# DSAA: Dual-Stage Attribute Activation for Fine-grained Open Vocabulary Detection

Source: [DSAA: Dual-Stage Attribute Activation for Fine-grained Open Vocabulary Detection](<https://www.sota2.com/research/paper/6a0beecfdbc836b87d82c6f8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-02T05:00:12.522Z

Authors: Donghong Jiang, Endian Lin, Hanqing Liu, Mingjie Liu, Luoping Cui, Zhao Yang, Chuang Zhu

Published: 2026-05-18T08:13:13.000Z

## Abstract

Open-Vocabulary Object Detection (OVD) models break the limitations of closed-set detection, enabling the identification of unseen categories through natural language prompts. However, they exhibit notable limitations in fine-grained detection tasks involving attributes like color, material, and texture. We attribute this performance bottleneck in OVD models to a core issue: when category signals dominate, OVD models tend to marginalize attribute information during inference. This leads to incorrect binding between attributes and target objects. To address this, we propose the Dual-Stage Attribute Activation (DSAA) framework, which enhances fine-grained detection capabilities by strengthening attribute semantics at two critical stages. In the text embedding stage, we employ Attribute Prefix Adapter (APA) module to generate attribute prefixes that inject explicit attribute priors. To further amplify the influence of these attributes, our Key/Value (K/V) Modulator module then intervenes during the BERT encoding phase, selectively enhancing the Key and Value vectors of the corresponding attribute tokens. In addition, we introduce an attribute-aware contrastive loss to improve discrimination among same-category instances with different attributes during training. Experimental results on the FG-OVD benchmark demonstrate the effectiveness of our method across various mainstream open-vocabulary models.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Open-Vocabulary Object Detection on FG-OVD (Difficulty and Attribute Metrics)](<https://www.sota2.com/research/sota/open-vocabulary-object-detection-on-fg-ovd-difficulty-and-attribute-metrics.md>): Open-vocabulary object detection; FG-OVD; Score (Hard Difficulty): 52.9.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.18023>)

[PDF](<https://arxiv.org/pdf/2605.18023.pdf>)