스트 임베딩 차이의 방향을 이용해 적외선 고유 정보를 지우지 않으면서 가시광선과 적외선 모달리티 간 지식 전이를 유도한다. 적외선 영상의 의미와 세부 정보에 대한 표현을 강화하기 위해, CLIP 가시광선 이미지 인코더의 의미 정렬과 확산 모델의 노이즈 예측 피드백을 결합한 생성-지각 공동 지도(Generative-Perceptual Co-Supervision)를 도입한다. 출처가 서로 분리된 네 개의 IR 분류 벤치마크에서 TMT는 비교 방법 중 가장 높은 평균 제로샷 정확도(48.92%)를 달성한다. 또한 적응 과정에서 적외선-텍스트 지도 없이도 비교 방법 중 최고의 IR-텍스트 검색 결과를 달성하며, CART와 SemanticRT 모두에서 CLIP 계열 방법 중 가장 높은 개방형 어휘 분할 mIoU를 달성한다.

arXiv:1801.00192

A Unified Method for First and Third Person Action Recognition

In this paper, a new video classification methodology is proposed which can be applied in both first and third person videos. The main idea behind the proposed strategy is to capture complementary information of appearance and motion efficiently by performing two independent streams on the videos. The first stream is aimed to capture long-term motions from shorter ones by keeping track of how elements in optical flow images have changed over time. Optical flow images are described by pre-trained networks that have been trained on large scale image datasets. A set of multi-channel time series are obtained by aligning descriptions beside each other. For extracting motion features from these time series, PoT representation method plus a novel pooling operator is followed due to several advantages. The second stream is accomplished to extract appearance features which are vital in the case of video classification. The proposed method has been evaluated on both first and third-person datasets and results present that the proposed methodology reaches the state of the art successfully.

arXiv:1504.06066

Object Detection Networks on Convolutional Feature Maps

Most object detectors contain two important components: a feature extractor and an object classifier. The feature extractor has rapidly evolved with significant research efforts leading to better deep convolutional architectures. The object classifier, however, has not received much attention and many recent systems (like SPPnet and Fast/Faster R-CNN) use simple multi-layer perceptrons. This paper demonstrates that carefully designing deep networks for object classification is just as important. We experiment with region-wise classifier networks that use shared, region-independent convolutional features. We call them "Networks on Convolutional feature maps" (NoCs). We discover that aside from deep feature maps, a deep and convolutional per-region classifier is of particular importance for object detection, whereas latest superior image classification models (such as ResNets and GoogLeNets) do not directly lead to good detection accuracy without using such a per-region classifier. We show by experiments that despite the effective ResNets and Faster R-CNN systems, the design of NoCs is an essential element for the 1st-place winning entries in ImageNet and MS COCO challenges 2015.

arXiv:1403.1362

Illumination,Expression and Occlusion Invariant Pose-Adaptive Face Recognition System for Real-Time Applications

Face recognition in real-time scenarios is mainly affected by illumination, expression and pose variations and also by occlusion. This paper presents the framework for pose adaptive component-based face recognition system. The framework proposed deals with all the above mentioned issues. The steps involved in the presented framework are (i) facial landmark localisation, (ii) facial component extraction, (iii) pre-processing of facial image (iv) facial pose estimation (v) feature extraction using Local Binary Pattern Histograms of each component followed by (vi) fusion of pose adaptive classification of components. By employing pose adaptive classification, the recognition process is carried out on some part of database, based on estimated pose, instead of applying the recognition process on the whole database. Pre-processing techniques employed to overcome the problems due to illumination variation are also discussed in this paper. Component-based techniques provide better recognition rates when face images are occluded compared to the holistic methods. Our method is simple, feasible and provides better results when compared to other holistic methods.

arXiv:1810.08280

Exploring Adversarial Examples in Malware Detection

The convolutional neural network (CNN) architecture is increasingly being applied to new domains, such as malware detection, where it is able to learn malicious behavior from raw bytes extracted from executables. These architectures reach impressive performance with no feature engineering effort involved, but their robustness against active attackers is yet to be understood. Such malware detectors could face a new attack vector in the form of adversarial interference with the classification model. Existing evasion attacks intended to cause misclassification on test-time instances, which have been extensively studied for image classifiers, are not applicable because of the input semantics that prevents arbitrary changes to the binaries. This paper explores the area of adversarial examples for malware detection. By training an existing model on a production-scale dataset, we show that some previous attacks are less effective than initially reported, while simultaneously highlighting architectural weaknesses that facilitate new attack strategies for malware classification. Finally, we explore how generalizable different attack strategies are, the trade-offs when aiming to increase their effectiveness, and the transferability of single-step attacks.

arXiv:1909.09602

Metric-Based Few-Shot Learning for Video Action Recognition

In the few-shot scenario, a learner must effectively generalize to unseen classes given a small support set of labeled examples. While a relatively large amount of research has gone into few-shot learning for image classification, little work has been done on few-shot video classification. In this work, we address the task of few-shot video action recognition with a set of two-stream models. We evaluate the performance of a set of convolutional and recurrent neural network video encoder architectures used in conjunction with three popular metric-based few-shot algorithms. We train and evaluate using a few-shot split of the Kinetics 600 dataset. Our experiments confirm the importance of the two-stream setup, and find prototypical networks and pooled long short-term memory network embeddings to give the best performance as few-shot method and video encoder, respectively. For a 5-shot 5-way task, this setup obtains 84.2% accuracy on the test set and 59.4% on a special "challenge" test set, composed of highly confusable classes.

arXiv:1909.10340

AHA! an 'Artificial Hippocampal Algorithm' for Episodic Machine Learning

The majority of ML research concerns slow, statistical learning of i.i.d. samples from large, labelled datasets. Animals do not learn this way. An enviable characteristic of animal learning is `episodic' learning - the ability to memorise a specific experience as a composition of existing concepts, after just one experience, without provided labels. The new knowledge can then be used to distinguish between similar experiences, to generalise between classes, and to selectively consolidate to long-term memory. The Hippocampus is known to be vital to these abilities. AHA is a biologically-plausible computational model of the Hippocampus. Unlike most machine learning models, AHA is trained without external labels and uses only local credit assignment. We demonstrate AHA in a superset of the Omniglot one-shot classification benchmark. The extended benchmark covers a wider range of known hippocampal functions by testing pattern separation, completion, and recall of original input. These functions are all performed within a single configuration of the computational model. Despite these constraints, image classification results are comparable to conventional deep convolutional ANNs.

arXiv:2001.04092

Semi-supervised learning method based on predefined evenly-distributed class centroids

Compared to supervised learning, semi-supervised learning reduces the dependence of deep learning on a large number of labeled samples. In this work, we use a small number of labeled samples and perform data augmentation on unlabeled samples to achieve image classification. Our method constrains all samples to the predefined evenly-distributed class centroids (PEDCC) by the corresponding loss function. Specifically, the PEDCC-Loss for labeled samples, and the maximum mean discrepancy loss for unlabeled samples are used to make the feature distribution closer to the distribution of PEDCC. Our method ensures that the inter-class distance is large and the intra-class distance is small enough to make the classification boundaries between different classes clearer. Meanwhile, for unlabeled samples, we also use KL divergence to constrain the consistency of the network predictions between unlabeled and augmented samples. Our semi-supervised learning method achieves the state-of-the-art results, with 4000 labeled samples on CIFAR10 and 1000 labeled samples on SVHN, and the accuracy is 95.10% and 97.58% respectively.

arXiv:2307.12577공식 코드 · Papers with Code

PRIOR: Prototype Representation Joint Learning from Medical Images and Reports

Contrastive learning based vision-language joint pre-training has emerged as a successful representation learning strategy. In this paper, we present a prototype representation learning framework incorporating both global and local alignment between medical images and reports. In contrast to standard global multi-modality alignment methods, we employ a local alignment module for fine-grained representation. Furthermore, a cross-modality conditional reconstruction module is designed to interchange information across modalities in the training phase by reconstructing masked images and reports. For reconstructing long reports, a sentence-wise prototype memory bank is constructed, enabling the network to focus on low-level localized visual and high-level clinical linguistic features. Additionally, a non-auto-regressive generation paradigm is proposed for reconstructing non-sequential reports. Experimental results on five downstream tasks, including supervised classification, zero-shot classification, image-to-text retrieval, semantic segmentation, and object detection, show the proposed method outperforms other state-of-the-art methods across multiple datasets and under different dataset size settings. The code is available at https://github.com/QtacierP/PRIOR.

arXiv:2404.19228

Weighted Point Cloud Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric

In typical multimodal contrastive learning, such as CLIP, encoders produce one point in the latent representation space for each input. However, one-point representation has difficulty in capturing the relationship and the similarity structure of a huge amount of instances in the real world. For richer classes of the similarity, we propose the use of weighted point clouds, namely, sets of pairs of weight and vector, as representations of instances. In this work, we theoretically show the benefit of our proposed method through a new understanding of the contrastive loss of CLIP, which we call symmetric InfoNCE. We clarify that the optimal similarity that minimizes symmetric InfoNCE is the pointwise mutual information, and show an upper bound of excess risk on downstream classification tasks of representations that achieve the optimal similarity. In addition, we show that our proposed similarity based on weighted point clouds consistently achieves the optimal similarity. To verify the effectiveness of our proposed method, we demonstrate pretraining of text-image representation models and classification tasks on common benchmarks.

arXiv:2408.06229공식 코드 · Papers with Code

A Comprehensive Case Study on the Performance of Machine Learning Methods on the Classification of Solar Panel Electroluminescence Images

Photovoltaics (PV) are widely used to harvest solar energy, an important form of renewable energy. Photovoltaic arrays consist of multiple solar panels constructed from solar cells. Solar cells in the field are vulnerable to various defects, and electroluminescence (EL) imaging provides effective and non-destructive diagnostics to detect those defects. We use multiple traditional machine learning and modern deep learning models to classify EL solar cell images into different functional/defective categories. Because of the asymmetry in the number of functional vs. defective cells, an imbalanced label problem arises in the EL image data. The current literature lacks insights on which methods and metrics to use for model training and prediction. In this paper, we comprehensively compare different machine learning and deep learning methods under different performance metrics on the classification of solar cell EL images from monocrystalline and polycrystalline modules. We provide a comprehensive discussion on different metrics. Our results provide insights and guidelines for practitioners in selecting prediction methods and performance metrics.

arXiv:2006.00730공식 코드 · Papers with Code

Automatic classification between COVID-19 pneumonia, non-COVID-19 pneumonia, and the healthy on chest X-ray image: combination of data augmentation methods

Purpose: This study aimed to develop and validate computer-aided diagnosis (CXDx) system for classification between COVID-19 pneumonia, non-COVID-19 pneumonia, and the healthy on chest X-ray (CXR) images. Materials and Methods: From two public datasets, 1248 CXR images were obtained, which included 215, 533, and 500 CXR images of COVID-19 pneumonia patients, non-COVID-19 pneumonia patients, and the healthy samples. The proposed CADx system utilized VGG16 as a pre-trained model and combination of conventional method and mixup as data augmentation methods. Other types of pre-trained models were compared with the VGG16-based model. Single type or no data augmentation methods were also evaluated. Splitting of training/validation/test sets was used when building and evaluating the CADx system. Three-category accuracy was evaluated for test set with 125 CXR images. Results: The three-category accuracy of the CAD system was 83.6% between COVID-19 pneumonia, non-COVID-19 pneumonia, and the healthy. Sensitivity for COVID-19 pneumonia was more than 90%. The combination of conventional method and mixup was more useful than single type or no data augmentation method. Conclusion: This study was able to create an accurate CADx system for the 3-category classification. Source code of our CADx system is available as open source for COVID-19 research.