https://github.com/lxtGH/OctaveConv_pytorch
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
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.
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Improving Self-Organizing Maps with Unsupervised Feature Extraction
Very Deep Convolutional Networks for Large-Scale Image Recognition
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
Enhancing Cross-task Transferability of Adversarial Examples with Dispersion Reduction
Improved Regularization of Convolutional Neural Networks with Cutout
Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
BinaryConnect: Training Deep Neural Networks with binary weights during propagations
Deep CORAL: Correlation Alignment for Deep Domain Adaptation
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
Very Deep Convolutional Networks for Large-Scale Image Recognition
BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
Presence-Only Geographical Priors for Fine-Grained Image Classification
Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
Attention Branch Network: Learning of Attention Mechanism for Visual Explanation
Attention Branch Network: Learning of Attention Mechanism for Visual Explanation
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
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.