GFT: Gradient Focal Transformer

• URL: http://arxiv.org/abs/2504.09852v1
• Date: Mon, 14 Apr 2025 03:49:06 GMT
• Title: GFT: Gradient Focal Transformer
• Authors: Boris Kriuk, Simranjit Kaur Gill, Shoaib Aslam, Amir Fakhrutdinov,
• Abstract summary: This paper introduces GFT (Gradient Focal Transformer), a new ViT-derived framework created for Fine-Grained Image Classification tasks.<n>GFT integrates the Gradient Attention Learning Alignment (GALA) mechanism to dynamically prioritize class-discriminative features.<n>GFT achieves SOTA accuracy on FGVC Aircraft, Food-101, and datasets with 93M parameters, outperforming ViT-based advanced FGIC models in efficiency.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fine-Grained Image Classification (FGIC) remains a complex task in computer vision, as it requires models to distinguish between categories with subtle localized visual differences. Well-studied CNN-based models, while strong in local feature extraction, often fail to capture the global context required for fine-grained recognition, while more recent ViT-backboned models address FGIC with attention-driven mechanisms but lack the ability to adaptively focus on truly discriminative regions. TransFG and other ViT-based extensions introduced part-aware token selection to enhance attention localization, yet they still struggle with computational efficiency, attention region selection flexibility, and detail-focus narrative in complex environments. This paper introduces GFT (Gradient Focal Transformer), a new ViT-derived framework created for FGIC tasks. GFT integrates the Gradient Attention Learning Alignment (GALA) mechanism to dynamically prioritize class-discriminative features by analyzing attention gradient flow. Coupled with a Progressive Patch Selection (PPS) strategy, the model progressively filters out less informative regions, reducing computational overhead while enhancing sensitivity to fine details. GFT achieves SOTA accuracy on FGVC Aircraft, Food-101, and COCO datasets with 93M parameters, outperforming ViT-based advanced FGIC models in efficiency. By bridging global context and localized detail extraction, GFT sets a new benchmark in fine-grained recognition, offering interpretable solutions for real-world deployment scenarios.

Related papers

• Point Cloud Understanding via Attention-Driven Contrastive Learning [64.65145700121442]
  Transformer-based models have advanced point cloud understanding by leveraging self-attention mechanisms. PointACL is an attention-driven contrastive learning framework designed to address these limitations. Our method employs an attention-driven dynamic masking strategy that guides the model to focus on under-attended regions.
  arXiv  Detail & Related papers  (2024-11-22T05:41:00Z)
• ELGC-Net: Efficient Local-Global Context Aggregation for Remote Sensing Change Detection [65.59969454655996]
  We propose an efficient change detection framework, ELGC-Net, which leverages rich contextual information to precisely estimate change regions. Our proposed ELGC-Net sets a new state-of-the-art performance in remote sensing change detection benchmarks. We also introduce ELGC-Net-LW, a lighter variant with significantly reduced computational complexity, suitable for resource-constrained settings.
  arXiv  Detail & Related papers  (2024-03-26T17:46:25Z)
• GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning [84.54244771470012]
  Source-Free Universal Domain Adaptation (SF-UniDA) aims to accurately classify "known" data belonging to common categories. We propose a novel Global and Local Clustering (GLC) technique, which comprises an adaptive one-vs-all global clustering algorithm. We evolve GLC to GLC++, integrating a contrastive affinity learning strategy.
  arXiv  Detail & Related papers  (2024-03-21T13:57:45Z)
• Leveraging Swin Transformer for Local-to-Global Weakly Supervised Semantic Segmentation [12.103012959947055]
  This work explores the use of Swin Transformer by proposing "SWTformer" to enhance the accuracy of the initial seed CAMs. SWTformer-V1 achieves a 0.98% mAP higher localization accuracy, outperforming state-of-the-art models. SWTformer-V2 incorporates a multi-scale feature fusion mechanism to extract additional information.
  arXiv  Detail & Related papers  (2024-01-31T13:41:17Z)
• ASWT-SGNN: Adaptive Spectral Wavelet Transform-based Self-Supervised Graph Neural Network [20.924559944655392]
  This paper proposes an Adaptive Spectral Wavelet Transform-based Self-Supervised Graph Neural Network (ASWT-SGNN) ASWT-SGNN accurately approximates the filter function in high-density spectral regions, avoiding costly eigen-decomposition. It achieves comparable performance to state-of-the-art models in node classification tasks.
  arXiv  Detail & Related papers  (2023-12-10T03:07:42Z)
• Hybrid Focal and Full-Range Attention Based Graph Transformers [0.0]
  We present a purely attention-based architecture, namely Focal and Full-Range Graph Transformer (FFGT) FFGT combines the conventional full-range attention with K-hop focal attention on ego-nets to aggregate both global and local information. Our approach enhances the performance of existing Graph Transformers on various open datasets.
  arXiv  Detail & Related papers  (2023-11-08T12:53:07Z)
• Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning [49.72857433721424]
  Vision Transformers (ViT) and Visual Prompt Tuning (VPT) achieve state-of-the-art performance with improved efficiency in various computer vision tasks. We present a novel algorithm, SGPT, that integrates Generalized FL (GFL) and Personalized FL (PFL) approaches by employing a unique combination of both shared and group-specific prompts.
  arXiv  Detail & Related papers  (2023-10-27T17:22:09Z)
• Salient Mask-Guided Vision Transformer for Fine-Grained Classification [48.1425692047256]
  Fine-grained visual classification (FGVC) is a challenging computer vision problem. One of its main difficulties is capturing the most discriminative inter-class variances. We introduce a simple yet effective Salient Mask-Guided Vision Transformer (SM-ViT)
  arXiv  Detail & Related papers  (2023-05-11T19:24:33Z)
• Feature Fusion Vision Transformer for Fine-Grained Visual Categorization [22.91753200323264]
  We propose a novel pure transformer-based framework Feature Fusion Vision Transformer (FFVT) We aggregate the important tokens from each transformer layer to compensate the local, low-level and middle-level information. We design a novel token selection mod-ule called mutual attention weight selection (MAWS) to guide the network effectively and efficiently towards selecting discriminative tokens.
  arXiv  Detail & Related papers  (2021-07-06T01:48:43Z)
• Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning [85.6386289476598]
  We develop a novel adversarial graph representation adaptation (AGRA) framework for cross-domain holistic-local feature co-adaptation. We conduct extensive and fair evaluations on several popular benchmarks and show that the proposed AGRA framework outperforms previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-08-03T15:00:31Z)

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.