https://github.com/havrylovv/isegprobe
FeatUp: A Model-Agnostic Framework for Features at Any Resolution
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
FeatUp: A Model-Agnostic Framework for Features at Any Resolution
U-Net: Convolutional Networks for Biomedical Image Segmentation
Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Feature Selective Anchor-Free Module for Single-Shot Object Detection
Rethinking Atrous Convolution for Semantic Image Segmentation
Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
ICNet for Real-Time Semantic Segmentation on High-Resolution Images
U-Net: Convolutional Networks for Biomedical Image Segmentation
Sparse R-CNN: End-to-End Object Detection with Learnable Proposals
Towards Deep Learning Models Resistant to Adversarial Attacks
CondConv: Conditionally Parameterized Convolutions for Efficient Inference
Object Detection with Pixel Intensity Comparisons Organized in Decision Trees
Training Region-based Object Detectors with Online Hard Example Mining
U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection
U-Net: Convolutional Networks for Biomedical Image Segmentation
How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers
MILA: Memory-Based Instance-Level Adaptation for Cross-Domain Object Detection
RandAugment: Practical automated data augmentation with a reduced search space
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.