The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels\n Methods
Bibliographic record
Abstract
A recent line of work showed that various forms of convolutional kernel\nmethods can be competitive with standard supervised deep convolutional networks\non datasets like CIFAR-10, obtaining accuracies in the range of 87-90% while\nbeing more amenable to theoretical analysis. In this work, we highlight the\nimportance of a data-dependent feature extraction step that is key to the\nobtain good performance in convolutional kernel methods. This step typically\ncorresponds to a whitened dictionary of patches, and gives rise to a\ndata-driven convolutional kernel methods. We extensively study its effect,\ndemonstrating it is the key ingredient for high performance of these methods.\nSpecifically, we show that one of the simplest instances of such kernel\nmethods, based on a single layer of image patches followed by a linear\nclassifier is already obtaining classification accuracies on CIFAR-10 in the\nsame range as previous more sophisticated convolutional kernel methods. We\nscale this method to the challenging ImageNet dataset, showing such a simple\napproach can exceed all existing non-learned representation methods. This is a\nnew baseline for object recognition without representation learning methods,\nthat initiates the investigation of convolutional kernel models on ImageNet. We\nconduct experiments to analyze the dictionary that we used, our ablations\nshowing they exhibit low-dimensional properties.\n
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 | 0.002 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.001 | 0.004 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".