https://github.com/BenediktAlkin/vtab1k-pytorch
공식 코드Parameter Efficient Fine-tuning via Explained Variance Adaptation
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.
Parameter Efficient Fine-tuning via Explained Variance Adaptation
Distributed Learning of Deep Neural Networks using Independent Subnet Training
ISLE: An Intelligent Streaming Framework for High-Throughput AI Inference in Medical Imaging
SITTA: Single Image Texture Translation for Data Augmentation
Beyond Categorical Label Representations for Image Classification
Langevin algorithms for very deep Neural Networks with application to image classification
Adversarial Augmentation for Enhancing Classification of Mammography Images
mFI-PSO: A Flexible and Effective Method in Adversarial Image Generation for Deep Neural Networks
DPT: Deformable Patch-based Transformer for Visual Recognition
Attacking by Aligning: Clean-Label Backdoor Attacks on Object Detection
PolyNet: A Pursuit of Structural Diversity in Very Deep Networks
Uncertainty Quantification using Variational Inference for Biomedical Image Segmentation
WaveCNet: Wavelet Integrated CNNs to Suppress Aliasing Effect for Noise-Robust Image Classification
Bottom-up Broadcast Neural Network For Music Genre Classification
Understanding Training-Data Leakage from Gradients in Neural Networks for Image Classification
Deep learning in a bilateral brain with hemispheric specialization
VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
Fourier Transform Approximation as an Auxiliary Task for Image Classification
Mind's Eye: Image Recognition by EEG via Multimodal Similarity-Keeping Contrastive Learning
DualConv: Dual Convolutional Kernels for Lightweight Deep Neural Networks
Low-Rank Subspace Override for Unsupervised Domain Adaptation
Going Beyond One-Hot Encoding in Classification: Can Human Uncertainty Improve Model Performance?
Mitigating belief projection in explainable artificial intelligence via Bayesian Teaching
Towards Principled Design of Deep Convolutional Networks: Introducing SimpNet
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.