Conventional Zero-Shot Learning with Semantic Graph-Enriched Non-Adversarial Synthetic Features
Bibliographic record
Abstract
Adversarial training-based generative methods have shown strong performance in Zero-Shot Learning (ZSL), but they often come with significant drawbacks — including training instability and high computational cost. These approaches typically use the same feature generation pipeline for both Conventional ZSL (CZSL), where test classes are strictly unseen, and Generalized ZSL (GZSL), where both seen and unseen classes are present during inference. In this work, we argue that such frameworks are unnecessarily expensive for CZSL setups, where the primary objective is accurate recognition of unseen classes. We propose CZSL-SGNSF, a non-adversarial generative method that synthesizes unseen visual features and further enhances them through semantic graph propagation by enabling knowledge transfers across related unseen categories. For classification, we introduce a classifier trained jointly with cross-entropy and KL-divergence objectives on visual-semantic contrast. Extensive experiments on SUN, AwA2, and CUB demonstrate that our approach surpasses state-of-the-art adversarial methods in CZSL performance with significantly lower computational overhead for feature synthesis, while achieving promising results in both CZSL and GZSL compared to non-adversarial methods.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".