Rethinking Prototype-based Similarity Learning for Few-Shot Object Detection

• URL: http://arxiv.org/abs/2606.23069v2
• Date: Mon, 29 Jun 2026 08:16:30 GMT
• Title: Rethinking Prototype-based Similarity Learning for Few-Shot Object Detection
• Abstract summary: Few-shot object detection aims to detect novel object categories from only a few labeled examples, avoiding costly large-scale annotation.<n>Recent prototype-based similarity learning approaches enable training-free adaptation by matching query features with class prototypes.<n>We introduce two complementary components: Text-Anchored Semantic Mask and Stage-Aligned Hierarchical Autoregressive Regression.
• Score: 3.405768252883924
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Few-shot object detection aims to detect novel object categories from only a few labeled examples, avoiding costly large-scale annotation. Recent prototype-based similarity learning approaches enable training-free adaptation by matching query features with class prototypes. However, they suffer from two fundamental limitations: (i) class confusion arising from inter-class similarity margin collapse, and (ii) insufficient visual cues for precise localization, as similarity scores capture only class-level semantic affinity while providing limited spatial information. To address these issues, we introduce two complementary components. Text-Anchored Semantic Mask (TSMa) leverages class-level text features as semantic anchors to identify semantically aligned channels through channel-wise interaction between visual and text features. By suppressing style-induced spurious responses and emphasizing class-intrinsic signals, TSMa enlarges inter-class similarity margins and mitigates class confusion. We further propose Stage-Aligned Hierarchical Autoregressive Regression (SHARe), which reformulates localization as a hierarchical autoregressive process that progressively refines bounding boxes across multiple stages. SHARe leverages the layer-wise characteristics of ViT representations by aligning feature abstraction levels with regression stages: deeper layers guide early coarse localization, while shallower layers rich in edge and texture cues refine spatial details in later stages. Experiments on COCO demonstrate a new state of the art, outperforming the previous best by +10.1 nAP, with extensive analysis validating each component. The code is available at https://github.com/VisualScienceLab-KHU/ReSet.

Related papers

• SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking [89.43370214059955]
  Open-vocabulary Multiple Object Tracking (MOT) aims to generalize trackers to novel categories not in the training set. We present a unified framework that jointly considers semantics, location, and appearance priors in the early steps of association. Our method eliminates complex post-processings for fusing different cues and boosts the association performance significantly for large-scale open-vocabulary tracking.
  arXiv  Detail & Related papers  (2024-09-17T14:36:58Z)
• Semantic Enhanced Few-shot Object Detection [37.715912401900745]
  We propose a fine-tuning based FSOD framework that utilizes semantic embeddings for better detection. Our method allows each novel class to construct a compact feature space without being confused with similar base classes.
  arXiv  Detail & Related papers  (2024-06-19T12:40:55Z)
• Distinguishability Calibration to In-Context Learning [31.375797763897104]
  We propose a method to map a PLM-encoded embedding into a new metric space to guarantee the distinguishability of the resulting embeddings. We also take the advantage of hyperbolic embeddings to capture the hierarchical relations among fine-grained class-associated token embedding.
  arXiv  Detail & Related papers  (2023-02-13T09:15:00Z)
• GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learning [55.79997930181418]
  Generalized Zero-Shot Learning aims to recognize images from both the seen and unseen classes by transferring semantic knowledge from seen to unseen classes. It is a promising solution to take the advantage of generative models to hallucinate realistic unseen samples based on the knowledge learned from the seen classes. We propose a novel flow-based generative framework that consists of multiple conditional affine coupling layers for learning unseen data generation.
  arXiv  Detail & Related papers  (2022-07-05T04:04:37Z)
• Dual Prototypical Contrastive Learning for Few-shot Semantic Segmentation [55.339405417090084]
  We propose a dual prototypical contrastive learning approach tailored to the few-shot semantic segmentation (FSS) task. The main idea is to encourage the prototypes more discriminative by increasing inter-class distance while reducing intra-class distance in prototype feature space. We demonstrate that the proposed dual contrastive learning approach outperforms state-of-the-art FSS methods on PASCAL-5i and COCO-20i datasets.
  arXiv  Detail & Related papers  (2021-11-09T08:14:50Z)
• Mitigating Generation Shifts for Generalized Zero-Shot Learning [52.98182124310114]
  Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic information (e.g., attributes) to recognize the seen and unseen samples, where unseen classes are not observable during training. We propose a novel Generation Shifts Mitigating Flow framework for learning unseen data synthesis efficiently and effectively. Experimental results demonstrate that GSMFlow achieves state-of-the-art recognition performance in both conventional and generalized zero-shot settings.
  arXiv  Detail & Related papers  (2021-07-07T11:43:59Z)
• Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation [66.85202434812942]
  We reformulate few-shot segmentation as a semantic reconstruction problem. We convert base class features into a series of basis vectors which span a class-level semantic space for novel class reconstruction. Our proposed approach, referred to as anti-aliasing semantic reconstruction (ASR), provides a systematic yet interpretable solution for few-shot learning problems.
  arXiv  Detail & Related papers  (2021-06-01T02:17:36Z)
• Isometric Propagation Network for Generalized Zero-shot Learning [72.02404519815663]
  A popular strategy is to learn a mapping between the semantic space of class attributes and the visual space of images based on the seen classes and their data. We propose Isometric propagation Network (IPN), which learns to strengthen the relation between classes within each space and align the class dependency in the two spaces. IPN achieves state-of-the-art performance on three popular Zero-shot learning benchmarks.
  arXiv  Detail & Related papers  (2021-02-03T12:45:38Z)

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.