There are 1 repository under zero-shot-retrieval topic.
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
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)
Zero-shot Entity Linking with blitz start in 3 minutes. Hard negative mining and encoder for all entities are also included in this implementation.
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.
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.
This is the open-source repository for the project "Solo-Synth GAN" which is one of the latest zero shot generative adversarial network