ali-k-hesar / how-AI-Sees-Our-World
Vision Transformer (ViT) models, with their attention mechanisms, revolutionized computer vision. By merging Class Activation Map (CAM) and Gradient-weighted Class Activation Map (Grad-CAM) concepts with ViT's attention maps, we gain deeper insights into how these models perceive and analyze images.
☆11Updated last year
Alternatives and similar repositories for how-AI-Sees-Our-World:
Users that are interested in how-AI-Sees-Our-World are comparing it to the libraries listed below
- [CVPR 2023 Highlight] Masked Image Modeling with Local Multi-Scale Reconstruction☆46Updated last year
- [CVPR 2024] Exploring Orthogonality in Open World Object Detection☆40Updated 7 months ago
- [ICCV'23 Oral] Unmasking Anomalies in Road-Scene Segmentation☆49Updated 9 months ago
- Code for CVPR2024 'Segment Every Out-of-Distribution Object '☆20Updated 3 weeks ago
- [CVPR 2022] official repo of "H2FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-domain Weakly Supervised Object Detection…☆29Updated 2 years ago
- Iterative Loop Method Combining Active and Semi-Supervised Learning for Domain Adaptive Semantic Segmentation☆32Updated last year
- Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-World Application☆29Updated 2 months ago
- ☆34Updated last year
- Implementation of the paper ''Implicit Feature Refinement for Instance Segmentation''.☆20Updated 3 years ago
- [CVPR' 22] Towards Robust Adaptive Object Detection under Noisy Annotations☆32Updated 2 years ago
- Multi-Anchor Active Domain Adaptation for Semantic Segmentation (ICCV 2021 Oral)☆43Updated 2 years ago
- Official Implementation of DE-DETR and DELA-DETR in "Towards Data-Efficient Detection Transformers"☆78Updated 10 months ago
- LeemSaebom / Attention-Guided-CAM-Visual-Explanations-of-Vision-Transformer-Guided-by-Self-AttentionThe official code for Attention Guided CAM: Visual Explanations of Vision Transformer Guided by Self-Attention☆13Updated 11 months ago
- ☆44Updated 9 months ago
- Code of the all the data augmentation [ Based on our survey, that will soon be published ]☆8Updated last year
- ☆56Updated last year
- Imbalanced learning tool for imbalanced recognition and segmentation☆82Updated last year
- [ICML 2023] Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN☆25Updated 5 months ago
- Vector-Decomposed Disentanglement for Domain-Invariant Object Detection☆31Updated 3 years ago
- LiBingyu01 / StitchFusion-StitchFusion-Weaving-Any-Visual-Modalities-to-Enhance-Multimodal-Semantic-Segmentation☆16Updated last week
- [ICCV 23]This is a Pytorch implementation of our paper "SMMix: Self-Motivated Image Mixing for Vision Transformers"☆16Updated last year
- [ICCV 2023] Source code of "Fcaformer: Forward Cross Attention in Hybrid Vision Transformer"☆22Updated last year
- 【IEEE Transactions on Multimedia 2022】Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement☆34Updated 2 years ago
- [ECCV 2022] Robust Object Detection With Inaccurate Bounding Boxes☆34Updated last year
- ☆38Updated 3 years ago
- ☆32Updated 2 years ago
- ☆25Updated 2 years ago
- ☆19Updated last year
- CVPR 2023☆59Updated 2 weeks ago
- [NeurIPS'22] Projector Ensemble Feature Distillation☆29Updated last year