134 citations · 302 across the 27 of their papers we have counts for
5 papers · 1 filter
Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidation
Naeem Paeedeh, Mahardhika Pratama, Wolfgang Mayer +3
Existing domain-incremental learning (DIL) strategies call for massive amounts of data to adapt to new domains and suffer from the overfitting problem in the case of data scarcity.…
Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction
Qiancheng Fu, Qingshan Xu, Yew-Soon Ong +1
Recently, neural implicit surfaces learning by volume rendering has become popular for multi-view reconstruction. However, one key challenge remains: existing approaches lack expli…
Word2Pix: Word to Pixel Cross Attention Transformer in Visual Grounding
Heng Zhao, Joey Tianyi Zhou, Yew-Soon Ong
Current one-stage methods for visual grounding encode the language query as one holistic sentence embedding before fusion with visual feature. Such a formulation does not treat eac…
Poison as a Cure: Detecting & Neutralizing Variable-Sized Backdoor Attacks in Deep Neural Networks
Alvin Chan, Yew-Soon Ong
Deep learning models have recently shown to be vulnerable to backdoor poisoning, an insidious attack where the victim model predicts clean images correctly but classifies the same…
MIML-FCN+: Multi-instance Multi-label Learning via Fully Convolutional Networks with Privileged Information
Hao Yang, Joey Tianyi Zhou, Jianfei Cai +1
Multi-instance multi-label (MIML) learning has many interesting applications in computer visions, including multi-object recognition and automatic image tagging. In these applicati…