Zero-shot Image Retrieval
11 papers with code • 4 benchmarks • 4 datasets
Benchmarks
These leaderboards are used to track progress in Zero-shot Image Retrieval
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
COCO-CN
Flickr30k-CNA
XTD10
Most implemented papers
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities
In this work, we present a conceptually simple and effective method to train a strong bilingual/multilingual multimodal representation model.
Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers
deepmind/multimodal_transformers
•
•
Recently multimodal transformer models have gained popularity because their performance on language and vision tasks suggest they learn rich visual-linguistic representations.
FLAVA: A Foundational Language And Vision Alignment Model
State-of-the-art vision and vision-and-language models rely on large-scale visio-linguistic pretraining for obtaining good performance on a variety of downstream tasks.
Visual Representation Learning with Self-Supervised Attention for Low-Label High-data Regime
AutoVision-cloud/SSL-ViT-lowlabel-highdata
•
•
For few-shot image classification we train SSL-ViTs without any supervision, on external data, and use this trained embedder to adapt quickly to novel classes with limited number of labels.
Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark
0jason000/wukong
•
•
Experiments show that Wukong can serve as a promising Chinese pre-training dataset and benchmark for different cross-modal learning methods.
Zero and R2D2: A Large-scale Chinese Cross-modal Benchmark and A Vision-Language Framework
yuxie11/R2D2
•
•
Along with the ZERO benchmark, we also develop a VLP framework with pre-Ranking + Ranking mechanism, boosted with target-guided Distillation and feature-guided Distillation (R2D2) for large-scale cross-modal learning.
FETA: Towards Specializing Foundation Models for Expert Task Applications
alfassy/FETA
•
•
However, as we show in this paper, FMs still have poor out-of-the-box performance on expert tasks (e. g. retrieval of car manuals technical illustrations from language queries), data for which is either unseen or belonging to a long-tail part of the data distribution of the huge datasets used for FM pre-training.
General Image Descriptors for Open World Image Retrieval using ViT CLIP
The Google Universal Image Embedding (GUIE) Challenge is one of the first competitions in multi-domain image representations in the wild, covering a wide distribution of objects: landmarks, artwork, food, etc.
Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese
The tremendous success of CLIP (Radford et al., 2021) has promoted the research and application of contrastive learning for vision-language pretraining.
FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing
Textual scene graph parsing has become increasingly important in various vision-language applications, including image caption evaluation and image retrieval.
