Papers Linear evaluation
“Linear evaluation” 태그가 달린 논문 128편 · 필터 해제
Contrastive Self-Supervised Learning As Neural Manifold Packing
Contrastive self-supervised learning based on point-wise comparisons has been widely studied for vision tasks. In the visual cortex of the brain, neuronal responses to distinct stimulus classes are organized into geometr…
Contrastive LearningLinear evaluationRepresentation LearningSelf-Supervised LearningSSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes
Self-supervised pre-trained audio networks have seen widespread adoption in real-world systems, particularly in multi-modal large language models. These networks are often employed in a frozen state, under the assumption…
Linear evaluationSelf-Supervised LearningAdversarial Robustness of Discriminative Self-Supervised Learning in Vision
Self-supervised learning (SSL) has advanced significantly in visual representation learning, yet comprehensive evaluations of its adversarial robustness remain limited. In this study, we evaluate the adversarial robustne…
Adversarial RobustnessLinear evaluationRepresentation LearningSelf-Supervised Learning+1Medical Semantic Segmentation with Diffusion Pretrain
Recent advances in deep learning have shown that learning robust feature representations is critical for the success of many computer vision tasks, including medical image segmentation. In particular, both transformer an…
Image SegmentationLinear evaluationMedical Image SegmentationOrgan Segmentation+2Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learning
Contrastive learning underpins most current self-supervised time series representation methods. The strategy for constructing positive and negative sample pairs significantly affects the final representation quality. How…
Contrastive LearningLinear evaluationRepresentation LearningTime SeriesSelf-Supervised Radiograph Anatomical Region Classification -- How Clean Is Your Real-World Data?
Modern deep learning-based clinical imaging workflows rely on accurate labels of the examined anatomical region. Knowing the anatomical region is required to select applicable downstream models and to effectively generat…
Linear evaluationCLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance
Beyond the success of Contrastive Language-Image Pre-training (CLIP), recent trends mark a shift toward exploring the applicability of lightweight vision-language models for resource-constrained scenarios. These models o…
Contrastive Learningcross-modal alignmentCross-Modal RetrievalLinear evaluation+6Self-supervised learning for radio-astronomy source classification: a benchmark
The upcoming Square Kilometer Array (SKA) telescope marks a significant step forward in radio astronomy, presenting new opportunities and challenges for data analysis. Traditional visual models pretrained on optical phot…
AstronomyLinear evaluationRadio InterferometrySelf-Supervised LearningSynCo: Synthetic Hard Negatives in Contrastive Learning for Better Unsupervised Visual Representations
Contrastive learning has become a dominant approach in self-supervised visual representation learning. Hard negatives - samples closely resembling the anchor - are key to enhancing learned representations' discriminative…
Contrastive LearningImage ClassificationImage SegmentationInstance Segmentation+8Contrastive Learning with Synthetic Positives
Contrastive learning with the nearest neighbor has proved to be one of the most efficient self-supervised learning (SSL) techniques by utilizing the similarity of multiple instances within the same class. However, its ef…
Contrastive LearningLinear evaluationSelf-Supervised LearningTransfer LearningWeakly Contrastive Learning via Batch Instance Discrimination and Feature Clustering for Small Sample SAR ATR
In recent years, impressive performance of deep learning technology has been recognized in Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR). Since a large amount of annotated data is required in this tec…
Contrastive LearningLinear evaluationMulti-modal Masked Siamese Network Improves Chest X-Ray Representation Learning
Self-supervised learning methods for medical images primarily rely on the imaging modality during pretraining. While such approaches deliver promising results, they do not leverage associated patient or scan information …
Linear evaluationRepresentation LearningSelf-Supervised LearningSemantic Compositions Enhance Vision-Language Contrastive Learning
In the field of vision-language contrastive learning, models such as CLIP capitalize on matched image-caption pairs as positive examples and leverage within-batch non-matching pairs as negatives. This approach has led to…
ClassificationContrastive LearningCross-Modal Retrievalimage-classification+6Semantic Graph Consistency: Going Beyond Patches for Regularizing Self-Supervised Vision Transformers
Self-supervised learning (SSL) with vision transformers (ViTs) has proven effective for representation learning as demonstrated by the impressive performance on various downstream tasks. Despite these successes, existing…
Linear evaluationRepresentation LearningSelf-Supervised LearningM2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation
Contrastive language-audio pre-training (CLAP) enables zero-shot (ZS) inference of audio and exhibits promising performance in several classification tasks. However, conventional audio representations are still crucial f…
Audio ClassificationLinear evaluationSelf-Supervised LearningTransfer LearningLearning Generalized Medical Image Representations through Image-Graph Contrastive Pretraining
Medical image interpretation using deep learning has shown promise but often requires extensive expert-annotated datasets. To reduce this annotation burden, we develop an Image-Graph Contrastive Learning framework that p…
Contrastive LearningDiagnosticKnowledge GraphsLinear evaluationMasked Modeling Duo: Towards a Universal Audio Pre-training Framework
Self-supervised learning (SSL) using masked prediction has made great strides in general-purpose audio representation. This study proposes Masked Modeling Duo (M2D), an improved masked prediction SSL, which learns by pre…
Audio ClassificationDenoisingEnvironment Sound Classification+3MVEB: Self-Supervised Learning with Multi-View Entropy Bottleneck
Self-supervised learning aims to learn representation that can be effectively generalized to downstream tasks. Many self-supervised approaches regard two views of an image as both the input and the self-supervised signal…
Linear evaluationSelf-Supervised LearningLeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representations
Contrastive instance discrimination methods outperform supervised learning in downstream tasks such as image classification and object detection. However, these methods rely heavily on data augmentation during representa…
Contrastive LearningData Augmentationimage-classificationImage Classification+6Overcoming Dimensional Collapse in Self-supervised Contrastive Learning for Medical Image Segmentation
Self-supervised learning (SSL) approaches have achieved great success when the amount of labeled data is limited. Within SSL, models learn robust feature representations by solving pretext tasks. One such pretext task is…
Contrastive LearningImage SegmentationLinear evaluationMedical Image Analysis+3