ExpAlign: Expectation-Guided Vision-Language Alignment for Open-Vocabulary Grounding
This addresses the challenge of fine-grained vision-language alignment for open-vocabulary detection and segmentation, particularly benefiting long-tail categories.
The paper tackles the problem of open-vocabulary grounding by proposing ExpAlign, a vision-language alignment framework that improves accuracy without explicit supervision. It achieves 36.2 AP_r on LVIS minival, outperforming state-of-the-art methods while remaining lightweight.
Open-vocabulary grounding requires accurate vision-language alignment under weak supervision, yet existing methods either rely on global sentence embeddings that lack fine-grained expressiveness or introduce token-level alignment with explicit supervision or heavy cross-attention designs. We propose ExpAlign, a theoretically grounded vision-language alignment framework built on a principled multiple instance learning formulation. ExpAlign introduces an Expectation Alignment Head that performs attention-based soft MIL pooling over token-region similarities, enabling implicit token and instance selection without additional annotations. To further stabilize alignment learning, we develop an energy-based multi-scale consistency regularization scheme, including a Top-K multi-positive contrastive objective and a Geometry-Aware Consistency Objective derived from a Lagrangian-constrained free-energy minimization. Extensive experiments show that ExpAlign consistently improves open-vocabulary detection and zero-shot instance segmentation, particularly on long-tail categories. Most notably, it achieves 36.2 AP$_r$ on the LVIS minival split, outperforming other state-of-the-art methods at comparable model scale, while remaining lightweight and inference-efficient.