Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
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…
cs.CV2026
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…
cs.CV2024
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…