vpariza / NeCoLinks
"Near, far: Patch-ordering enhances vision foundation models' scene understanding": A New SSL Post-Training Approach for Improving DINOv2’s spatial representations in 19 GPU hours with Patch Neighbor Consistency
☆29Updated 9 months ago
Alternatives and similar repositories for NeCo
Users that are interested in NeCo are comparing it to the libraries listed below
Sorting:
- Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations ICCV23☆30Updated last year
- [CVPR24] Official Implementation of GEM (Grounding Everything Module)☆137Updated 10 months ago
- Library implementation of "No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations"☆40Updated last year
- [ECCV'24] Official PyTorch implementation of In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation☆49Updated last year
- Personalized Representation from Personalized Generation (ICLR 2025)☆66Updated 11 months ago
- Official implementation of MOST: Multiple object localization with self-supervised transformers published at ICCV 2023☆17Updated last year
- This repo contains the official implementation of ICLR 2024 paper "Is ImageNet worth 1 video? Learning strong image encoders from 1 long …☆95Updated last year
- Official implementation of 'CLIP-DINOiser: Teaching CLIP a few DINO tricks' paper.☆273Updated last year
- [NeurIPS 2024] Understanding Multi-Granularity for Open-Vocabulary Part Segmentation☆60Updated last year
- Official implementation of the WACV 2024 paper CLIP-DIY☆34Updated 2 years ago
- [ECCV’24] Official repository for "BEAF: Observing Before-AFter Changes to Evaluate Hallucination in Vision-language Models"☆21Updated 10 months ago
- ☆29Updated last year
- Code for the paper "AMEGO: Active Memory from long EGOcentric videos" published at ECCV 2024☆43Updated last year
- ☆16Updated last year
- CycleReward is a reward model trained on cycle consistency preferences to measure image-text alignment.☆53Updated 3 months ago
- (ICCV 2023) MasQCLIP for Open-Vocabulary Universal Image Segmentation☆37Updated 2 years ago
- FreeDA: Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation (CVPR 2024)☆49Updated last year
- PyTorch Implementation of NACLIP in "Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation"☆71Updated last year
- [ECCV2024] ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference☆97Updated 10 months ago
- [ECCV 2024] Official implementation of the paper "Towards Latent Masked Image Modeling for Self-Supervised Visual Representation Learning…☆29Updated 11 months ago
- The Official PyTorch Implementation of OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation☆34Updated last year
- Official Implementation of the CrossMAE paper: Rethinking Patch Dependence for Masked Autoencoders☆131Updated 10 months ago
- [NeurIPS 2024] Official code for DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut☆50Updated last year
- IFSeg: Image-free Semantic Segmentation via Vision-Language Model (CVPR 2023)☆95Updated 2 years ago
- Official PyTorch Implementation for Diffusion Hyperfeatures, NeurIPS 2023☆113Updated last year
- Code for the paper Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models @ CVPR 2024☆72Updated last year
- [CVPR 2024 Highlight] SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers☆73Updated last year
- Official code of Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning☆261Updated 4 months ago
- Official repository of paper "Subobject-level Image Tokenization" (ICML-25)☆92Updated 7 months ago
- Official PyTorch Implementation of Efficient and Versatile Robust Fine-Tuning of Zero-shot Models, ECCV 2024☆17Updated last year