https://github.com/f-neumann77/hyperkan
공식 코드HyperKAN: Kolmogorov-Arnold Networks make Hyperspectral Image Classificators Smarter
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.
HyperKAN: Kolmogorov-Arnold Networks make Hyperspectral Image Classificators Smarter
Combining GANs and AutoEncoders for Efficient Anomaly Detection
Deep Fast Vision: A Python Library for Accelerated Deep Transfer Learning Vision Prototyping
AlphaNet: Improved Training of Supernets with Alpha-Divergence
Unsupervised Pre-Training of Image Features on Non-Curated Data
Detecting Twenty-thousand Classes using Image-level Supervision
Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation
LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
Needles in Haystacks: On Classifying Tiny Objects in Large Images
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
Aggregated Residual Transformations for Deep Neural Networks
Revisiting Weakly Supervised Pre-Training of Visual Perception Models
X3D: Expanding Architectures for Efficient Video Recognition
Video Classification with Channel-Separated Convolutional Networks
A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
Decoupling Representation and Classifier for Long-Tailed Recognition
ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
Deep Clustering for Unsupervised Learning of Visual Features
Training data-efficient image transformers & distillation through attention
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection
Differentiable Model Compression via Pseudo Quantization Noise
SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.