5 papers
GLF-Q: Global-Local Feature-based Quantization for Vision Transformers
Peilin Sun, Guang Liang, Jin Tong +1
Post-training quantization (PTQ) efficiently compresses Vision Transformers (ViTs) without retraining, yet suffers severe accuracy degradation at low bit-widths. Existing optimizat…
Colinearity Decay: Training Quantization-Friendly ViTs with Outlier Decay
Jin Tong, Guang Liang, Peilin Sun +1
Low-bit quantization is a practical route for efficiently deploying vision Transformers, yet activation outliers complicate fully quantized deployment. Existing methods either hand…
Diffusion Model as a Generalist Segmentation Learner
Haoxiao Wang, Antao Xiang, Haiyang Sun +8
Diffusion models are primarily trained for image synthesis, yet their denoising trajectories encode rich, spatially aligned visual priors. In this paper, we demonstrate that these…
PVTransformer: Point-to-Voxel Transformer for Scalable 3D Object Detection
Zhaoqi Leng, Pei Sun, Tong He +2
3D object detectors for point clouds often rely on a pooling-based PointNet to encode sparse points into grid-like voxels or pillars. In this paper, we identify that the common Poi…
LEF: Late-to-Early Temporal Fusion for LiDAR 3D Object Detection
Tong He, Pei Sun, Zhaoqi Leng +3
We propose a late-to-early recurrent feature fusion scheme for 3D object detection using temporal LiDAR point clouds. Our main motivation is fusing object-aware latent embeddings i…