2023/09/02 by Dahun Kim, Anelia Angelova, Kim, Dahun +3 · 5 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications
paper · pdf · doi:10.48550/arxiv.2309.00775
openalex publication_date 2023/09/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We present Contrastive Feature Masking Vision Transformer (CFM-ViT) - an image-text pretraining methodology that achieves simultaneous learning of image- and region-level representation for open-vocabulary object detection (OVD). Our approach combines the masked autoencoder (MAE) objective into the contrastive learning objective to improve the representation for localization tasks. Unlike standard MAE, we perform reconstruction in the joint image-text embedding space, rather than the pixel space as is customary with the classical MAE method, which causes the model to better learn region-level semantics. Moreover, we introduce Positional Embedding Dropout (PED) to address scale variation between image-text pretraining and detection finetuning by randomly dropping out the positional embeddings during pretraining. PED improves detection performance and enables the use of a frozen ViT backbone as a region classifier, preventing the forgetting of open-vocabulary knowledge during detection finetuning. On LVIS open-vocabulary detection benchmark, CFM-ViT achieves a state-of-the-art 33.9 APr, surpassing the best approach by 7.6 points and achieves better zero-shot detection transfer. Finally, CFM-ViT acquires strong image-level representation, outperforming the state of the art on 8 out of 12 metrics on zero-shot image-text retrieval benchmarks.