https://github.com/e-solutions-GmbH/TensorFlow-iEVM
Exploring the Open World Using Incremental Extreme Value Machines
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.
Exploring the Open World Using Incremental Extreme Value Machines
Improved Regularization of Convolutional Neural Networks with Cutout
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Convolutional Neural Networks for Global Human Settlements Mapping from Sentinel-2 Satellite Imagery
A Benchmark for Interpretability Methods in Deep Neural Networks
A Simple Framework for Contrastive Learning of Visual Representations
A Simple Framework for Contrastive Learning of Visual Representations
Wasserstein Adversarial Examples via Projected Sinkhorn Iterations
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Towards Deep Learning Models Resistant to Adversarial Attacks
Going Deeper with Contextual CNN for Hyperspectral Image Classification
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.