Learning to Align Generative Appearance Priors for Fine-grained Image Retrieval

• URL: http://arxiv.org/abs/2605.09859v1
• Date: Mon, 11 May 2026 01:35:26 GMT
• Title: Learning to Align Generative Appearance Priors for Fine-grained Image Retrieval
• Abstract summary: GAPan is an alignment network that reformulates the learning objective from category prediction toward appearance modeling.<n>We show that GAPan achieves state-of-the-art performance on both widely-used fine- and coarse-grained benchmarks.
• Score: 54.09324791167742
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fine-grained image retrieval (FGIR) typically relies on supervision from seen categories to learn discriminative embeddings for retrieving unseen categories. However, such supervision often biases retrieval models toward the semantics of seen categories rather than the underlying appearance characteristics that generalize across categories, thereby limiting retrieval performance on unseen categories. To tackle this, we propose GAPan, a Generative Appearance Prior alignment network that reformulates the learning objective from category prediction toward appearance modeling. Technically, GAPan treats retrieval features with an invertible density model based on normalizing flows. In the forward direction, the flow maps all instance features into a latent density space, where each seen category is modeled by a class-conditional Gaussian prior and optimized via exact likelihood estimation. This formulation preserves richer appearance details by leveraging the invertible property of the flows. In the reverse direction, samples from the high-density regions of these learned priors are mapped back to the feature space to produce appearance-aware anchors that reflect intra-category variation. These anchors supervise a prior-driven alignment objective that aligns retrieval embeddings with category-specific appearance distributions, thereby improving generalization to unseen categories. Evaluations demonstrate that our GAPan achieves state-of-the-art performance on both widely-used fine- and coarse-grained benchmarks.

Related papers

• Rethinking Global Average Pooling: Your Classifier Is Secretly a Multi-Instance Learner [0.0]
  Modern image classifiers widely adopt global average pooling (GAP) followed by a linear classification head.<n>This linearity ensures that the image-level logits equal the average of logits obtained by applying the classification head pointwise to the feature grid prior to GAP.<n>This structure naturally suggests a multiple-instance learning (MIL) interpretation, where an image is viewed as a bag of spatial instances.
  arXiv  Detail & Related papers  (2026-06-12T15:35:05Z)
• Adversarial Reconstruction Feedback for Robust Fine-grained Generalization [29.202222418152285]
  AdvRF is a novel adversarial reconstruction feedback framework for learning category-agnostic discrepancy representations.<n>It reformulates FGIR as a visual discrepancy reconstruction task via synergizing category-aware discrepancy localization from retrieval models.<n>It achieves impressive performance on both widely-used fine-grained and coarse-grained datasets.
  arXiv  Detail & Related papers  (2025-07-29T12:20:03Z)
• Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery [49.1865089933055]
  We propose a novel, efficient and self-supervised method capable of discovering previously unknown categories at test time. A salient feature of our approach is the assignment of minimum length category codes to individual data instances. Experimental evaluations, bolstered by state-of-the-art benchmark comparisons, testify to the efficacy of our solution.
  arXiv  Detail & Related papers  (2023-10-30T17:45:32Z)
• Parametric Classification for Generalized Category Discovery: A Baseline Study [70.73212959385387]
  Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples. We investigate the failure of parametric classifiers, verify the effectiveness of previous design choices when high-quality supervision is available, and identify unreliable pseudo-labels as a key problem. We propose a simple yet effective parametric classification method that benefits from entropy regularisation, achieves state-of-the-art performance on multiple GCD benchmarks and shows strong robustness to unknown class numbers.
  arXiv  Detail & Related papers  (2022-11-21T18:47:11Z)
• Fine-grained Retrieval Prompt Tuning [149.9071858259279]
  Fine-grained Retrieval Prompt Tuning steers a frozen pre-trained model to perform the fine-grained retrieval task from the perspectives of sample prompt and feature adaptation. Our FRPT with fewer learnable parameters achieves the state-of-the-art performance on three widely-used fine-grained datasets.
  arXiv  Detail & Related papers  (2022-07-29T04:10:04Z)
• Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification [17.08583412899347]
  Real-world data often follows a long-tailed distribution, which makes the performance of existing classification algorithms degrade heavily. We propose a novel reasoning-based implicit semantic data augmentation method to borrow transformation directions from other classes. Experimental results on CIFAR-100-LT, ImageNet-LT, and iNaturalist 2018 have demonstrated the effectiveness of our proposed method.
  arXiv  Detail & Related papers  (2021-12-15T07:14:39Z)
• On Clustering Categories of Categorical Predictors in Generalized Linear Models [0.0]
  We propose a method to reduce the complexity of Generalized Linear Models in the presence of categorical predictors. The traditional one-hot encoding, where each category is represented by a dummy variable, can be wasteful, difficult to interpret, and prone to overfitting. This paper addresses these challenges by finding a reduced representation of the categorical predictors by clustering their categories.
  arXiv  Detail & Related papers  (2021-10-19T15:36:35Z)
• Towards Novel Target Discovery Through Open-Set Domain Adaptation [73.81537683043206]
  Open-set domain adaptation (OSDA) considers that the target domain contains samples from novel categories unobserved in external source domain. We propose a novel framework to accurately identify the seen categories in target domain, and effectively recover the semantic attributes for unseen categories.
  arXiv  Detail & Related papers  (2021-05-06T04:22:29Z)
• MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection [80.24165350584502]
  We propose Memory Guided Attention for Category-Aware Domain Adaptation. The proposed method consists of employing category-wise discriminators to ensure category-aware feature alignment. The method is evaluated on several benchmark datasets and is shown to outperform existing approaches.
  arXiv  Detail & Related papers  (2021-03-07T01:08:21Z)

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.