Semantically-Prompted Language Models Improve Visual Descriptions
Bibliographic record
Abstract
Language-vision models like CLIP have made significant strides in vision tasks, such as zeroshot image classification (ZSIC).However, generating specific and expressive visual descriptions remains challenging; descriptions produced by current methods are often ambiguous and lacking in granularity.To tackle these issues, we propose V-GLOSS: Visual Glosses, a novel method built upon two key ideas.The first is Semantic Prompting, which conditions a language model on structured semantic knowledge.The second is a new contrastive algorithm that elicits fine-grained distinctions between similar concepts.With both ideas, we demonstrate that V-GLOSS improves visual descriptions and achieves strong results in the zero-shot setting on general and fine-grained image-classification datasets, including Ima-geNet, STL-10, FGVC Aircraft, and Flowers 102.Moreover, these descriptive capabilities contribute to enhancing image-generation performance.Finally, we introduce a qualitytested silver dataset with descriptions generated with V-GLOSS for all ImageNet classes.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.010 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.006 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.023 | 0.010 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".