https://github.com/cea-list/sce
Similarity Contrastive Estimation for Self-Supervised Soft Contrastive Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Image Classification is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike object detection, which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as image retrieval, which also involves finding similar images in a large database.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Similarity Contrastive Estimation for Self-Supervised Soft Contrastive Learning
Xception: Deep Learning with Depthwise Separable Convolutions
Boosting Occluded Image Classification via Subspace Decomposition Based Estimation of Deep Features
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Calibrated Top-1 Uncertainty estimates for classification by score based models
The LogBarrier adversarial attack: making effective use of decision boundary information
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
MnasNet: Platform-Aware Neural Architecture Search for Mobile
Confident Learning: Estimating Uncertainty in Dataset Labels
Discriminative Joint Probability Maximum Mean Discrepancy (DJP-MMD) for Domain Adaptation
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
Confident Learning: Estimating Uncertainty in Dataset Labels
Improved Regularization of Convolutional Neural Networks with Cutout
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
RSMamba: Remote Sensing Image Classification with State Space Model
RSMamba: Remote Sensing Image Classification with State Space Model
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory
Visual Transformers: Token-based Image Representation and Processing for Computer Vision
Co-Correcting: Noise-tolerant Medical Image Classification via mutual Label Correction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.