443 citations · 544 across the 17 of their papers we have counts for
6 papers · 1 filter
Unfolding Once is Enough: A Deployment-Friendly Transformer Unit for Super-Resolution
Yong Liu, Hang Dong, Boyang Liang +6
Recent years have witnessed a few attempts of vision transformers for single image super-resolution (SISR). Since the high resolution of intermediate features in SISR models increa…
RIFormer: Keep Your Vision Backbone Effective While Removing Token Mixer
Jiahao Wang, Songyang Zhang, Yong Liu +6
This paper studies how to keep a vision backbone effective while removing token mixers in its basic building blocks. Token mixers, as self-attention for vision transformers (ViTs),…
Learning Quality-aware Dynamic Memory for Video Object Segmentation
Yong Liu, Ran Yu, Fei Yin +4
Recently, several spatial-temporal memory-based methods have verified that storing intermediate frames and their masks as memory are helpful to segment target objects in videos. Ho…
UniInst: Unique Representation for End-to-End Instance Segmentation
Yimin Ou, Rui Yang, Lufan Ma +5
Existing instance segmentation methods have achieved impressive performance but still suffer from a common dilemma: redundant representations (e.g., multiple boxes, grids, and anch…
A Survey of Visual Sensory Anomaly Detection
Xi Jiang, Guoyang Xie, Jinbao Wang +4
Visual sensory anomaly detection (AD) is an essential problem in computer vision, which is gaining momentum recently thanks to the development of AI for good. Compared with semanti…
Automatic Data Augmentation by Learning the Deterministic Policy
Yinghuan Shi, Tiexin Qin, Yong Liu +3
Aiming to produce sufficient and diverse training samples, data augmentation has been demonstrated for its effectiveness in training deep models. Regarding that the criterion of th…