InfoTaxa: Information-Calibrated Label-Free Clustering for Fine-Grained Visual Taxonomy

• URL: http://arxiv.org/abs/2609.17218v1
• Date: Tue, 15 Sep 2026 14:03:52 GMT
• Title: InfoTaxa: Information-Calibrated Label-Free Clustering for Fine-Grained Visual Taxonomy
• Abstract summary: Image-only fine-grained taxonomy exhibits a consistent coarse-to-fine failure mode.<n>We study this behaviour on BIOSCAN-5M through an information-calibrated clustering analysis.
• Score: 17.572363828337476
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Label-free clustering of frozen pretrained visual embeddings offers a scalable route to biodiversity monitoring, but image-only fine-grained taxonomy exhibits a consistent coarse-to-fine failure mode: clusters recover broad taxonomic structure yet plateau at species level. We study this behaviour on BIOSCAN-5M through an information-calibrated clustering analysis. BioCLIP~2 features with UMAP and HDBSCAN reach $0.79$ AMI at family and $0.67$ at genus, substantially improving over the prior image baseline and remaining competitive with oracle-$K$, graph-based, and learned clustering heads on the same frozen features. To diagnose whether the remaining plateau is method-limited or information-limited, we introduce InfoTaxa, which combines clustering efficiency---the fraction of probe-estimated image information recovered by an unsupervised partition---with paired DNA as an audit signal only, not an inference input. The density pipeline recovers approximately $0.90$ and $0.81$ of the image-available information at order and family, respectively. Held-out late-fusion probes show that adding DNA to the image embedding reduces species-level prediction error by approximately two bits. Robustness analyses cover multiple image encoders, described-species and rare-class subsets, probe diagnostics, and held-out-species coarse-rank generalisation and same-species retrieval. Thus, in the tested setting, species-level label-free clustering is both clustering-limited and representation-limited: improved clustering may recover additional image-exposed structure, but cannot close the DNA-audited information gap alone.

Related papers

• Vision Transformers for Zero-Shot Clustering of Animal Images: A Comparative Benchmarking Study [0.19116784879310023]
  Manual labeling of animal images remains a significant bottleneck in ecological research.<n>This study investigates whether state-of-the-art Vision Transformer (ViT) foundation models can reduce thousands of unlabeled animal images directly to species-level clusters.
  arXiv  Detail & Related papers  (2026-02-03T08:27:22Z)
• Hierarchical Identity Learning for Unsupervised Visible-Infrared Person Re-Identification [81.3063589622217]
  Unsupervised visible-infrared person re-identification (USVI-ReID) aims to learn modality-invariant image features from unlabeled cross-modal person datasets.
  arXiv  Detail & Related papers  (2025-09-15T05:10:43Z)
• Disentanglement of Biological and Technical Factors via Latent Space Rotation in Clinical Imaging Improves Disease Pattern Discovery [0.4820000447145793]
  We introduce an approach to actively learn the domain shift via post-hoc rotation of the data latent space.<n>Results show that the learned disentangled representation leads to stable clusters representing tissue-types across different acquisition settings.
  arXiv  Detail & Related papers  (2025-09-14T21:16:15Z)
• DiffKillR: Killing and Recreating Diffeomorphisms for Cell Annotation in Dense Microscopy Images [105.46086313858062]
  We introduce DiffKillR, a novel framework that reframes cell annotation as the combination of archetype matching and image registration tasks.<n>DiffKillR efficiently propagates annotations across large microscopy images, reducing the need for extensive manual labeling.<n>We will discuss the theoretical properties of DiffKillR and validate it on three microscopy tasks, demonstrating its advantages over existing supervised, semi-supervised, and unsupervised methods.
  arXiv  Detail & Related papers  (2024-10-04T00:38:29Z)
• Generalized Category Discovery with Clustering Assignment Consistency [56.92546133591019]
  Generalized category discovery (GCD) is a recently proposed open-world task. We propose a co-training-based framework that encourages clustering consistency. Our method achieves state-of-the-art performance on three generic benchmarks and three fine-grained visual recognition datasets.
  arXiv  Detail & Related papers  (2023-10-30T00:32:47Z)
• Rethinking Image Forgery Detection via Soft Contrastive Learning and Unsupervised Clustering [27.495469888054032]
  Image forgery detection aims to detect and locate forged regions in an image.<n>Most existing forgery detection algorithms formulate classification problems to classify pixels into forged or pristine.<n>We propose FOrensic ContrAstive cLustering (FOCAL) method, a novel, simple yet very effective paradigm based on soft contrastive learning and unsupervised clustering.
  arXiv  Detail & Related papers  (2023-08-18T05:05:30Z)
• InfoNCE Loss Provably Learns Cluster-Preserving Representations [54.28112623495274]
  We show that the representation learned by InfoNCE with a finite number of negative samples is consistent with respect to clusters in the data. Our main result is to show that the representation learned by InfoNCE with a finite number of negative samples is also consistent with respect to clusters in the data.
  arXiv  Detail & Related papers  (2023-02-15T19:45:35Z)
• Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment [73.61888777504377]
  Full-reference (FR) image quality assessment (IQA) evaluates the visual quality of a distorted image by measuring its perceptual difference with pristine-quality reference. Unlabeled data can be easily collected from an image degradation or restoration process, making it encouraging to exploit unlabeled training data to boost FR-IQA performance. In this paper, we suggest to incorporate semi-supervised and positive-unlabeled (PU) learning for exploiting unlabeled data while mitigating the adverse effect of outliers.
  arXiv  Detail & Related papers  (2022-04-19T09:10:06Z)
• Weakly-supervised Generative Adversarial Networks for medical image classification [1.479639149658596]
  We propose a novel medical image classification algorithm called Weakly-Supervised Generative Adversarial Networks (WSGAN) WSGAN only uses a small number of real images without labels to generate fake images or mask images to enlarge the sample size of the training set. We show that WSGAN can obtain relatively high learning performance by using few labeled and unlabeled data.
  arXiv  Detail & Related papers  (2021-11-29T15:38:48Z)
• Dynamic $\beta$-VAEs for quantifying biodiversity by clustering optically recorded insect signals [0.6091702876917281]
  We propose an adaptive variant of the variational autoencoder (VAE) capable of clustering data by phylogenetic groups. We demonstrate the usefulness of the dynamic $beta$-VAE on optically recorded insect signals from regions of southern Scandinavia.
  arXiv  Detail & Related papers  (2021-02-10T16:14:13Z)
• Unsupervised Person Re-identification via Softened Similarity Learning [122.70472387837542]
  Person re-identification (re-ID) is an important topic in computer vision. This paper studies the unsupervised setting of re-ID, which does not require any labeled information. Experiments on two image-based and video-based datasets demonstrate state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-04-07T17:16:41Z)
• High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification [84.43394420267794]
  We propose a novel framework by learning high-order relation and topology information for discriminative features and robust alignment. Our framework significantly outperforms state-of-the-art by6.5%mAP scores on Occluded-Duke dataset.
  arXiv  Detail & Related papers  (2020-03-18T12:18:35Z)

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.