paper-with-me

Papers

Information Bottleneck Approach to Spatial Attention Learning

2021-08-07 · Qiuxia Lai, Yu Li, Ailing Zeng, Minhao Liu, Hanqiu Sun, Qiang Xu

The selective visual attention mechanism in the human visual system (HVS) restricts the amount of information to reach visual awareness for perceiving natural scenes, allowing near real-time information processing with limited computational capacity [Koch and Ullman, 1987]. This kind of selectivity acts as an 'Information Bottleneck (IB)', which seeks a trade-off between information compression and predictive accuracy. However, such information constraints are rarely explored in the attention mechanism for deep neural networks (DNNs). In this paper, we propose an IB-inspired spatial attention module for DNN structures built for visual recognition. The module takes as input an intermediate representation of the input image, and outputs a variational 2D attention map that minimizes the mutual information (MI) between the attention-modulated representation and the input, while maximizing the MI between the attention-modulated representation and the task label. To further restrict the information bypassed by the attention map, we quantize the continuous attention scores to a set of learnable anchor values during training. Extensive experiments show that the proposed IB-inspired spatial attention mechanism can yield attention maps that neatly highlight the regions of interest while suppressing backgrounds, and bootstrap standard DNN structures for visual recognition tasks (e.g., image classification, fine-grained recognition, cross-domain classification). The attention maps are interpretable for the decision making of the DNNs as verified in the experiments. Our code is available at https://github.com/ashleylqx/AIB.git.

📄 PDF Abstract BibTeX arXiv:2108.03418

Code (1)

ashleylqx/aib 공식 구현 pytorch

Tasks

Decision Makingdomain classificationimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Average Pooling 설명 없음
Sigmoid Activation 설명 없음

Similar Papers 제목 키워드 기반

Information Bottleneck-based Causal Attention for Multi-label Medical Image Recognition

2025-08-11 · Xiaoxiao Cui, Yiran Li, Kai He, Shanzhi Jiang 외 arxiv

Multi-label classification (MLC) of medical images aims to identify multiple diseases and holds significant clinical potential. A critical step is to learn class-specific features for accurate diagnosis and improved inte…

Multi-Label Classification

Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Information

2019-05-09 · CVPR 2019 6 · Kai Su, Dongdong Yu, Zhenqi Xu, Xin Geng 외

Multi-person pose estimation is an important but challenging problem in computer vision. Although current approaches have achieved significant progress by fusing the multi-scale feature maps, they pay little attention to…

Multi-Person Pose EstimationPose Estimation

S3TA: A Soft, Spatial, Sequential, Top-Down Attention Model

2019-05-01 · ICLR 2019 5 · Alex Mott, Daniel Zoran, Mike Chrzanowski, Daan Wierstra 외

We present a soft, spatial, sequential, top-down attention model (S3TA). This model uses a soft attention mechanism to bottleneck its view of the input. A recurrent core is used to generate query vectors, which actively …

Decision Making

DRCT: Saving Image Super-resolution away from Information Bottleneck

2024-03-31 · Chih-Chung Hsu, Chia-Ming Lee, Yi-Shiuan Chou

In recent years, Vision Transformer-based approaches for low-level vision tasks have achieved widespread success. Unlike CNN-based models, Transformers are more adept at capturing long-range dependencies, enabling the re…

Image Super-ResolutionSuper-Resolution

Deep Ordinal Hashing with Spatial Attention

2018-05-07 · Lu Jin, Xiangbo Shu, Kai Li, Zechao Li 외

Hashing has attracted increasing research attentions in recent years due to its high efficiency of computation and storage in image retrieval. Recent works have demonstrated the superiority of simultaneous feature repres…

Deep HashingImage RetrievalRetrieval