Focus Longer to See Better:Recursively Refined Attention for Fine-Grained Image Classification
Deep Neural Network has shown great strides in the coarse-grained image classification task. It was in part due to its strong ability to extract discriminative feature representations from the images. However, the marginal visual difference between different classes in fine-grained images makes this very task harder. In this paper, we tried to focus on these marginal differences to extract more representative features. Similar to human vision, our network repetitively focuses on parts of images to spot small discriminative parts among the classes. Moreover, we show through interpretability techniques how our network focus changes from coarse to fine details. Through our experiments, we also show that a simple attention model can aggregate (weighted) these finer details to focus on the most dominant discriminative part of the image. Our network uses only image-level labels and does not need bounding box/part annotation information. Further, the simplicity of our network makes it an easy plug-n-play module. Apart from providing interpretability, our network boosts the performance (up to 2%) when compared to its baseline counterparts. Our codebase is available at https://github.com/TAMU-VITA/Focus-Longer-to-See-Better
Code (1)
Tasks
Fine-Grained Image ClassificationGeneral Classificationimage-classificationImage ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Development of spatial suppression surrounding the focus of visual attention
The capacity to filter out irrelevant information from our environment is critical to efficient processing. Yet, during development, when building a knowledge base of the world is occurring, the ability to selectively al…
RDRN: Recursively Defined Residual Network for Image Super-Resolution
Deep convolutional neural networks (CNNs) have obtained remarkable performance in single image super-resolution (SISR). However, very deep networks can suffer from training difficulty and hardly achieve further performan…
Image Super-ResolutionSuper-ResolutionRecursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing
Within the field of instance segmentation, most of the state-of-the-art deep learning networks rely nowadays on cascade architectures, where multiple object detectors are trained sequentially, re-sampling the ground trut…
Instance SegmentationObject DetectionSemantic SegmentationHierarchically-Refined Label Attention Network for Sequence Labeling
CRF has been used as a powerful model for statistical sequence labeling. For neural sequence labeling, however, BiLSTM-CRF does not always lead to better results compared with BiLSTM-softmax local classification. This ca…
CCG SupertaggingNamed Entity Recognition (NER)NERPart-Of-Speech Tagging+2Recursive Agent Optimization
We introduce Recursive Agent Optimization (RAO), a reinforcement learning approach for training recursive agents: agents that can spawn and delegate sub-tasks to new instantiations of themselves recursively. Recursive ag…
Reinforcement Learning