# DVF: Advancing Robust and Accurate Fine-Grained Image Retrieval with Retrieval Guidelines

arXiv: https://arxiv.org/abs/2404.15771 · HTML: https://mlsanity.com/paper/2404.15771/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 49 references that are in the map.
- First posted on arXiv 24 Apr 2024.

## Builds on (most cited first, 25 of 25)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [DeiT III: Revenge of the ViT](https://mlsanity.com/paper/2204.07118/) (2022)
- [No Fuss Distance Metric Learning using Proxies](https://mlsanity.com/paper/1703.07464/) (2017)
- [Open-Vocabulary DETR with Conditional Matching](https://mlsanity.com/paper/2203.11876/) (2022)
- [Proxy Anchor Loss for Deep Metric Learning](https://mlsanity.com/paper/2003.13911/) (2020)
- [Hyperbolic Vision Transformers: Combining Improvements in Metric Learning](https://mlsanity.com/paper/2203.10833/) (2022)
- [ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis](https://mlsanity.com/paper/2004.01113/) (2020)
- [A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses](https://mlsanity.com/paper/2003.08983/) (2020)
- [Bird Species Categorization Using Pose Normalized Deep Convolutional Nets](https://mlsanity.com/paper/1406.2952/) (2014)
- [Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval](https://mlsanity.com/paper/1604.04994/) (2016)
- [Learning Intra-Batch Connections for Deep Metric Learning](https://mlsanity.com/paper/2102.07753/) (2021)
- [M3Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition](https://mlsanity.com/paper/2308.03063/) (2023)
- [Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment](https://mlsanity.com/paper/2210.01439/) (2022)
- [Attribute-Aware Attention Model for Fine-grained Representation Learning](https://mlsanity.com/paper/1901.00392/) (2019)
- [Learning with Memory-based Virtual Classes for Deep Metric Learning](https://mlsanity.com/paper/2103.16940/) (2021)
- [Multi-view Information Integration and Propagation for Occluded Person Re-identification](https://mlsanity.com/paper/2311.03828/) (2023)
- [Keypoint-Aligned Embeddings for Image Retrieval and Re-identification](https://mlsanity.com/paper/2008.11368/) (2020)
- [Delving into Multimodal Prompting for Fine-grained Visual Classification](https://mlsanity.com/paper/2309.08912/) (2023)
- [Fine-grained Retrieval Prompt Tuning](https://mlsanity.com/paper/2207.14465/) (2022)
- [Learning Contrastive Self-Distillation for Ultra-Fine-Grained Visual Categorization Targeting Limited Samples](https://mlsanity.com/paper/2311.06056/) (2023)

## Built on by (most cited first, 6 of 6)

- [Visual Position Prompt for MLLM based Visual Grounding](https://mlsanity.com/paper/2503.15426/) (2025)
- [Fine-grained Image Retrieval via Dual-Vision Adaptation](https://mlsanity.com/paper/2506.16273/) (2025)
- [Multi-Modal Motion Retrieval by Learning a Fine-Grained Joint Embedding Space](https://mlsanity.com/paper/2507.23188/) (2025)
- [OT-DETECTOR: Delving into Optimal Transport for Zero-shot Out-of-Distribution Detection](https://mlsanity.com/paper/2503.06442/) (2025)
- [Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognition](https://mlsanity.com/paper/2504.09215/) (2025)
- [FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts](https://mlsanity.com/paper/2511.00480/) (2025)

## Abstract (arXiv)

Fine-grained image retrieval (FGIR) is to learn visual representations that distinguish visually similar objects while maintaining generalization. Existing methods propose to generate discriminative features, but rarely consider the particularity of the FGIR task itself. This paper presents a meticulous analysis leading to the proposal of practical guidelines to identify subcategory-specific discrepancies and generate discriminative features to design effective FGIR models. These guidelines include emphasizing the object (G1), highlighting subcategory-specific discrepancies (G2), and employing effective training strategy (G3). Following G1 and G2, we design a novel Dual Visual Filtering mechanism for the plain visual transformer, denoted as DVF, to capture subcategory-specific discrepancies. Specifically, the dual visual filtering mechanism comprises an object-oriented module and a semantic-oriented module. These components serve to magnify objects and identify discriminative regions, respectively. Following G3, we implement a discriminative model training strategy to improve the discriminability and generalization ability of DVF. Extensive analysis and ablation studies confirm the efficacy of our proposed guidelines. Without bells and whistles, the proposed DVF achieves state-of-the-art performance on three widely-used fine-grained datasets in closed-set and open-set settings.