https://github.com/kentttttt/darknet
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
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.
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
TADAM: Task dependent adaptive metric for improved few-shot learning
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Gradient Centralization: A New Optimization Technique for Deep Neural Networks
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations
Augmenting Convolutional networks with attention-based aggregation
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?
Fast Dynamic Routing Based on Weighted Kernel Density Estimation
Interpolation Consistency Training for Semi-Supervised Learning
Inferencing Based on Unsupervised Learning of Disentangled Representations
An Infinite Parade of Giraffes: Expressive Augmentation and Complexity Layers for Cartoon Drawing
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
Improved Regularization of Convolutional Neural Networks with Cutout
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.