vpariza / open-hummingbird-eval
This is a repository that implements the Dense NN Retrieval Evaluation used for evaluating the In-Context Learning Capabilities of Vision Encoders.
☆20Updated this week
Alternatives and similar repositories for open-hummingbird-eval:
Users that are interested in open-hummingbird-eval are comparing it to the libraries listed below
- Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations ICCV23☆27Updated 4 months ago
- "Near, far: Patch-ordering enhances vision foundation models' scene understanding": A New SSL Post-Training Approach for Improving DINOv2…☆20Updated 2 weeks ago
- [CVPR 2024 Highlight] SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers☆64Updated 11 months ago
- This repo contains the official implementation of ICLR 2024 paper "Is ImageNet worth 1 video? Learning strong image encoders from 1 long …☆88Updated 11 months ago
- Library implementation of "No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations"☆36Updated 6 months ago
- [ICLR 2023 - UNOFFICIAL] Bridging the Gap to Real-World Object-Centric Learning☆14Updated last year
- [ECCV 2024] PyTorch implementation of CropMAE, introduced in "Efficient Image Pre-Training with Siamese Cropped Masked Autoencoders"☆58Updated 2 months ago
- Perceptual Grouping in Contrastive Vision-Language Models (ICCV'23)☆36Updated last year
- PyTorch implementation of the paper "No reason for no supervision: Improving the generalization of supervised models"☆20Updated 2 years ago
- Official implementation of the CVPR'24 paper [Adaptive Slot Attention: Object Discovery with Dynamic Slot Number]☆42Updated 3 months ago
- [CVPR24] Official Implementation of GEM (Grounding Everything Module)☆121Updated last month
- ☆78Updated 2 years ago
- [NeurIPS 2023] Self-supervised Object-Centric Learning for Videos☆27Updated 5 months ago
- Code and data for the paper "Emergent Visual-Semantic Hierarchies in Image-Text Representations" (ECCV 2024)☆28Updated 8 months ago
- FLOSS: Plug-in Training-free and label-free text template selection that boosts OVSS methods☆20Updated 2 weeks ago
- ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation (CVPR'25)☆11Updated last month
- ☆11Updated last year
- An extremely simple method for validation-free efficient adaptation of CLIP-like VLMs that is robust to the learning rate.☆25Updated 3 weeks ago
- (NeurIPS 2022) Self-Supervised Visual Representation Learning with Semantic Grouping☆97Updated 2 months ago
- Official Release of NeurIPS 2023 Spotlight paper "Object-Centric Slot Diffusion"☆65Updated last year
- Official implementation of MOST: Multiple object localization with self-supervised transformers published at ICCV 2023☆17Updated last year
- An implementation of several unsupervised object discovery models (Slot Attention, SLATE, GNM) in PyTorch with pre-trained models.☆13Updated 2 years ago
- This repo contains the code for our paper Compositor: Bottom-Up Clustering and Compositing for Robust Part and Object Segmentation☆17Updated last month
- Learning to Count without Annotations☆23Updated 11 months ago
- Official code repo of PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs☆26Updated 3 months ago
- Pytorch implementation of "TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut"☆60Updated 2 years ago
- Code release for NeurIPS 2023 paper SlotDiffusion: Object-centric Learning with Diffusion Models☆85Updated last year
- Repository for our paper "Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities"☆22Updated 2 months ago
- ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models☆41Updated last year
- [CVPR'23] AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders☆79Updated last year