TreeAdapter: Hierarchical Taxonomy-Guided Adapter Composition for Fine-Grained Species Image Generation

• URL: http://arxiv.org/abs/2607.24215v1
• Date: Mon, 27 Jul 2026 09:47:55 GMT
• Title: TreeAdapter: Hierarchical Taxonomy-Guided Adapter Composition for Fine-Grained Species Image Generation
• Abstract summary: TreeAdapter is a novel framework that explicitly leverages hierarchical taxonomic data.<n>We introduce a two-stage training paradigm where ancestor adapters are optimized to model only the residual visual features unexplained by their descendants.<n>TreeAdapter achieves state-of-the-art fine-grained generation quality, outperforming both general-purpose and domain-specific baselines.
• Score: 4.373125385645128
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although general text-to-image models excel in open-domain generation, their performance degrades significantly in specialized downstream domains, particularly when generating images of rare biological species. Hindered by long-tailed distributions, general models struggle to capture subtle fine-grained details, while per-species fine-tuning methods over-isolate individual species and consequently ignore the shared visual features among closely related taxa. To address this, we propose TreeAdapter, a novel framework that explicitly leverages hierarchical taxonomic data. Rather than using a monolithic model or independent per-species modules, TreeAdapter attaches lightweight adapters to every node of the taxonomic tree. Specifically, leaf-node adapters capture species-specific visual traits, while internal-node adapters encapsulate shared semantics among descendant taxa. We introduce a two-stage training paradigm where ancestor adapters are optimized to model only the residual visual features unexplained by their descendants. This model architecture and training paradigm enable the model to fully leverage hierarchical information, ensuring the accurate generation of visual features for each species. Extensive experiments across three large-scale biodiversity benchmarks demonstrate that TreeAdapter achieves state-of-the-art fine-grained generation quality, outperforming both general-purpose and domain-specific baselines.

Related papers

• TaxaAdapter: Vision Taxonomy Models are Key to Fine-grained Image Generation over the Tree of Life [39.89855645414284]
  TaxaAdapter is a simple and lightweight approach that incorporates Vision Taxonomy Models (VTMs) to guide fine-grained species generation.<n>Our method injects VTM embeddings into a frozen text-to-image diffusion model, improving species-level fidelity.<n>Our results highlight that VTMs are a key ingredient for scalable, fine-grained species generation.
  arXiv  Detail & Related papers  (2026-03-27T07:22:43Z)
• Bridging Classical and Modern Computer Vision: PerceptiveNet for Tree Crown Semantic Segmentation [0.0]
  PerceptiveNet is a novel model incorporating a Logarithmic Gabor- parameterised convolutional layer with trainable filter parameters.<n>We investigate the impact of Log-Gabor, Gabor, and standard convolutional layers on semantic segmentation performance.<n>Our results outperform state-of-the-art models, demonstrating significant performance improvements on a tree crown dataset.
  arXiv  Detail & Related papers  (2025-05-29T16:11:08Z)
• PhyloGen: Language Model-Enhanced Phylogenetic Inference via Graph Structure Generation [50.80441546742053]
  Phylogenetic trees elucidate evolutionary relationships among species.<n>Traditional Markov Chain Monte Carlo methods face slow convergence and computational burdens.<n>We propose PhyloGen, a novel method leveraging a pre-trained genomic language model.
  arXiv  Detail & Related papers  (2024-12-25T08:33:05Z)
• Low-Biased General Annotated Dataset Generation [62.04202037186855]
  We present a low-biased general annotated dataset generation framework (lbGen)<n>Instead of expensive manual collection, we aim at directly generating low-biased images with category annotations.<n> Experimental results confirm that, compared with the manually labeled dataset or other synthetic datasets, the utilization of our generated low-biased dataset leads to stable generalization capacity enhancement.
  arXiv  Detail & Related papers  (2024-12-14T13:28:40Z)
• HeGraphAdapter: Tuning Multi-Modal Vision-Language Models with Heterogeneous Graph Adapter [19.557300178619382]
  We propose a novel Heterogeneous Graph Adapter to achieve tuning VLMs for the downstream tasks. We employ a specific Heterogeneous Graph Neural Network to excavate multi-modality structure knowledge for the downstream tasks. Experimental results on 11 benchmark datasets demonstrate the effectiveness and benefits of the proposed HeGraphAdapter.
  arXiv  Detail & Related papers  (2024-10-10T12:20:58Z)
• Tree semantic segmentation from aerial image time series [24.14827064108217]
  We perform semantic segmentation of trees using an aerial dataset image spanning over a year. We compare models trained on single images versus those trained on time series to assess the impact of tree phenology on segmentation performances. We leverage the hierarchical structure of tree species taxonomy by incorporating a custom loss function that refines predictions at three levels: species, genus, and higher-level taxa.
  arXiv  Detail & Related papers  (2024-07-18T02:19:57Z)
• Deep Visual-Genetic Biometrics for Taxonomic Classification of Rare Species [1.9819034119774483]
  We propose aligned visual-genetic inference spaces with the aim to implicitly encode cross-domain associations for improved performance. We experimentally demonstrate the efficacy of the concept via application to microscopic imagery of 30k+ planktic foraminifer shells. Visual-genetic alignment can significantly benefit visual-only recognition of the rarest species.
  arXiv  Detail & Related papers  (2023-05-11T10:04:27Z)
• Improving GANs for Long-Tailed Data through Group Spectral Regularization [51.58250647277375]
  We propose a novel group Spectral Regularizer (gSR) that prevents the spectral explosion alleviating mode collapse. We find that gSR effectively combines with existing augmentation and regularization techniques, leading to state-of-the-art image generation performance on long-tailed data.
  arXiv  Detail & Related papers  (2022-08-21T17:51:05Z)
• Epigenetic evolution of deep convolutional models [81.21462458089142]
  We build upon a previously proposed neuroevolution framework to evolve deep convolutional models. We propose a convolutional layer layout which allows kernels of different shapes and sizes to coexist within the same layer. The proposed layout enables the size and shape of individual kernels within a convolutional layer to be evolved with a corresponding new mutation operator.
  arXiv  Detail & Related papers  (2021-04-12T12:45:16Z)
• Intersection Regularization for Extracting Semantic Attributes [72.53481390411173]
  We consider the problem of supervised classification, such that the features that the network extracts match an unseen set of semantic attributes. For example, when learning to classify images of birds into species, we would like to observe the emergence of features that zoologists use to classify birds. We propose training a neural network with discrete top-level activations, which is followed by a multi-layered perceptron (MLP) and a parallel decision tree.
  arXiv  Detail & Related papers  (2021-03-22T14:32:44Z)
• Two-View Fine-grained Classification of Plant Species [66.75915278733197]
  We propose a novel method based on a two-view leaf image representation and a hierarchical classification strategy for fine-grained recognition of plant species. A deep metric based on Siamese convolutional neural networks is used to reduce the dependence on a large number of training samples and make the method scalable to new plant species.
  arXiv  Detail & Related papers  (2020-05-18T21:57:47Z)

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.