ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models

Learning visual representations from natural language supervision has recently shown great promise in a number of pioneering works. In general, these language-augmented visual models demonstrate strong transferability to a variety of datasets and tasks. However, it remains challenging to evaluate the transferablity of these models due to the lack of easy-to-use evaluation toolkits and public benchmarks. To tackle this, we build ELEVATER (Evaluation of Language-augmented Visual Task-level Transfer), the first benchmark and toolkit for evaluating(pre-trained) language-augmented visual models. ELEVATER is composed of three components. (i) Datasets. As downstream evaluation suites, it consists of 20 image classification datasets and 35 object detection datasets, each of which is augmented with external knowledge. (ii) Toolkit. An automatic hyper-parameter tuning toolkit is developed to facilitate model evaluation on downstream tasks. (iii) Metrics. A variety of evaluation metrics are used to measure sample-efficiency (zero-shot and few-shot) and parameter-efficiency (linear probing and full model fine-tuning). ELEVATER is a platform for Computer Vision in the Wild (CVinW), and is publicly released at at https://computer-vision-in-the-wild.github.io/ELEVATER/

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Object Detection ELEVATER GLIP-T AP 62.6 # 1
Zero-Shot Image Classification ICinW CLIP (ViT B-32) Average Score 56.64 # 1
Zero-Shot Image Classification ODinW GLIP (Tiny A) Average Score 11.4 # 1
Zero-Shot Object Detection ODinW GLIP (Tiny A) Average Score 11.4 # 4
Object Detection ODinW Full-shot 35 Tasks GLIP-T AP 62.6 # 2

Methods


No methods listed for this paper. Add relevant methods here