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

• URL: http://arxiv.org/abs/2605.18023v1
• Date: Mon, 18 May 2026 08:13:13 GMT
• Title: DSAA: Dual-Stage Attribute Activation for Fine-grained Open Vocabulary Detection
• Abstract summary: Open-Vocabulary Object Detection (OVD) models break the limitations of closed-set detection.<n>They exhibit notable limitations in fine-grained detection tasks involving attributes like color, ma- terial, and texture.<n>We propose the Dual-Stage Attribute Activation framework, which enhances fine-grained detection capa- bilities.
• Score: 10.512210722250236
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Open-Vocabulary Object Detection (OVD) models break the limitations of closed-set detection, enabling the iden- tification of unseen categories through natural language prompts. However, they exhibit notable limitations in fine- grained detection tasks involving attributes like color, ma- terial, and texture. We attribute this performance bottle- neck in OVD models to a core issue: when category sig- nals dominate, OVD models tend to marginalize attribute information during inference. This leads to incorrect bind- ing between attributes and target objects. To address this, we propose the Dual-Stage Attribute Activation (DSAA) framework, which enhances fine-grained detection capa- bilities by strengthening attribute semantics at two criti- cal stages. In the text embedding stage, we employ At- tribute Prefix Adapter (APA) module to generate attribute prefixes that inject explicit attribute priors. To further am- plify the influence of these attributes, our Key/Value (K/V) Modulator module then intervenes during the BERT encod- ing phase, selectively enhancing the Key and Value vec- tors of the corresponding attribute tokens. In addition, we introduce an attribute-aware contrastive loss to improve discrimination among same-category instances with differ- ent attributes during training. Experimental results on the FG-OVD benchmark demonstrate the effectiveness of our method across various mainstream open-vocabulary mod- els.

Related papers

• SLIP-RS: Structured-Attribute Language-Image Pre-Training for Remote Sensing Object Detection [47.63279428416795]
  Existing language-image pre-training for remote sensing object detection is constrained by Monolithic Label Learning.<n>We propose SLIP-RS, establishing a Structured-Attribute Decoupling Paradigm that maps the open-ended category space into a finite, physically meaningful space.<n>Experiments demonstrate that SLIP-RS establishes unprecedented performance in fine-grained detection and cross-domain generalization.
  arXiv  Detail & Related papers  (2026-05-22T01:50:19Z)
• FACTOR: Counterfactual Training-Free Test-Time Adaptation for Open-Vocabulary Object Detection [63.91351553178842]
  FACTOR is a training-free Test-time adaptation for Open-vocabulary object detection.<n>It quantifies attribute sensitivity, semantic relevance, and prediction variation to selectively suppress attribute-dependent predictions.<n>Experiments on PASCAL-C, COCO-C, and FoggyCityscapes show that FACTOR consistently outperforms prior TTA methods.
  arXiv  Detail & Related papers  (2026-05-05T02:31:18Z)
• GUIDED: Granular Understanding via Identification, Detection, and Discrimination for Fine-Grained Open-Vocabulary Object Detection [54.19989440021701]
  Fine-grained open-vocabulary object detection (FG-OVD) aims to detect novel object categories described by attribute-rich texts.<n>FG-OVD achieves new state-of-the-art results, demonstrating the benefits of disentangled modeling and modular optimization.
  arXiv  Detail & Related papers  (2026-03-27T22:08:11Z)
• What Makes You Unique? Attribute Prompt Composition for Object Re-Identification [70.67907354506278]
  Object Re-IDentification aims to recognize individuals across non-overlapping camera views.<n>Single-domain models tend to overfit to domain-specific features, whereas cross-domain models often rely on diverse normalization strategies.<n>We propose an Attribute Prompt Composition framework, which exploits textual semantics to jointly enhance discrimination and generalization.
  arXiv  Detail & Related papers  (2025-09-23T07:03:08Z)
• Compositional Caching for Training-free Open-vocabulary Attribute Detection [65.46250297408974]
  We present Compositional Caching (ComCa), a training-free method for open-vocabulary attribute detection.<n>ComCa requires only the list of target attributes and objects as input, using them to populate an auxiliary cache of images.<n>Experiments on public datasets demonstrate that ComCa significantly outperforms zero-shot and cache-based baselines.
  arXiv  Detail & Related papers  (2025-03-24T21:00:37Z)
• Hybrid Discriminative Attribute-Object Embedding Network for Compositional Zero-Shot Learning [83.10178754323955]
  Hybrid Discriminative Attribute-Object Embedding (HDA-OE) network is proposed to solve the problem of complex interactions between attributes and object visual representations.<n>To increase the variability of training data, HDA-OE introduces an attribute-driven data synthesis (ADDS) module.<n>To further improve the discriminative ability of the model, HDA-OE introduces the subclass-driven discriminative embedding (SDDE) module.<n>The proposed model has been evaluated on three benchmark datasets, and the results verify its effectiveness and reliability.
  arXiv  Detail & Related papers  (2024-11-28T09:50:25Z)
• CASA: Class-Agnostic Shared Attributes in Vision-Language Models for Efficient Incremental Object Detection [30.286598189230396]
  Class-Agnostic Shared Attribute Base encourages the model to learn category-agnostic attributes shared across incremental classes.<n>For subsequent tasks, the retained attributes are frozen, and new attributes are selected from the remaining candidates.<n>Experiments on the COCO dataset demonstrate the state-of-the-art performance of our method.
  arXiv  Detail & Related papers  (2024-10-08T08:36:12Z)
• HA-FGOVD: Highlighting Fine-grained Attributes via Explicit Linear Composition for Open-Vocabulary Object Detection [11.792370846774133]
  We propose a universal and explicit approach for frozen mainstream OVD models that boosts their attribute-level detection capabilities. Our proposed method uniformly improves fine-grained attribute-level OVD of various mainstream models and achieves new state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-09-24T14:43:14Z)
• Improving Object Detection and Attribute Recognition by Feature Entanglement Reduction [26.20319853343761]
  We show that object detection should be attribute-independent and attributes be largely object-independent. We disentangle them by the use of a two-stream model where the category and attribute features are computed independently but the classification heads share Regions of Interest (RoIs) Compared with a traditional single-stream model, our model shows significant improvements over VG-20, a subset of Visual Genome, on both supervised and attribute transfer tasks.
  arXiv  Detail & Related papers  (2021-08-25T22:27:06Z)
• Disentangled Face Attribute Editing via Instance-Aware Latent Space Search [30.17338705964925]
  A rich set of semantic directions exist in the latent space of Generative Adversarial Networks (GANs) Existing methods may suffer poor attribute variation disentanglement, leading to unwanted change of other attributes when altering the desired one. We propose a novel framework (IALS) that performs Instance-Aware Latent-Space Search to find semantic directions for disentangled attribute editing.
  arXiv  Detail & Related papers  (2021-05-26T16:19:08Z)
• Attribute-based Regularization of Latent Spaces for Variational Auto-Encoders [79.68916470119743]
  We present a novel method to structure the latent space of a Variational Auto-Encoder (VAE) to encode different continuous-valued attributes explicitly. This is accomplished by using an attribute regularization loss which enforces a monotonic relationship between the attribute values and the latent code of the dimension along which the attribute is to be encoded.
  arXiv  Detail & Related papers  (2020-04-11T20:53:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.