https://github.com/itanvir/gradcam
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
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.
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
Efficient Ladder-style DenseNets for Semantic Segmentation of Large Images
Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images
Averaging Weights Leads to Wider Optima and Better Generalization
Averaging Weights Leads to Wider Optima and Better Generalization
Certifiably Adversarially Robust Detection of Out-of-Distribution Data
Very Deep Convolutional Networks for Large-Scale Image Recognition
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
LambdaNetworks: Modeling Long-Range Interactions Without Attention
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
Post-Training Piecewise Linear Quantization for Deep Neural Networks
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.