| --- |
| library_name: onnx |
| pipeline_tag: image-classification |
| tags: |
| - onnx |
| - onnxruntime |
| - image-classification |
| - multi-label-classification |
| - efficientnet |
| - social-comparison |
| - on-device |
| - browser |
| - mobile |
| license: other |
| model-index: |
| - name: safesocial-trigger-classifier |
| results: |
| - task: |
| type: image-classification |
| dataset: |
| name: primary Instagram-domain merged test (teacher-labeled) |
| type: teacher-agreement |
| metrics: |
| - type: micro f1 |
| value: 0.6817 |
| - type: macro f1 |
| value: 0.5126 |
| - type: exact match |
| value: 0.2952 |
| - type: label accuracy |
| value: 0.8684 |
| - task: |
| type: image-classification |
| dataset: |
| name: Karpathy COCO 500-image OOD holdout (teacher-labeled) |
| type: teacher-agreement |
| metrics: |
| - type: micro f1 |
| value: 0.6526 |
| - type: macro f1 |
| value: 0.3466 |
| - type: exact match |
| value: 0.5480 |
| - type: label accuracy |
| value: 0.9176 |
| --- |
| |
| # SafeSocial Trigger Classifier |
|
|
| SafeSocial is integrated into [WebBrain](https://webbrain.one) as an on-device, privacy-preserving visual moderation and wellbeing layer that automatically detects and mitigates sensitive social-comparison triggers across user feeds before content is rendered. |
|
|
|  |
|
|
| Compact on-device multi-label image classifier that detects Instagram-style |
| social-comparison triggers. Intended as a privacy-preserving, user-controlled |
| filtering aid — **not** a diagnostic tool, moderation authority, or measure of |
| human validity. |
|
|
| > All metrics below are **student-teacher agreement** against the Qwen teacher |
| > (`qwen3.6-35b-a3b`), not human-ground-truth accuracy. A human-verified |
| > evaluation set is still the main missing piece before making strong |
| > real-world claims. |
|
|
| ## Files |
|
|
| - `model.onnx` — deployment model, opset 17, input `pixel_values` (NCHW float32), output `probabilities` (sigmoid multi-label) |
| - `safesocial-model.json` — machine-readable manifest: labels, per-label thresholds, preprocessing, checkpoint provenance, train/val metrics |
|
|
| SHA-256 of `model.onnx` at release: `fd37c1cd4aafa2bc318b7d29725fa6be3931d09cc1723bb30be3ee819ee22933` |
|
|
| ## Labels (10, core taxonomy) |
|
|
| `romance_jealousy`, `social_fomo`, `luxury_status`, `travel_lifestyle`, |
| `body_beauty_comparison`, `achievement_status`, `social_proof_popularity`, |
| `exclusivity_access`, `none`, `uncertain` |
|
|
| Two labels from the earlier broad taxonomy were removed before this run and are |
| **not** predicted by this checkpoint: `envy` (too subjective / visually |
| underdetermined) and `financial_fomo` (too rare in the image sample). |
|
|
| ## Performance (tuned per-label thresholds) |
|
|
| Primary merged test (core + Kaggle partial, unchanged benchmark split): |
|
|
| | metric | value | |
| | --- | ---: | |
| | micro F1 | 0.6817 | |
| | macro F1 | 0.5126 | |
| | exact match | 0.2952 | |
| | label accuracy | 0.8684 | |
|
|
| Separate Karpathy COCO 500-image OOD holdout: |
|
|
| | metric | value | |
| | --- | ---: | |
| | micro F1 | 0.6526 | |
| | macro F1 | 0.3466 | |
| | exact match | 0.5480 | |
| | label accuracy | 0.9176 | |
|
|
| Report the two domains separately. Do not mix COCO numbers into the primary |
| Instagram-domain benchmark. |
|
|
| ## Thresholds (tuned on validation split, shipped in `safesocial-model.json`) |
|
|
| | label | threshold | |
| | --- | ---: | |
| | romance_jealousy | 0.75 | |
| | social_fomo | 0.80 | |
| | luxury_status | 0.45 | |
| | travel_lifestyle | 0.70 | |
| | body_beauty_comparison | 0.35 | |
| | achievement_status | 0.90 | |
| | social_proof_popularity | 0.60 | |
| | exclusivity_access | 0.60 | |
| | none | 0.75 | |
| | uncertain | 1.00 | |
|
|
| These thresholds need human review before product claims, especially for rare |
| labels. |
|
|
| ## Preprocessing |
|
|
| - `image_size`: 224, `resize`: 256, center crop |
| - color: RGB, layout NCHW |
| - normalize with ImageNet mean `[0.485, 0.456, 0.406]`, std `[0.229, 0.224, 0.225]` |
| - input name: `pixel_values`, output name: `probabilities` |
|
|
| ## Training |
|
|
| - backbone: `timm/tf_efficientnet_lite0` (feature dim 1280, trained end to end) |
| - teacher: `qwen3.6-35b-a3b` via local vLLM, core reduced taxonomy |
| - data: core `kkcosmos/instagram-images-with-captions` (19,991 valid rows) + partial `prithvijaunjale/instagram-images-with-captions` (2,641 rows) = 22,632 merged rows, plus capped ~20% Karpathy COCO auxiliary (4,500 train rows), 20 epochs |
| - this checkpoint is the aux20 20-epoch EfficientNet-Lite0 run from `paper/core_20k_findings.md` |
|
|
| ## Quick use (Python + onnxruntime) |
|
|
| ```python |
| import json |
| import numpy as np |
| import onnxruntime as ort |
| from PIL import Image |
| |
| manifest = json.load(open("safesocial-model.json")) |
| labels = manifest["labels"] |
| thresholds = manifest["label_thresholds"] |
| |
| img = Image.open("photo.jpg").convert("RGB") |
| img = img.resize((256, 256)) |
| w, h = img.size |
| img = img.crop(((w-224)//2, (h-224)//2, (w+224)//2, (h+224)//2)) |
| x = np.asarray(img, dtype=np.float32) / 255.0 |
| mean = np.array([0.485, 0.456, 0.406], np.float32) |
| std = np.array([0.229, 0.224, 0.225], np.float32) |
| x = (x - mean) / std |
| x = np.transpose(x, (2, 0, 1))[None] |
| |
| sess = ort.InferenceSession("model.onnx", providers=["CPUExecutionProvider"]) |
| probs = sess.run(None, {"pixel_values": x})[0][0] |
| print({l: float(p) for l, p in zip(labels, probs)}) |
| print([l for l, p in zip(labels, probs) if p >= thresholds[l]]) |
| ``` |
|
|
| Browser: ONNX Runtime Web (WebGPU/WASM). Mobile: ONNX Runtime React Native via |
| an Expo development build (Expo Go cannot run the native path); mock scores are |
| only a fallback. See the source repo `browser_extension/` and `mobile_app/` |
| prototypes. |
|
|
| ## Limitations / data caveat |
|
|
| - Teacher-labeled test data measures agreement with the teacher, not human validity. |
| - `uncertain` had ~zero support in test splits. |
| - Public Instagram-style datasets often have unclear scraping/licensing histories: fine for exploratory research, but product training should prefer opt-in, licensed, or synthetic imagery. |
| - COCO/Flickr data is auxiliary out-of-domain robustness data, not primary benchmark evidence. |
| - Do not redistribute source Instagram/Kaggle/HF image files unless the source license explicitly allows it. |
| - No LICENSE file ships in the source repo at release time; confirm rights before commercial use. |
|
|
| ## Source |
|
|
| Experiment details: `paper/core_20k_findings.md` in the SafeSocial repo. Model |
| export: `image_classifier/export_deployment_bundle.py`. |
|
|
|
|
| ## License |
|
|
| This project is released under a **Private** license. For commercial licensing, integration inquiries, or permissions, please contact **WebBrain**. |
|
|
|
|
