ArkidMitra commited on
Commit
3a3ee47
Β·
verified Β·
1 Parent(s): 29e7460

org card: under-250M class first, then all-systems

Browse files
Files changed (1) hide show
  1. README.md +23 -1
README.md CHANGED
@@ -28,7 +28,29 @@ short_description: SOTA fashion retrieval, measured and open.
28
  </section>
29
 
30
  <section>
31
- <h2>Text-to-image retrieval β€” six systems, full corpus, one harness</h2>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  <p>
33
  Full-corpus MAP@10 through one shared pipeline, identical preprocessing per
34
  model, no gallery subsampling anywhere. Best per row in bold with πŸ₯‡, second πŸ₯ˆ.
 
28
  </section>
29
 
30
  <section>
31
+ <h2>Text-to-image β€” models under 250M parameters</h2>
32
+ <p>The size class most deployments use. Full-corpus MAP@10; best per row bold πŸ₯‡, second πŸ₯ˆ:</p>
33
+ <table>
34
+ <tr><th>benchmark (corpus)</th><th>FashionSigLIP 203M</th><th>MODA 203M</th><th>MODA Pro Lite 213M</th></tr>
35
+ <tr><td>KAGL (44K)</td><td>0.2769</td><td>0.2890 πŸ₯ˆ</td><td><b>0.3185</b> πŸ₯‡</td></tr>
36
+ <tr><td>Polyvore (94K)</td><td>0.3665</td><td>0.3726 πŸ₯ˆ</td><td><b>0.3997</b> πŸ₯‡</td></tr>
37
+ <tr><td>Atlas (78K)</td><td>0.1826</td><td>0.1884 πŸ₯ˆ</td><td><b>0.1945</b> πŸ₯‡</td></tr>
38
+ <tr><td>Fashion200K (202K)</td><td>0.1858 πŸ₯ˆ</td><td><b>0.1947</b> πŸ₯‡</td><td>0.1802</td></tr>
39
+ <tr><td>DeepFashion In-Shop (53K)</td><td>0.1587 πŸ₯ˆ</td><td><b>0.1703</b> πŸ₯‡</td><td>0.1031</td></tr>
40
+ <tr><td>DeepFashion Multimodal (43K)</td><td><b>0.0148</b> πŸ₯‡</td><td>0.0147 πŸ₯ˆ</td><td>0.0118</td></tr>
41
+ </table>
42
+ <p>
43
+ Every benchmark in this class is led by a MODA-family model except one, where
44
+ frozen FashionSigLIP keeps a 0.8% edge.
45
+ <b><a href="https://huggingface.co/HopitAI/moda-pro-lite">MODA Pro Lite</a> owns catalog
46
+ and title search</b> (KAGL +10.2%, Polyvore +7.3%, Atlas +3.2% over MODA) from one
47
+ checkpoint, no serving recipe; <b>MODA owns captions and instance retrieval</b>
48
+ (4 of 6 wins over FashionSigLIP significant under paired bootstrap).
49
+ </p>
50
+ </section>
51
+
52
+ <section>
53
+ <h2>Text-to-image β€” all systems, including larger models</h2>
54
  <p>
55
  Full-corpus MAP@10 through one shared pipeline, identical preprocessing per
56
  model, no gallery subsampling anywhere. Best per row in bold with πŸ₯‡, second πŸ₯ˆ.