Proposal Distribution Calibration for Few-Shot Object Detection

1 code implementation • 15 Dec 2022 • Bohao Li, Chang Liu, Mengnan Shi, Xiaozhong Chen, Xiangyang Ji, Qixiang Ye

Adapting object detectors learned with sufficient supervision to novel classes under low data regimes is charming yet challenging.

Few-Shot Object Detection Object +1

Beyond Masking: Demystifying Token-Based Pre-Training for Vision Transformers

1 code implementation • 27 Mar 2022 • Yunjie Tian, Lingxi Xie, Jiemin Fang, Mengnan Shi, Junran Peng, Xiaopeng Zhang, Jianbin Jiao, Qi Tian, Qixiang Ye

The past year has witnessed a rapid development of masked image modeling (MIM).

Feature-Gate Coupling for Dynamic Network Pruning

1 code implementation • 29 Nov 2021 • Mengnan Shi, Chang Liu, Qixiang Ye, Jianbin Jiao

Gating modules have been widely explored in dynamic network pruning to reduce the run-time computational cost of deep neural networks while preserving the representation of features.

Contrastive Learning Network Pruning

A scalable convolutional neural network for task-specified scenarios via knowledge distillation

no code implementations • 19 Sep 2016 • Mengnan Shi, Fei Qin, Qixiang Ye, Zhenjun Han, Jianbin Jiao

In this paper, we explore the redundancy in convolutional neural network, which scales with the complexity of vision tasks.

Knowledge Distillation