Bibliographic record
Abstract
Image retrieval is an important task in computer vision. Among various image retrieval approaches, deep hashing methods map input images to binary codes for nearest neighbor search, achieving advantages in both search time and space. In recent years, most deep hashing methods have adopted convolutional neural networks (CNNs) as the backbone network. CNNs can effectively extract local information, but perform poorly in capturing global information, resulting in decreased accuracy of image retrieval. The latest visual transformers can capture global features well, but blur out the details of local features. To solve the problem, this paper proposes a Conformer-based deep hashing architecture, called ConHash, which employs a CNN and a Transformer in parallel to maximize the preservation of both local and global features. Specifically, a new encoding optimization loss, called entropy-balanced loss, was proposed to increase the entropy of the hash codes and bring them closer to the ideal uniform distribution. Comprehensive experiments were carried out on Canadian Institute For Advanced Research (CIFAR-10) and ImageNet datasets. The results show that the proposed approach achieved state-of-the-art performance. Compared to the latest deep hashing methods, our approach achieved a 4.3% and 8.7% average improvement of mean average precision (mAP) at different bit lengths. This proves the superiority of our method.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".