Why are image crops crucial? 🤔 We found that simply adding text segments isn't enough. The biggest performance gains come when text segments are paired with image crops, proving the power of serial image computing.

We've evaluated it across three diverse datasets: BiVLC, Winoground (171 instances), and BiSCoR-Ctrl. See the significant improvements by inference-time approach (ITA) on three existing models:

Our approach is straightforward yet effective:
1. Divide the image into smaller crops.
2. Extract text segments capturing objects, attributes and relations.
3. Use the VLM to find image crops that best fit the text segments.
4. Aggregate matching similarities for the final score.

#newHitzPaper
Can a simple inference-time approach unlock better Vision-Language Compositionality?🤯
Our latest paper shows how adding structure at inference significantly boosts performance in popular dual-encoder VLMs on different datasets.

Read more: arxiv.org/abs/2506.09691