https://github.com/dsba-lab/openal
Active Learning for Convolutional Neural Networks: A Core-Set Approach
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.
Active Learning for Convolutional Neural Networks: A Core-Set Approach
Augmenting Data with Mixup for Sentence Classification: An Empirical Study
Ensemble learning in CNN augmented with fully connected subnetworks
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
A Large-Scale Car Dataset for Fine-Grained Categorization and Verification
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
MOODv2: Masked Image Modeling for Out-of-Distribution Detection
Diversity with Cooperation: Ensemble Methods for Few-Shot Classification
NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications
Designing Neural Network Architectures using Reinforcement Learning
Image Quality Assessment Guided Deep Neural Networks Training
Image Quality Assessment Guided Deep Neural Networks Training
Image Quality Assessment Guided Deep Neural Networks Training
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.