https://github.com/garygsw/smooth-taylor
공식 코드Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution
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.
Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution
OpenStreetView-5M: The Many Roads to Global Visual Geolocation
ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer
Learnable Adaptive Cosine Estimator (LACE) for Image Classification
Unsupervised representation learning with recognition-parametrised probabilistic models
Combining Human Predictions with Model Probabilities via Confusion Matrices and Calibration
An empirical study on the effects of different types of noise in image classification tasks
Instance Enhancement Batch Normalization: an Adaptive Regulator of Batch Noise
A Single Graph Convolution Is All You Need: Efficient Grayscale Image Classification
Variational Stochastic Gradient Descent for Deep Neural Networks
Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells
SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training
NOVUM: Neural Object Volumes for Robust Object Classification
Benchmarking Pathology Feature Extractors for Whole Slide Image Classification
Investigating the Corruption Robustness of Image Classifiers with Random Lp-norm Corruptions
Regularization with Latent Space Virtual Adversarial Training
Measurement noise scaling laws for cellular representation learning
Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection
Unsupervised Representation Learning by Predicting Image Rotations
Overinterpretation reveals image classification model pathologies
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.