https://github.com/Rishit-dagli/Gradient-Centralization-TensorFlow
Gradient Centralization: A New Optimization Technique for Deep Neural Networks
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.
Gradient Centralization: A New Optimization Technique for Deep Neural Networks
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection
Unicom: Universal and Compact Representation Learning for Image Retrieval
PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions
MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models
Adversarial Defense of Image Classification Using a Variational Auto-Encoder
Student-Teacher Feature Pyramid Matching for Anomaly Detection
Very Deep Convolutional Networks for Large-Scale Image Recognition
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Very Deep Convolutional Networks for Large-Scale Image Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.