activity
20182024
most citedMutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification

392 citations · 509 across the 15 of their papers we have counts for

collaborators

17 papers

cs.CV2022

Darwinian Model Upgrades: Model Evolving with Selective Compatibility

Binjie Zhang, Shupeng Su, Yixiao Ge +5

The traditional model upgrading paradigm for retrieval requires recomputing all gallery embeddings before deploying the new model (dubbed as "backfilling"), which is quite expensiv…

eess.SY2022

Equivariant Filter Design for Discrete-time systems

Yixiao Ge, Pieter van Goor, Robert Mahony

The kinematics of many nonlinear control systems, especially in the robotics field, admit a transitive Lie-group symmetry, which is useful in high performance observer design. The…

cs.CV20224 cited

Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection

Yuxin Fang, Shusheng Yang, Shijie Wang +3

We present an approach to efficiently and effectively adapt a masked image modeling (MIM) pre-trained vanilla Vision Transformer (ViT) for object detection, which is based on our t…

cs.CV20223 cited

Privacy-Preserving Model Upgrades with Bidirectional Compatible Training in Image Retrieval

Shupeng Su, Binjie Zhang, Yixiao Ge +4

The task of privacy-preserving model upgrades in image retrieval desires to reap the benefits of rapidly evolving new models without accessing the raw gallery images. A pioneering…

cs.CV2022

MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval

Yuying Ge, Yixiao Ge, Xihui Liu +5

Dominant pre-training work for video-text retrieval mainly adopt the "dual-encoder" architectures to enable efficient retrieval, where two separate encoders are used to contrast gl…

cs.CV2022

Towards Universal Backward-Compatible Representation Learning

Binjie Zhang, Yixiao Ge, Yantao Shen +6

Conventional model upgrades for visual search systems require offline refresh of gallery features by feeding gallery images into new models (dubbed as "backfill"), which is time-co…