EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
read the original abstract
We launch EVA, a vision-centric foundation model to explore the limits of visual representation at scale using only publicly accessible data. EVA is a vanilla ViT pre-trained to reconstruct the masked out image-text aligned vision features conditioned on visible image patches. Via this pretext task, we can efficiently scale up EVA to one billion parameters, and sets new records on a broad range of representative vision downstream tasks, such as image recognition, video action recognition, object detection, instance segmentation and semantic segmentation without heavy supervised training. Moreover, we observe quantitative changes in scaling EVA result in qualitative changes in transfer learning performance that are not present in other models. For instance, EVA takes a great leap in the challenging large vocabulary instance segmentation task: our model achieves almost the same state-of-the-art performance on LVISv1.0 dataset with over a thousand categories and COCO dataset with only eighty categories. Beyond a pure vision encoder, EVA can also serve as a vision-centric, multi-modal pivot to connect images and text. We find initializing the vision tower of a giant CLIP from EVA can greatly stabilize the training and outperform the training from scratch counterpart with much fewer samples and less compute, providing a new direction for scaling up and accelerating the costly training of multi-modal foundation models. To facilitate future research, we release all the code and models at https://github.com/baaivision/EVA.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
Are Large Pre-trained Vision Language Models Effective Construction Safety Inspectors?
Presents the ConstructionSite 10k dataset and evaluates pre-trained VLMs on zero-shot and few-shot construction safety inspection tasks.
-
InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
Instruction tuning of BLIP-2 with an instruction-aware Query Transformer delivers state-of-the-art zero-shot performance on held-out vision-language datasets and strong finetuned results on downstream tasks.
-
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
BLIP-2 bootstraps vision-language pre-training from frozen image encoders and LLMs via a lightweight two-stage Querying Transformer, delivering SOTA results with 54x fewer trainable parameters than Flamingo80B on zero...
-
XAMI -- A Benchmark Dataset for Artefact Detection in XMM-Newton Optical Images
Introduces the XAMI benchmark dataset of 1000 annotated XMM-Newton images for artefact detection together with a hybrid CNN-transformer instance segmentation demonstration.
-
MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
MiniGPT-4 shows that aligning a frozen vision encoder to Vicuna via one projection layer plus a second-stage detailed-description fine-tune produces GPT-4-like vision-language abilities including detailed captions, cr...
-
EVA-CLIP: Improved Training Techniques for CLIP at Scale
EVA-CLIP delivers improved CLIP training recipes that yield 82.0% zero-shot ImageNet-1K accuracy for a 5B-parameter model after only 9 billion samples.
-
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
InternVL scales a vision model to 6B parameters and aligns it with LLMs using web data to achieve state-of-the-art results on 32 visual-linguistic benchmarks.
-
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
MiniGPT-v2 adds unique task identifiers to a large language model so one system can perform image description, visual question answering, and visual grounding after three-stage training.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.