Xianbin Cao

12

Papers

0

Total Citations

Papers (12)

SET: Spectral Enhancement for Tiny Object Detection

Uncertainty-Aware Gradient Stabilization for Small Object Detection

Bi-ViT: Pushing the Limit of Vision Transformer Quantization

Modulated Convolutional Networks

Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks

Attentional Neural Fields for Crowd Counting

Relational Attention Network for Crowd Counting

Representation Disparity-aware Distillation for 3D Object Detection

Few-Shot Semantic Segmentation with Democratic Attention Networks

IDa-Det: An Information Discrepancy-Aware Distillation for 1-Bit Detectors

Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer

Q-DM: An Efficient Low-bit Quantized Diffusion Model