A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
-
Updated
Jul 28, 2024 - Python
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
[ECCV2024] Video Foundation Models & Data for Multimodal Understanding
official code of “OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding”
Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)
[EMNLP 2022] This is the code repo for our EMNLP‘22 paper "COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning".
Evaluate custom and HuggingFace text-to-image/zero-shot-image-classification models like CLIP, SigLIP, DFN5B, and EVA-CLIP. Metrics include Zero-shot accuracy, Linear Probe, Image retrieval, and KNN accuracy.
Zero-shot Entity Linking with blitz start in 3 minutes. Hard negative mining and encoder for all entities are also included in this implementation.
Transductive Zero-Shot Hashing For Multi-Label Image Retrieval
Pytorch implementation of CVPR'16 paper "Learning Deep Representations of Fine-Grained Visual Descriptions", by Reed et al.
[ICCV 2021] PyTorch implementation of "Universal Cross-Domain Retrieval: Generalizing across Classes and Domains"
A toolkit for research on multimodal representation learning
[https://arxiv.org/abs/2208.09198] Test-Time Training for Universal Cross-Domain Retrieval
This is the open-source repository for the project "Solo-Synth GAN" which is one of the latest zero shot generative adversarial network
Add a description, image, and links to the zero-shot-retrieval topic page so that developers can more easily learn about it.
To associate your repository with the zero-shot-retrieval topic, visit your repo's landing page and select "manage topics."