3 papers
cs.LG2026
OpenAttention: One Percent Is Enough with Tail Proxies
Hyunwoo Yu, Jongbeom Lee, Hyunbin Kim +8
Sparse attention reads only a small subset of the key-value cache, and how to treat the unread tail remains a key challenge. Discarding the tail biases the output, and sampling it…
cs.CV2024
MetaSeg: MetaFormer-based Global Contexts-aware Network for Efficient Semantic Segmentation
Beoungwoo Kang, Seunghun Moon, Yubin Cho +2
Beyond the Transformer, it is important to explore how to exploit the capacity of the MetaFormer, an architecture that is fundamental to the performance improvements of the Transfo…
cs.CV2024
Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic Segmentation
Hyunwoo Yu, Yubin Cho, Beoungwoo Kang +3
We present an Encoder-Decoder Attention Transformer, EDAFormer, which consists of the Embedding-Free Transformer (EFT) encoder and the all-attention decoder leveraging our Embeddin…