astra-vision / ProLIPLinks
An extremely simple method for validation-free efficient adaptation of CLIP-like VLMs that is robust to the learning rate.
☆25Updated 3 months ago
Alternatives and similar repositories for ProLIP
Users that are interested in ProLIP are comparing it to the libraries listed below
Sorting:
- ☆10Updated last year
- PyTorch code and pretrained weights for the UNIC models.☆35Updated 10 months ago
- FLOSS: Plug-in Training-free and label-free text template selection that boosts OVSS methods☆23Updated this week
- [ECCV'24] Official PyTorch implementation of In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation☆45Updated 9 months ago
- ☆22Updated 4 months ago
- ☆14Updated 2 years ago
- MIMIC: Masked Image Modeling with Image Correspondences☆16Updated last year
- [CVPR 2024 Highlight] ImageNet-D☆43Updated 9 months ago
- Official Pytorch codebase for Open-Vocabulary Instance Segmentation without Manual Mask Annotations [CVPR 2023]☆50Updated 6 months ago
- Library implementation of "No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations"☆38Updated 8 months ago
- ☆26Updated 9 months ago
- PyTorch Implementation of NACLIP in "Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation"☆57Updated 9 months ago
- PyTorch implementation of the paper "No reason for no supervision: Improving the generalization of supervised models"☆18Updated 2 years ago
- ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models☆43Updated last year
- Perceptual Grouping in Contrastive Vision-Language Models (ICCV'23)☆37Updated last year
- (ICCV 2023) MasQCLIP for Open-Vocabulary Universal Image Segmentation☆38Updated last year
- Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling @ CVPR22☆42Updated 2 years ago
- [ECCV-24] This is the official implementation of the paper "SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation".☆24Updated 9 months ago
- FreeDA: Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation (CVPR 2024)☆44Updated 10 months ago
- [ECCV’24] Official repository for "BEAF: Observing Before-AFter Changes to Evaluate Hallucination in Vision-language Models"☆20Updated 3 months ago
- [NeurIPS 2024] Official PyTorch implementation of "Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives"☆41Updated 7 months ago
- [CVPR 2024] Domain generalization by interpolating original feature styles with styles obtained using random descriptions in natural lang…☆50Updated 2 months ago
- [ICCV23] EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation☆30Updated last year
- (NeurIPS 2024) What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights☆27Updated 8 months ago
- [ECCV 2024] PyTorch implementation of CropMAE, introduced in "Efficient Image Pre-Training with Siamese Cropped Masked Autoencoders"☆59Updated 4 months ago
- [CVPR24] Official Implementation of GEM (Grounding Everything Module)☆126Updated 3 months ago
- Official Implementation of DiffCLIP: Differential Attention Meets CLIP☆36Updated 4 months ago
- Source code for selective scaling in the paper of << On Calibrating Semantic Segmentation Models - Analyses and An Algorithm>> (CVPR 2023…☆15Updated 2 years ago
- ☆60Updated last year
- [CVPR 2024] Official Implementation of Collaborating Foundation models for Domain Generalized Semantic Segmentation☆70Updated 3 months ago