output
20072026
most citedDeep Subdomain Adaptation Network for Image Classification

1.2k citations

Showing 2021 · cs.CVShow all

16 papers · 2 filters

cs.CV2021★ 61 cited

Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting

Junhua Zou, Zhisong Pan, Junyang Qiu +3

We introduce a three stage pipeline: resized-diverse-inputs (RDIM), diversity-ensemble (DEM) and region fitting, that work together to generate transferable adversarial examples. W…

cs.CV2021★ 13 cited

ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers

Husheng Han, Kaidi Xu, Xing Hu +6

Adversarial patch attacks that craft the pixels in a confined region of the input images show their powerful attack effectiveness in physical environments even with noises or defor…

cs.CV2021

Topic Scene Graph Generation by Attention Distillation from Caption

W. Wang, R. Wang, X. Chen

If an image tells a story, the image caption is the briefest narrator. Generally, a scene graph prefers to be an omniscient generalist, while the image caption is more willing to b…

cs.CV2021★ 3 cited

Multi-Modulation Network for Audio-Visual Event Localization

Hao Wang, Zheng-Jun Zha, Liang Li +2

We study the problem of localizing audio-visual events that are both audible and visible in a video. Existing works focus on encoding and aligning audio and visual features at the…

cs.CV2021★ 28 cited

FoodLogoDet-1500: A Dataset for Large-Scale Food Logo Detection via Multi-Scale Feature Decoupling Network

Qiang Hou, Weiqing Min, Jing Wang +3

Food logo detection plays an important role in the multimedia for its wide real-world applications, such as food recommendation of the self-service shop and infringement detection…

cs.CV2021★ 1 cited

Meta Gradient Adversarial Attack

Zheng Yuan, Jie Zhang, Yunpei Jia +3

In recent years, research on adversarial attacks has become a hot spot. Although current literature on the transfer-based adversarial attack has achieved promising results for impr…