首页/论文/2001.05153

arXiv 2001.051532020-01-15cs.CV

Extending Class Activation Mapping Using Gaussian Receptive Field

Pohang University of Science and Technology（浦项科技大学）

Bum Jun Kim, Gyogwon Koo, Hyeyeon Choi, Sang Woo Kim

备注：: 7 pages, 5 figures

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

This paper addresses the visualization task of deep learning models. To improve Class Activation Mapping (CAM) based visualization method, we offer two options. First, we propose Gaussian upsampling, an improved upsampling method that can reflect the characteristics of deep learning models. Second, we identify and modify unnatural terms in the mathematical derivation of the existing CAM studies. Based on two options, we propose Extended-CAM, an advanced CAM-based visualization method, which exhibits improved theoretical properties. Experimental results show that Extended-CAM provides more accurate visualization than the existing methods.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Understanding the Effective Receptive Field in Deep Convolutional Neural Networks

University of Toronto（多伦多大学）

We study characteristics of receptive fields of units in deep convolutional networks. The receptive field size is a crucial issue in many visual tasks, as the output must respond to large enough areas in the image to capture information about large objects. We introduce the notion of an effective receptive field, and show that it both has a Gaussian distribution and only occupies a fraction of the full theoretical receptive field. We analyze the effective receptive field in several architecture designs, and the effect of nonlinear activations, dropout, sub-sampling and skip connections on it. …

2017-01-25cs.AIcs.CVcs.LG

Receptive Field Size Optimization with Continuous Time Pooling

Peter Pazmany Catholic University（帕兹马尼·彼得天主教大学）

The pooling operation is a cornerstone element of convolutional neural networks. These elements generate receptive fields for neurons, in which local perturbations should have minimal effect on the output activations, increasing robustness and invariance of the network. In this paper we will present an altered version of the most commonly applied method, maximum pooling, where pooling in theory is substituted by a continuous time differential equation, which generates a location sensitive pooling operation, more similar to biological receptive fields. We will present how this continuous method…

2020-11-06cs.AIcs.CV

Translated Skip Connections -- Expanding the Receptive Fields of Fully Convolutional Neural Networks

University of the Witwatersrand（金山大学）

The effective receptive field of a fully convolutional neural network is an important consideration when designing an architecture, as it defines the portion of the input visible to each convolutional kernel. We propose a neural network module, extending traditional skip connections, called the translated skip connection. Translated skip connections geometrically increase the receptive field of an architecture with negligible impact on both the size of the parameter space and computational complexity. By embedding translated skip connections into a benchmark architecture, we demonstrate that o…

2022-11-03cs.CVcs.LGeess.IV

Prediction of Dashed Café Wall illusion by the Classical Receptive Field Model

Flinders University（弗林德斯大学）

The Café Wall illusion is one of a class of tilt illusions where lines that are parallel appear to be tilted. We demonstrate that a simple Differences of Gaussian model provides an explanatory mechanism for the illusory tilt perceived in a family of Café Wall illusion generalizes to the dashed versions of Café Wall. Our explanation models the visual mechanisms in low level stages and the lateral inhibition of simple cells that can reveal tilt cues in Geometrical distortion illusions such as Tile illusions particularly Café Wall illusions. For this, we simulate the activations of the retinal/co…

2020-05-11cs.CVq-bio.NC

Rethinking the Faster R-CNN Architecture for Temporal Action Localization

University of Michigan（密歇根大学）；Google Research（谷歌研究院）

We propose TAL-Net, an improved approach to temporal action localization in video that is inspired by the Faster R-CNN object detection framework. TAL-Net addresses three key shortcomings of existing approaches: (1) we improve receptive field alignment using a multi-scale architecture that can accommodate extreme variation in action durations; (2) we better exploit the temporal context of actions for both proposal generation and action classification by appropriately extending receptive fields; and (3) we explicitly consider multi-stream feature fusion and demonstrate that fusing motion late i…

2018-04-20cs.CV

Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation

Singapore Management University（新加坡管理大学）；Nanyang Technological University（南洋理工大学）；Damo Academy, Alibaba Group（阿里巴巴集团达摩院）

Extracting class activation maps (CAM) is arguably the most standard step of generating pseudo masks for weakly-supervised semantic segmentation (WSSS). Yet, we find that the crux of the unsatisfactory pseudo masks is the binary cross-entropy loss (BCE) widely used in CAM. Specifically, due to the sum-over-class pooling nature of BCE, each pixel in CAM may be responsive to multiple classes co-occurring in the same receptive field. As a result, given a class, its hot CAM pixels may wrongly invade the area belonging to other classes, or the non-hot ones may be actually a part of the class. To th…

2022-03-02cs.CV

更多相关论文收起更多论文

空间上下文对多任务海冰分割的影响研究

Investigating the Effect of Spatial Context on Multi-Task Sea Ice Segmentation

University of Colorado Boulder（科罗拉多大学博尔德分校）；National Snow and Ice Data Center (NSIDC)（国家冰雪数据中心）；CIRES（环境科学合作研究所）

本研究通过多任务分割模型系统探究空间上下文对海冰密集度、发展阶段、浮冰尺寸分割的影响，分析不同感受野、数据组合的性能差异，为海冰制图的深度学习模型优化提供参考。

2025-07-28cs.CVeess.IV

视觉位置细胞编码：空间表征与认知地图的计算模型

Visual Place Cell Encoding: A Computational Model for Spatial Representation and Cognitive Mapping

本文提出视觉位置细胞编码模型，通过聚类视觉特征模拟位置细胞激活，无需运动或奖励即可区分相似位置并适应环境变化，支持认知地图构建。

2025-04-22cs.CVcs.RO

FINER++：构建用于激活隐式神经表示的可变周期函数族

FINER++: Building a Family of Variable-periodic Functions for Activating Implicit Neural Representation

School of Electronic Science and Engineering, Nanjing University（南京大学电子科学与工程学院）；Vivo（vivo公司）；School of Mathematics, Nanjing University（南京大学数学学院）；Department of Computer Science and Technology, Nanjing University（南京大学计算机科学与技术系）

针对隐式神经表示的频谱偏差和容量-收敛差距问题，提出FINER++框架，通过扩展激活函数为可变周期函数并初始化偏置以灵活调整频率集，在多种任务和主干上提升了信号表示性能。

2024-07-28cs.CV

Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning

University of Michigan（密歇根大学）；Stanford University（斯坦福大学）；NTT Research, Inc.（NTT研究院）

Inspired by BatchNorm, there has been an explosion of normalization layers in deep learning. Recent works have identified a multitude of beneficial properties in BatchNorm to explain its success. However, given the pursuit of alternative normalization layers, these properties need to be generalized so that any given layer's success/failure can be accurately predicted. In this work, we take a first step towards this goal by extending known properties of BatchNorm in randomly initialized deep neural networks (DNNs) to several recently proposed normalization layers. Our primary findings follow: (…

2021-10-26cs.CVcs.LG

Aff-Wild2: Extending the Aff-Wild Database for Affect Recognition

Imperial College London（帝国理工学院）；University of Oulu（奥卢大学）

Automatic understanding of human affect using visual signals is a problem that has attracted significant interest over the past 20 years. However, human emotional states are quite complex. To appraise such states displayed in real-world settings, we need expressive emotional descriptors that are capable of capturing and describing this complexity. The circumplex model of affect, which is described in terms of valence (i.e., how positive or negative is an emotion) and arousal (i.e., power of the activation of the emotion), can be used for this purpose. Recent progress in the emotion recognition…

2019-12-13cs.AIcs.CVcs.LG