Saccadic Vision for Fine-Grained Visual Classification

• URL: http://arxiv.org/abs/2509.15688v1
• Date: Fri, 19 Sep 2025 07:03:37 GMT
• Title: Saccadic Vision for Fine-Grained Visual Classification
• Authors: Johann Schmidt, Sebastian Stober, Joachim Denzler, Paul Bodesheim,
• Abstract summary: Fine-grained visual classification (FGVC) requires distinguishing between visually similar categories through subtle, localized features.<n>Existing part-based methods rely on complex localization networks that learn mappings from pixel to sample space.<n>We propose a two-stage process that first extracts peripheral features and generates a sample map.<n>We employ contextualized selective attention to weigh the impact of each fixation patch before fusing peripheral and focus representations.
• Score: 10.681604440788854
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Fine-grained visual classification (FGVC) requires distinguishing between visually similar categories through subtle, localized features - a task that remains challenging due to high intra-class variability and limited inter-class differences. Existing part-based methods often rely on complex localization networks that learn mappings from pixel to sample space, requiring a deep understanding of image content while limiting feature utility for downstream tasks. In addition, sampled points frequently suffer from high spatial redundancy, making it difficult to quantify the optimal number of required parts. Inspired by human saccadic vision, we propose a two-stage process that first extracts peripheral features (coarse view) and generates a sample map, from which fixation patches are sampled and encoded in parallel using a weight-shared encoder. We employ contextualized selective attention to weigh the impact of each fixation patch before fusing peripheral and focus representations. To prevent spatial collapse - a common issue in part-based methods - we utilize non-maximum suppression during fixation sampling to eliminate redundancy. Comprehensive evaluation on standard FGVC benchmarks (CUB-200-2011, NABirds, Food-101 and Stanford-Dogs) and challenging insect datasets (EU-Moths, Ecuador-Moths and AMI-Moths) demonstrates that our method achieves comparable performance to state-of-the-art approaches while consistently outperforming our baseline encoder.

Related papers

• PromptMAD: Cross-Modal Prompting for Multi-Class Visual Anomaly Localization [9.018570847586878]
  We propose PromptMAD, a cross-modal prompting framework for unsupervised visual anomaly detection and localization.<n>Our method enriches visual reconstruction with semantic context, improving the detection of subtle and textural anomalies.<n>Our architecture also includes a supervised segmentor that fuses multi-scale convolutional features with Transformer-based spatial attention.
  arXiv  Detail & Related papers  (2026-01-30T03:04:06Z)
• Beyond Frequency: Seeing Subtle Cues Through the Lens of Spatial Decomposition for Fine-Grained Visual Classification [8.936378000130812]
  We propose Subtle-Cue Oriented Perception Engine (SCOPE), which adaptively enhances the representational capability of low-level details and high-level semantics in the spatial domain.<n>SCOPE achieves new state-of-the-art on four popular fine-grained image classification benchmarks.
  arXiv  Detail & Related papers  (2025-08-09T12:13:40Z)
• Fine-grained Recognition with Learnable Semantic Data Augmentation [68.48892326854494]
  Fine-grained image recognition is a longstanding computer vision challenge. We propose diversifying the training data at the feature-level to alleviate the discriminative region loss problem. Our method significantly improves the generalization performance on several popular classification networks.
  arXiv  Detail & Related papers  (2023-09-01T11:15:50Z)
• Frequency Perception Network for Camouflaged Object Detection [51.26386921922031]
  We propose a novel learnable and separable frequency perception mechanism driven by the semantic hierarchy in the frequency domain.<n>Our entire network adopts a two-stage model, including a frequency-guided coarse localization stage and a detail-preserving fine localization stage.<n>Compared with the currently existing models, our proposed method achieves competitive performance in three popular benchmark datasets.
  arXiv  Detail & Related papers  (2023-08-17T11:30:46Z)
• Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment [53.401889855278704]
  Few-shot fine-grained recognition (FS-FGR) aims to recognize novel fine-grained categories with the help of limited available samples. We propose a two-stage background suppression and foreground alignment framework, which is composed of a background activation suppression (BAS) module, a foreground object alignment (FOA) module, and a local to local (L2L) similarity metric. Experiments conducted on multiple popular fine-grained benchmarks demonstrate that our method outperforms the existing state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2022-10-04T07:54:40Z)
• Multi-scale and Cross-scale Contrastive Learning for Semantic Segmentation [5.281694565226513]
  We apply contrastive learning to enhance the discriminative power of the multi-scale features extracted by semantic segmentation networks. By first mapping the encoder's multi-scale representations to a common feature space, we instantiate a novel form of supervised local-global constraint.
  arXiv  Detail & Related papers  (2022-03-25T01:24:24Z)
• MC-LCR: Multi-modal contrastive classification by locally correlated representations for effective face forgery detection [11.124150983521158]
  We propose a novel framework named Multi-modal Contrastive Classification by Locally Correlated Representations. Our MC-LCR aims to amplify implicit local discrepancies between authentic and forged faces from both spatial and frequency domains. We achieve state-of-the-art performance and demonstrate the robustness and generalization of our method.
  arXiv  Detail & Related papers  (2021-10-07T09:24:12Z)
• Mask-Guided Feature Extraction and Augmentation for Ultra-Fine-Grained Visual Categorization [15.627971638835948]
  The Ultra-fine-grained visual categorization (Ultra-FGVC) problems have been understudied. FGVC aims at classifying objects from the same species, while the Ultra-FGVC targets at more challenging problems of classifying images at an ultra-fine granularity. The challenges for Ultra-FGVC mainly comes from two aspects: one is that the Ultra-FGVC often arises overfitting problems due to the lack of training samples. A mask-guided feature extraction and feature augmentation method is proposed in this paper to extract discriminative and informative regions of images.
  arXiv  Detail & Related papers  (2021-09-16T06:57:05Z)
• Adversarial Feature Augmentation and Normalization for Visual Recognition [109.6834687220478]
  Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings. We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
  arXiv  Detail & Related papers  (2021-03-22T20:36:34Z)
• Generative Partial Visual-Tactile Fused Object Clustering [81.17645983141773]
  We propose a Generative Partial Visual-Tactile Fused (i.e., GPVTF) framework for object clustering. A conditional cross-modal clustering generative adversarial network is then developed to synthesize one modality conditioning on the other modality. To the end, two pseudo-label based KL-divergence losses are employed to update the corresponding modality-specific encoders.
  arXiv  Detail & Related papers  (2020-12-28T02:37:03Z)
• Image Fine-grained Inpainting [89.17316318927621]
  We present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields. To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss. We also employ a discriminator with local and global branches to ensure local-global contents consistency.
  arXiv  Detail & Related papers  (2020-02-07T03:45:25Z)

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.