25 citations · 41 across the 6 of their papers we have counts for
7 papers
TAVP: Task-Adaptive Visual Prompt for Cross-domain Few-shot Segmentation
Jiaqi Yang, Yaning Zhang, Jingxi Hu +3
While large visual models (LVM) demonstrated significant potential in image understanding, due to the application of large-scale pre-training, the Segment Anything Model (SAM) has…
High-level Feature Guided Decoding for Semantic Segmentation
Ye Huang, Di Kang, Shenghua Gao +2
Existing pyramid-based upsamplers (e.g. SemanticFPN), although efficient, usually produce less accurate results compared to dilation-based models when using the same backbone. This…
CARD: Semantic Segmentation with Efficient Class-Aware Regularized Decoder
Ye Huang, Di Kang, Liang Chen +5
Semantic segmentation has recently achieved notable advances by exploiting "class-level" contextual information during learning. However, these approaches simply concatenate class-…
CAR: Class-aware Regularizations for Semantic Segmentation
Ye Huang, Di Kang, Liang Chen +4
Recent segmentation methods, such as OCR and CPNet, utilizing "class level" information in addition to pixel features, have achieved notable success for boosting the accuracy of ex…
Channelized Axial Attention for Semantic Segmentation -- Considering Channel Relation within Spatial Attention for Semantic Segmentation
Ye Huang, Di Kang, Wenjing Jia +2
Spatial and channel attentions, modelling the semantic interdependencies in spatial and channel dimensions respectively, have recently been widely used for semantic segmentation. H…
See More Than Once -- Kernel-Sharing Atrous Convolution for Semantic Segmentation
Ye Huang, Qingqing Wang, Wenjing Jia +1
The state-of-the-art semantic segmentation solutions usually leverage different receptive fields via multiple parallel branches to handle objects with different sizes. However, emp…
FACLSTM: ConvLSTM with Focused Attention for Scene Text Recognition
Qingqing Wang, Wenjing Jia, Xiangjian He +3
Scene text recognition has recently been widely treated as a sequence-to-sequence prediction problem, where traditional fully-connected-LSTM (FC-LSTM) has played a critical role. D…