GCAM: Gaussian and causal-attention model of food fine-grained recognition
This addresses fine-grained recognition challenges in food classification, which is important for applications like dietary tracking or food logging, but it appears incremental as it builds on existing attention and feature extraction methods.
The paper tackles the problem of distinguishing visually similar food samples in fine-grained recognition by proposing GCAM, a Gaussian and causal-attention model that enhances feature mapping and uses counterfactual reasoning to improve attention weights, achieving state-of-the-art performance on four datasets including ETH-FOOD101, UECFOOD256, Vireo-FOOD172, and CUB-200.
Currently, most food recognition relies on deep learning for category classification. However, these approaches struggle to effectively distinguish between visually similar food samples, highlighting the pressing need to address fine-grained issues in food recognition. To mitigate these challenges, we propose the adoption of a Gaussian and causal-attention model for fine-grained object recognition.In particular, we train to obtain Gaussian features over target regions, followed by the extraction of fine-grained features from the objects, thereby enhancing the feature mapping capabilities of the target regions. To counteract data drift resulting from uneven data distributions, we employ a counterfactual reasoning approach. By using counterfactual interventions, we analyze the impact of the learned image attention mechanism on network predictions, enabling the network to acquire more useful attention weights for fine-grained image recognition. Finally, we design a learnable loss strategy to balance training stability across various modules, ultimately improving the accuracy of the final target recognition. We validate our approach on four relevant datasets, demonstrating its excellent performance across these four datasets.We experimentally show that GCAM surpasses state-of-the-art methods on the ETH-FOOD101, UECFOOD256, and Vireo-FOOD172 datasets. Furthermore, our approach also achieves state-of-the-art performance on the CUB-200 dataset.