paper-with-me

홈 › Papers

Coarse2Fine: A Two-stage Training Method for Fine-grained Visual Classification

2019-09-06 · Amir Erfan Eshratifar, David Eigen, Michael Gormish, Massoud Pedram

Small inter-class and large intra-class variations are the main challenges in fine-grained visual classification. Objects from different classes share visually similar structures and objects in the same class can have different poses and viewpoints. Therefore, the proper extraction of discriminative local features (e.g. bird's beak or car's headlight) is crucial. Most of the recent successes on this problem are based upon the attention models which can localize and attend the local discriminative objects parts. In this work, we propose a training method for visual attention networks, Coarse2Fine, which creates a differentiable path from the input space to the attended feature maps. Coarse2Fine learns an inverse mapping function from the attended feature maps to the informative regions in the raw image, which will guide the attention maps to better attend the fine-grained features. We show Coarse2Fine and orthogonal initialization of the attention weights can surpass the state-of-the-art accuracies on common fine-grained classification tasks.

📄 PDF Abstract BibTeX arXiv:1909.02680

Code (0)

등록된 구현이 없습니다.

Tasks

Fine-Grained Image ClassificationGeneral ClassificationVocal Bursts Valence Prediction

Similar Papers 제목 키워드 기반

From Incomplete Coarse-Grained to Complete Fine-Grained: A Two-Stage Framework for Spatiotemporal Data Reconstruction

2024-10-05 · Ziyu Sun, Haoyang Su, En Wang, Funing Yang 외

With the rapid development of various sensing devices, spatiotemporal data is becoming increasingly important nowadays. However, due to sensing costs and privacy concerns, the collected data is often incomplete and coars…

Denoising

PL-Net: Progressive Learning Network for Medical Image Segmentation

2021-10-27 · Junlong Cheng, Chengrui Gao, Hongchun Lu, Zhangqiang Ming 외

In recent years, segmentation methods based on deep convolutional neural networks (CNNs) have made state-of-the-art achievements for many medical analysis tasks. However, most of these approaches improve performance by o…

Image SegmentationMedical Image AnalysisMedical Image SegmentationSegmentation+1

Direct Depth Learning Network for Stereo Matching

2020-12-10 · Hong Zhang, Haojie Li, Shenglun Chen, Tiantian Yan 외

Being a crucial task of autonomous driving, Stereo matching has made great progress in recent years. Existing stereo matching methods estimate disparity instead of depth. They treat the disparity errors as the evaluation…

Autonomous DrivingDepth EstimationStereo Matching

Improving Few-shot and Zero-shot Entity Linking with Coarse-to-Fine Lexicon-based Retriever

2023-08-07 · Shijue Huang, Bingbing Wang, Libo Qin, Qin Zhao 외

Few-shot and zero-shot entity linking focus on the tail and emerging entities, which are more challenging but closer to real-world scenarios. The mainstream method is the ''retrieve and rerank'' two-stage framework. In t…

Entity LinkingRetrieval

Hierarchical Structured Model for Fine-to-coarse Manifesto Text Analysis

2018-05-08 · NAACL 2018 6 · Shivashankar Subramanian, Trevor Cohn, Timothy Baldwin

Election manifestos document the intentions, motives, and views of political parties. They are often used for analysing a party's fine-grained position on a particular issue, as well as for coarse-grained positioning of …

Position