A feature embedding strategy for high-level CNN representations from multiple convnets
Bibliographic record
Abstract
Recently, pre-trained deep convolutional neural networks (DCNNs or ConvNets) have proven that the high-level features extracted at the top fully connected (FC) layer can improve the accuracy of various image understanding, recognition, and classification tasks. However, it has not been explored if such high-level features from different DCNN architectures contain complementary cues for image representation. Thence, in this paper, we further investigate a feature embedding strategy to exploit high-level features from multiple DCNNs in a framework of image-based object/action classification. We derive a generalized feature space by embedding different high-level features extracted through three ConvNets under Principal component analysis (PCA)-based reconstruction, energy level-based normalization, and five different fusion rules. Test outcomes on four different object classification datasets and an action classification dataset show that regardless of variation in image statistics and tasks the proposed multi-DCNN high-level feature embedding is well suited for the aforesaid tasks and it can be an effective complement of DCNN. In general, we observe that the proposed strategy is highly competitive with other approaches and tends to produce improvement in the classification accuracy.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".