Sequential Random Network for Fine-grained Image Classification

2021-03-12 · Chaorong Li, Malu Zhang, Wei Huang, Fengqing Qin, Anping Zeng, Yuanyuan Huang

Deep Convolutional Neural Network (DCNN) and Transformer have achieved remarkable successes in image recognition. However, their performance in fine-grained image recognition is still difficult to meet the requirements of actual needs. This paper proposes a Sequence Random Network (SRN) to enhance the performance of DCNN. The output of DCNN is one-dimensional features. This one-dimensional feature abstractly represents image information, but it does not express well the detailed information of image. To address this issue, we use the proposed SRN which composed of BiLSTM and several Tanh-Dropout blocks (called BiLSTM-TDN), to further process DCNN one-dimensional features for highlighting the detail information of image. After the feature transform by BiLSTM-TDN, the recognition performance has been greatly improved. We conducted the experiments on six fine-grained image datasets. Except for FGVC-Aircraft, the accuracies of the proposed methods on the other datasets exceeded 99%. Experimental results show that BiLSTM-TDN is far superior to the existing state-of-the-art methods. In addition to DCNN, BiLSTM-TDN can also be extended to other models, such as Transformer.

📄 PDF Abstract BibTeX arXiv:2103.07230

Code (0)

등록된 구현이 없습니다.

Tasks

Classification image-classification

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

DCNN Diffusion-convolutional neural networks (DCNN) is a model for graph-structured data. Through the introduction of a diffusion-convolution operation, diffusion-based representations…

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Position-Wise Feed-Forward Layer 설명 없음

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Attention 설명 없음

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Target-oriented Sentiment Classification with Sequential Cross-modal Semantic Graph

2022-08-19 · Yufeng Huang, Zhuo Chen, Jiaoyan Chen, Jeff Z. Pan 외

Multi-modal aspect-based sentiment classification (MABSC) is task of classifying the sentiment of a target entity mentioned in a sentence and an image. However, previous methods failed to account for the fine-grained sem…

Decoder Image Captioning Sentence Sentiment Analysis+1

Cost-Aware Fine-Grained Recognition for IoTs Based on Sequential Fixations

2018-11-16 · ICCV 2019 10 · Hanxiao Wang, Venkatesh Saligrama, Stan Sclaroff, Vitaly Ablavsky

We consider the problem of fine-grained classification on an edge camera device that has limited power. The edge device must sparingly interact with the cloud to minimize communication bits to conserve power, and the clo…

Classification Decision Making Deep Reinforcement Learning Foveation+2

Boosting Few-Shot Classification with View-Learnable Contrastive Learning

2021-07-20 · Xu Luo, Yuxuan Chen, Liangjian Wen, Lili Pan 외

The goal of few-shot classification is to classify new categories with few labeled examples within each class. Nowadays, the excellent performance in handling few-shot classification problems is shown by metric-based met…

Classification Contrastive Learning Few-Shot Learning Meta-Learning

Auto-view contrastive learning for few-shot image recognition

2021-01-01 · Xu Luo, Yuxuan Chen, Liangjian Wen, Lili Pan 외

Few-shot learning aims to recognize new classes with few annotated instances within each category. Recently, metric-based meta-learning approaches have shown the superior performance in tackling few-shot learning problem…

Contrastive Learning Few-Shot Learning Fine-Grained Image Classification General Classification+3

BoxCars: Improving Fine-Grained Recognition of Vehicles using 3-D Bounding Boxes in Traffic Surveillance

2017-03-02 · Jakub Sochor, Jakub Špaňhel, Adam Herout

In this paper, we focus on fine-grained recognition of vehicles mainly in traffic surveillance applications. We propose an approach that is orthogonal to recent advancements in fine-grained recognition (automatic part di…

3D Object Detection Vehicle Pose Estimation