47 citations · 133 across the 15 of their papers we have counts for
9 papers · 1 filter
ELSA: Enhanced Local Self-Attention for Vision Transformer
Jingkai Zhou, Pichao Wang, Fan Wang +3
Self-attention is powerful in modeling long-range dependencies, but it is weak in local finer-level feature learning. The performance of local self-attention (LSA) is just on par w…
Decoupling and Recoupling Spatiotemporal Representation for RGB-D-based Motion Recognition
Benjia Zhou, Pichao Wang, Jun Wan +6
Decoupling spatiotemporal representation refers to decomposing the spatial and temporal features into dimension-independent factors. Although previous RGB-D-based motion recognitio…
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation
Zhaoyuan Yin, Pichao Wang, Fan Wang +4
Unsupervised semantic segmentation aims to obtain high-level semantic representation on low-level visual features without manual annotations. Most existing methods are bottom-up ap…
Self-Supervised Pre-Training for Transformer-Based Person Re-Identification
Hao Luo, Pichao Wang, Yi Xu +5
Transformer-based supervised pre-training achieves great performance in person re-identification (ReID). However, due to the domain gap between ImageNet and ReID datasets, it usual…
Achieving Human Parity on Visual Question Answering
Ming Yan, Haiyang Xu, Chenliang Li +14
The Visual Question Answering (VQA) task utilizes both visual image and language analysis to answer a textual question with respect to an image. It has been a popular research topi…
MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection
Zhenhong Sun, Ming Lin, Xiuyu Sun +3
In object detection, the detection backbone consumes more than half of the overall inference cost. Recent researches attempt to reduce this cost by optimizing the backbone architec…
Improved Fine-Tuning by Better Leveraging Pre-Training Data
Ziquan Liu, Yi Xu, Yuanhong Xu +5
As a dominant paradigm, fine-tuning a pre-trained model on the target data is widely used in many deep learning applications, especially for small data sets. However, recent studie…
ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning
Zhiwu Qing, Ziyuan Huang, Shiwei Zhang +5
The central idea of contrastive learning is to discriminate between different instances and force different views from the same instance to share the same representation. To avoid…
Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition
Ming Lin, Pichao Wang, Zhenhong Sun +5
Accuracy predictor is a key component in Neural Architecture Search (NAS) for ranking architectures. Building a high-quality accuracy predictor usually costs enormous computation.…