Weeds and Crops: The Stem Emergence Point Dataset Collection
Bibliographic record
Abstract
Weeds present a significant threat to agriculture by competing with crops for vital resources like water, nutrients, and sunlight, ultimately reducing crop yields. Detecting weeds at an early stage is crucial for implementing effective control measures such as herbicide application, mechanical removal, or other treatments, which become less efficient and more costly as crops grow. In this paper, a dataset of 2,382 images with 1,389 images from a carrot field and 993 images from a lettuce field is presented. The visual challenge lies in accurately distinguishing weeds from crops. The paper also presents three deep neural network models for the weed detection task: a standard CNN, a hybrid CNN-LSTM, and a pure LSTM model—to assess the impact of temporal information on classification performance. Model performances are analyzed under identical training and testing conditions, evaluating trade-offs in accuracy, false detection rates, and inference speed. Our findings suggest that while the pure CNN model achieves the lowest false weed detection rate, it also has the highest false crop identification rate (13\%), whereas the pure LSTM model converges faster and provides the best overall weed classification performance.
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) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.005 |
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".