LAGO: Language-Guided Adaptive Object-Region Focus for Zero-Shot Visual-Text Alignment

TL;DR

LAGO is a novel framework for zero-shot visual-text alignment that adaptively focuses on relevant object regions guided by language, improving efficiency and robustness in fine-grained recognition tasks.

Contribution

LAGO introduces a two-stage process with object-centric candidate discovery and adaptive language-guided refinement, reducing inference cost and avoiding error amplification.

Findings

LAGO achieves state-of-the-art results on zero-shot benchmarks.

LAGO requires fewer candidate regions during inference.

LAGO demonstrates robustness under distribution shifts.

Abstract

Zero-shot recognition aims to classify an image by selecting the most compatible label description from a set of candidate classes without any task-specific supervision. In fine-grained settings, however, the relevant evidence often lies in localized parts, attributes, or textures rather than in the full image, making whole-image alignment suboptimal. Recent localized visual-text alignment methods address this by comparing class descriptions with multiple image regions, but they typically rely on large sets of random or redundant crops, increasing inference cost and introducing many highly redundant or weakly relevant candidates. Moreover, introducing semantic guidance too early can create an error-amplifying feedback process in which inaccurate intermediate predictions bias later localization and reinforce subsequent mistakes; we refer to this failure mode as the prediction loop. We propose LAGO (LAnguage-Guided adaptive Object-region focus), a framework for efficient and robust zero-shot localized visual-text alignment. LAGO first performs class-agnostic object-centric candidate discovery to obtain a stable visual initialization, and then applies adaptive language-guided refinement with the strength of semantic guidance controlled by intermediate confidence. It further combines object-level, contextual, and full-image evidence through an effective object-context dual-channel aggregation strategy. Extensive experiments show that LAGO consistently achieves state-of-the-art performance on standard zero-shot benchmarks and challenging distribution-shift settings, while requiring substantially fewer candidate regions at inference time.