Papers › Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via...
Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects
Junyu Lu, Dixiang Zhang, Songxin Zhang, Zejian Xie, Zhuoyang Song, Cong Lin, Jiaxing Zhang, BingYi Jing, Pingjian Zhang
Large Vision Language Models (LVLMs) have demonstrated impressive zero-shot capabilities in various vision-language dialogue scenarios. However, the absence of fine-grained visual object detection hinders the model from understanding the details of images, leading to irreparable visual hallucinations and factual errors. In this paper, we propose Lyrics, a novel multi-modal pre-training and instruction fine-tuning paradigm that bootstraps vision-language alignment from fine-grained cross-modal collaboration. Building on the foundation of BLIP-2, Lyrics infuses local visual features extracted from a visual refiner that includes image tagging, object detection and semantic segmentation modules into the Querying Transformer, while on the text side, the language inputs equip the boundary boxes and tags derived from the visual refiner. We further introduce a two-stage training scheme, in which the pre-training stage bridges the modality gap through explicit and comprehensive vision-language alignment targets. During the instruction fine-tuning stage, we introduce semantic-aware visual feature extraction, a crucial method that enables the model to extract informative features from concrete visual objects. Our approach achieves robust performance on 13 datasets across various vision-language tasks, and demonstrates promising multi-modal understanding, perception and conversation capabilities in 11 scenario-based benchmark toolkits.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Captioning | COCO (Common Objects in Context) | Lyrics | CIDEr | 121.1 | #6 of 17 | Archive leaderboard | report |
| Image Captioning | nocaps entire | Lyrics | CIDEr | 126.8 | #1 of 39 | Archive leaderboard | report |
| Visual Question Answering (VQA) | GQA test-dev | Lyrics | Accuracy | 62.4 | #6 of 17 | Archive leaderboard | report |
| Visual Question Answering (VQA) | OK-VQA | Lyrics | Accuracy | 58.2 | #10 of 37 | Archive leaderboard | report |
| Visual Question Answering (VQA) | VQA v2 test-dev | Lyrics | Accuracy | 81.2 | #9 of 56 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections