Update README.md

README.md

@@ -1,75 +1,54 @@
----
-language: en
-license: apache-2.0
-tags:
-- nutrition
-- calorie-estimation
-- food
-- computer-vision
-- regression
-- siglip
-datasets:
-- pinkieseb/nutrition_dataset
-- aryachakraborty/Food_Calorie_Dataset
-metrics:
-- mae
-- rmse
-model-index:
-- name: CalorieK
-  results:
-  - task:
-      type: image-regression
-    dataset:
-      name: Nutrition5k (locked test)
-      type: Nutrition5k
-    metrics:
-    - type: mae
-      value: 86.2
-      name: Calorie MAE (kcal)
----
-
 # CalorieK — food-photo calorie & macro estimation
 
 A single RGB food photo in, five numbers out: **calories (kcal), mass (g), protein (g), carbohydrate (g), fat (g)**.
 CalorieK is a SigLIP2-base vision tower with a small regression head, fine-tuned end-to-end and evaluated
 under a strict, leakage-audited Nutrition5k protocol.
 
-## Headline result — locked Nutrition5k test set (608 dishes, official test split, never seen)
+![CalorieK predicted vs. actual calories](https://huggingface.co/Dralkh/CalorieK/resolve/main/calorie_accuracy.png)
+
+## Headline result — locked Nutrition5k test set (606 dishes, official test split, never seen)
 
-| Metric | CalorieK | CalorieCLIP (same 608 dishes) |
+| Metric | CalorieK | CalorieCLIP (same dishes) |
 | --- | --- | --- |
-| Calorie MAE | **86.2 kcal** (95% CI 53.5–132.3) | 155.7 kcal |
-| Median absolute error | **30.1 kcal** | 106.3 kcal |
-| Within ±50 kcal | **64.8%** | 20.2% |
-| Within ±100 kcal | **84.0%** | 47.0% |
-| Bias | **−49.5 kcal** | +67.5 kcal |
-| Invalid predictions | 0 / 608 | 0 / 608 |
+| Calorie MAE | **56.3 kcal** | 126.4 kcal |
+| Median absolute error | **30.0 kcal** | 106.2 kcal |
+| Within ±50 kcal | **65.0%** | 20.3% |
+| Within ±100 kcal | **84.3%** | 47.2% |
+| Bias | **−19.5 kcal** | +97.5 kcal |
+| Invalid predictions | 0 / 606 | 0 / 606 |
 
-CalorieK roughly halves CalorieCLIP's calorie MAE (86 vs 156 kcal) and nearly doubles its within-±100
-hit rate on the same 608 dishes. Every test image is a deterministic central frame from the official
-Nutrition5k camera-A side-angle video of an official _test-split_ dish — selected by dish ID, never by
-image quality. Evaluation is dish-level (`physical_meal_id`).
+CalorieK more than halves CalorieCLIP's calorie MAE and nearly doubles its within-±100 hit rate on the
+same dishes. Every test image is a deterministic central frame from the official Nutrition5k camera-A
+side-angle video of an official _test-split_ dish — selected by dish ID, never by image quality.
+Evaluation is dish-level (`physical_meal_id`).
 
-### Macronutrient accuracy (same 608 dishes)
+> Two of the 608 official test dishes carry corrupt ground-truth labels (a single 7,974 g "olives"
+> ingredient gives one dish 876 g of fat in a 159 g dish, and another an 8 kg mass) and are excluded
+> as physically impossible (calories > 2000). Including them, CalorieK's calorie MAE is 86.2 kcal
+> (RMSE 533, driven almost entirely by those two dishes); excluding them RMSE is 94.
+
+### Macronutrient accuracy (same 606 dishes)
 
 | Task | MAE | PMAE |
 | --- | --- | --- |
-| Mass | 68.2 g | 34.7% |
-| Protein | 6.4 g | 38.1% |
-| Carbohydrate | 7.9 g | 40.6% |
-| Fat | 7.7 g | 54.5% |
+| Mass | 55.3 g | 30.1% |
+| Protein | 6.2 g | 37.4% |
+| Carbohydrate | 6.3 g | 35.3% |
+| Fat | 5.0 g | 43.5% |
 
-## Comparison with open VLMs (paired 304-dish subset, seed 17)
+## Comparison with open VLMs (paired 303-dish subset, seed 17)
 
 Each model answered the same calorie question on the same dishes, scored against the official
 Nutrition5k calorie labels.
 
+![CalorieK vs. baselines](https://huggingface.co/Dralkh/CalorieK/resolve/main/model_comparison.png)
+
 | Model | Params | MAE (kcal) | Median AE | Within ±100 kcal | Bias |
 | --- | --- | --- | --- | --- | --- |
-| **CalorieK (ours)** | 93.7M | **84.5** | **28.0** | **82.2%** | −46.2 |
-| Qwen3.5-9B (Q8_0)‡ | 9B | 112.4 | 56.8 | 68.4% | −44.0 |
-| CalorieCLIP (public) | 151M | 155.9 | 106.4 | 46.7% | +71.0 |
-| MiniMax M3 (reasoning)§ | 428B (MoE) | 160.0 | 95.7 | 52.6% | +53.6 |
+| **CalorieK (ours)** | 93.7M | **54.7** | **27.8** | **82.5%** | −16.3 |
+| Qwen3.5-9B (Q8_0)‡ | 9B | 82.6 | 55.7 | 68.6% | −14.0 |
+| CalorieCLIP (public) | 151M | 126.7 | 106.4 | 46.9% | +101.0 |
+| MiniMax M3 (reasoning)§ | 428B (MoE) | 130.6 | 94.7 | 52.8% | +83.7 |
 
 ‡ Qwen3.5-9B: 8-bit GGUF (Q8_0) via llama.cpp, 4k context, thinking off.
 § MiniMax M3: hosted reasoning model, chain-of-thought enabled — extensive per-dish reasoning did not
@@ -87,7 +66,7 @@ weight decay 0.05, seed 17.
 - **Checkpoint selection**: best validation calorie MAE on 80 held-out camera-A dishes (validation MAE 57.3 kcal).
 Training ran ~13 minutes on one RTX 4080 (16 GB).
 - **Calibration**: a conformal radius fitted on 86 held-out calibration dishes gives 90% prediction
-intervals of ±119 kcal, with 87.3% actual coverage on the locked test set (`calibration.json`).
+intervals of ±119 kcal (`calibration.json`).
 
 ## Training data (20,000 samples, leakage-audited)
 
@@ -142,8 +121,8 @@ print(f"{kcal:.0f} kcal ± 119 (90% interval), {mass_g:.0f} g, P{protein_g:.0f}/
 
 - **Domain**: trained and evaluated on Nutrition5k-style plated single dishes photographed from the side;
 accuracy on multi-plate scenes, packaged food, or drinks is untested.
-- **Heavy tail**: RMSE (533) is far above MAE (86) — very high-calorie dishes are occasionally missed badly.
-Use the calibrated interval, not the point estimate, for anything that matters.
+- **High-calorie under-prediction**: the model plateaus and under-predicts on dishes above ~500 kcal
+(see the scatter above). Use the calibrated interval, not the point estimate, for anything that matters.
 - **Frames, not meals**: training frames come from videos of ~1,250 distinct dishes; visual diversity is
 narrower than the sample count suggests.