DeepAI AI Chat
Log In Sign Up

EfficientCLIP: Efficient Cross-Modal Pre-training by Ensemble Confident Learning and Language Modeling

by   Jue Wang, et al.

While large scale pre-training has achieved great achievements in bridging the gap between vision and language, it still faces several challenges. First, the cost for pre-training is expensive. Second, there is no efficient way to handle the data noise which degrades model performance. Third, previous methods only leverage limited image-text paired data, while ignoring richer single-modal data, which may result in poor generalization to single-modal downstream tasks. In this work, we propose an EfficientCLIP method via Ensemble Confident Learning to obtain a less noisy data subset. Extra rich non-paired single-modal text data is used for boosting the generalization of text branch. We achieve the state-of-the-art performance on Chinese cross-modal retrieval tasks with only 1/10 training resources compared to CLIP and WenLan, while showing excellent generalization to single-modal tasks, including text retrieval and text classification.


page 3

page 8


Zero and R2D2: A Large-scale Chinese Cross-modal Benchmark and A Vision-Language Framework

Vision-language pre-training (VLP) relying on large-scale pre-training d...

UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning

Existed pre-training methods either focus on single-modal tasks or multi...

Learning by Hallucinating: Vision-Language Pre-training with Weak Supervision

Weakly-supervised vision-language (V-L) pre-training (W-VLP) aims at lea...

Data Efficient Masked Language Modeling for Vision and Language

Masked language modeling (MLM) is one of the key sub-tasks in vision-lan...

VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix

Existing vision-language pre-training (VLP) methods primarily rely on pa...

CommerceMM: Large-Scale Commerce MultiModal Representation Learning with Omni Retrieval

We introduce CommerceMM - a multimodal model capable of providing a dive...

Self-Supervised Audio-and-Text Pre-training with Extremely Low-Resource Parallel Data

Multimodal pre-training for audio-and-text has recently been proved to b...