Add embedding model selection and comparison test scripts

- Update DetectLogosDETR to support both CLIP and DINOv2 models
  - Rename clip_model parameter to embedding_model
  - Add model type detection for different embedding extraction
  - DINOv2 uses CLS token, CLIP uses get_image_features()
- Add -e/--embedding-model argument to test_logo_detection.py
- Include model name in file output header
- Add run_threshold_tests.sh for testing various threshold/margin values
- Add run_model_comparison.sh for comparing CLIP vs DINOv2 models

run_model_comparison.sh

@@ -0,0 +1,92 @@
+#!/bin/bash
+#
+# Compare different embedding models for logo detection.
+# Tests CLIP vs DINOv2 models.
+#
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+OUTPUT_FILE="${SCRIPT_DIR}/model_comparison_results.txt"
+
+# Common parameters
+NUM_LOGOS=20
+REFS_PER_LOGO=10
+POSITIVE_SAMPLES=20
+NEGATIVE_SAMPLES=100
+MIN_MATCHING_REFS=3
+THRESHOLD=0.80
+MARGIN=0.10
+SEED=42
+
+# Clear output file and write header
+echo "Embedding Model Comparison Tests" > "$OUTPUT_FILE"
+echo "=================================" >> "$OUTPUT_FILE"
+echo "Date: $(date)" >> "$OUTPUT_FILE"
+echo "" >> "$OUTPUT_FILE"
+echo "Common Parameters:" >> "$OUTPUT_FILE"
+echo "  Matching method: multi-ref (max)" >> "$OUTPUT_FILE"
+echo "  Reference logos: $NUM_LOGOS" >> "$OUTPUT_FILE"
+echo "  Refs per logo: $REFS_PER_LOGO" >> "$OUTPUT_FILE"
+echo "  Positive samples: $POSITIVE_SAMPLES" >> "$OUTPUT_FILE"
+echo "  Negative samples: $NEGATIVE_SAMPLES" >> "$OUTPUT_FILE"
+echo "  Min matching refs: $MIN_MATCHING_REFS" >> "$OUTPUT_FILE"
+echo "  Threshold: $THRESHOLD" >> "$OUTPUT_FILE"
+echo "  Margin: $MARGIN" >> "$OUTPUT_FILE"
+echo "  Seed: $SEED" >> "$OUTPUT_FILE"
+echo "" >> "$OUTPUT_FILE"
+
+echo "Running model comparison tests..."
+echo "  Matching method: multi-ref (max)"
+echo "  Reference logos: $NUM_LOGOS"
+echo "  Threshold: $THRESHOLD"
+echo "  Margin: $MARGIN"
+echo "  Seed: $SEED"
+echo ""
+
+# IMPORTANT: Clear cache between model tests since embeddings are model-specific
+echo "NOTE: Cache will be cleared between model tests to ensure correct embeddings."
+echo ""
+
+# Test 1: CLIP ViT-Large (default)
+echo "=== Test 1: CLIP ViT-Large (openai/clip-vit-large-patch14) ==="
+uv run python "$SCRIPT_DIR/test_logo_detection.py" \
+    --num-logos $NUM_LOGOS \
+    --refs-per-logo $REFS_PER_LOGO \
+    --positive-samples $POSITIVE_SAMPLES \
+    --negative-samples $NEGATIVE_SAMPLES \
+    --matching-method multi-ref \
+    --min-matching-refs $MIN_MATCHING_REFS \
+    --use-max-similarity \
+    --threshold $THRESHOLD \
+    --margin $MARGIN \
+    --seed $SEED \
+    --embedding-model "openai/clip-vit-large-patch14" \
+    --clear-cache \
+    --output-file "$OUTPUT_FILE"
+
+echo ""
+
+# Test 2: DINOv2 Small
+echo "=== Test 2: DINOv2 Small (facebook/dinov2-small) ==="
+uv run python "$SCRIPT_DIR/test_logo_detection.py" \
+    --num-logos $NUM_LOGOS \
+    --refs-per-logo $REFS_PER_LOGO \
+    --positive-samples $POSITIVE_SAMPLES \
+    --negative-samples $NEGATIVE_SAMPLES \
+    --matching-method multi-ref \
+    --min-matching-refs $MIN_MATCHING_REFS \
+    --use-max-similarity \
+    --threshold $THRESHOLD \
+    --margin $MARGIN \
+    --seed $SEED \
+    --embedding-model "facebook/dinov2-small" \
+    --clear-cache \
+    --output-file "$OUTPUT_FILE"
+
+echo ""
+echo "Results saved to: $OUTPUT_FILE"
+echo ""
+echo "Note: You can also try other models:"
+echo "  - facebook/dinov2-base"
+echo "  - facebook/dinov2-large"
+echo "  - openai/clip-vit-base-patch32"
+echo "  - openai/clip-vit-large-patch14-336"