Codesota · Models · AltCLIP3 results · 3 benchmarks
Model card
AltCLIP.
unknown
§ 02 · Benchmarks
Every benchmark AltCLIP has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | COCO Captions | Multimodal · Image Captioning | r-1 | 42.9% | #3 | — | source ↗ |
| 02 | ImageNet-V2 | Computer Vision · Image Classification | accuracy | 68.2% | #4 | — | source ↗ |
| 03 | ImageNet-1K | Computer Vision · Image Classification | accuracy | 74.5% | #22 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where AltCLIP actually performs.
§ 04 · Papers
1 paper with results for AltCLIP.
- 2022-11-12· 3 results
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities
§ 06 · Sources & freshness
Where these numbers come from.
pwc-dump
3
results
0 of 3 rows marked verified.