glacial
发表于 2025-3-23 11:34:07
Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks,ctim model by injecting a backdoor pattern into a small proportion of the training data. At test time, the victim model behaves normally on clean test data, yet consistently predicts a specific (likely incorrect) target class whenever the backdoor pattern is present in a test example. While existing
BANAL
发表于 2025-3-23 16:09:41
Learning to Learn with Variational Information Bottleneck for Domain Generalization, we address both problems. We introduce a probabilistic meta-learning model for domain generalization, in which classifier parameters shared across domains are modeled as distributions. This enables better handling of prediction uncertainty on unseen domains. To deal with domain shift, we learn doma
Thyroiditis
发表于 2025-3-23 20:58:51
Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysis,ghly aligned 3D shapes based on point coordinates, but suffer from performance drops with shape rotations. Some geometric features, e.g., distances and angles of points as inputs of network, are rotation-invariant but lose positional information of points. In this work, we propose a novel deep netwo
Osteons
发表于 2025-3-24 01:24:18
Thanks for Nothing: Predicting Zero-Valued Activations with Lightweight Convolutional Neural Networe observation that spatial correlation exists in CNN output feature maps (ofms), we propose a method to dynamically predict whether ofm activations are zero-valued or not according to their neighboring activation values, thereby avoiding zero-valued activations and reducing the number of convolution
capsule
发表于 2025-3-24 02:55:48
http://reply.papertrans.cn/24/2343/234226/234226_15.png
箴言
发表于 2025-3-24 08:13:51
SCAN: Learning to Classify Images Without Labels,ification remains an important, and open challenge in computer vision. Several recent approaches have tried to tackle this problem in an end-to-end fashion. In this paper, we deviate from recent works, and advocate a two-step approach where feature learning and clustering are decoupled. First, a sel
Diatribe
发表于 2025-3-24 11:03:59
Graph Convolutional Networks for Learning with Few Clean and Many Noisy Labels,d noisy data is modeled by a graph per class and Graph Convolutional Networks (GCN) are used to predict class relevance of noisy examples. For each class, the GCN is treated as a binary classifier, which learns to discriminate clean from noisy examples using a weighted binary cross-entropy loss func
avulsion
发表于 2025-3-24 14:54:03
Object-and-Action Aware Model for Visual Language Navigation,on the basis of visible environments. This requires to extract value from two very different types of natural-language information. The first is object description (e.g., ‘table’, ‘door’), each presenting as a tip for the agent to determine the next action by finding the item visible in the environm
AXIS
发表于 2025-3-24 20:39:29
A Comprehensive Study of Weight Sharing in Graph Networks for 3D Human Pose Estimation,rmance. One limitation of the vanilla graph convolution is that it models the relationships between neighboring nodes via a shared weight matrix. This is suboptimal for articulated body modeling as the relations between different body joints are different. The objective of this paper is to have a co
DUCE
发表于 2025-3-25 03:13:47
0302-9743 uter Vision, ECCV 2020, which was planned to be held in Glasgow, UK, during August 23-28, 2020. The conference was held virtually due to the COVID-19 pandemic..The 1360 revised papers presented in these proceedings were carefully reviewed and selected from a total of 5025 submissions. The papers dea