A zero-shot composed image retrieval model trained on synthetic triplets, generated by an MLLM from moderately similar unlabeled image pairs, beats prior methods on three benchmarks.
Global and Local Semantic Completion Learning for Vision-Language Pre-training
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Cross-modal alignment plays a crucial role in vision-language pre-training (VLP) models, enabling them to capture meaningful associations across different modalities. For this purpose, numerous masked modeling tasks have been proposed for VLP to further promote cross-modal interactions. The core idea of previous masked modeling tasks is to focus on reconstructing the masked tokens based on visible context for learning local-local alignment. However, most of them pay little attention to the global semantic features generated for the masked data, resulting in a limited cross-modal alignment ability of global representations to local features of the other modality. Therefore, in this paper, we propose a novel Global and Local Semantic Completion Learning (GLSCL) task to facilitate global-local alignment and local-local alignment simultaneously. Specifically, the GLSCL task complements the missing semantics of masked data and recovers global and local features by cross-modal interactions. Our GLSCL consists of masked global semantic completion (MGSC) and masked local token completion (MLTC). MGSC promotes learning more representative global features, which have a great impact on the performance of downstream tasks, while MLTC reconstructs modal-fusion local tokens, further enhancing accurate comprehension of multimodal data. To evaluate the proposed approaches on cross-modal alignment, we develop a validation benchmark called ALIGN-BENCH. Moreover, we present a flexible vision encoder, enabling our model to simultaneously perform image-text and video-text multimodal tasks. Experimental results show that our proposed method obtains state-of-the-art performance on various vision-language benchmarks, such as visual question answering, image-text retrieval, and video-text retrieval.
citation-role summary
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval
A zero-shot composed image retrieval model trained on synthetic triplets, generated by an MLLM from moderately similar unlabeled image pairs, beats prior methods on three benchmarks.