Jose M Alvarez

Latest

• Vision Transformers Are Good Mask Auto-Labelers
• VoxFormer: Sparse voxel transformer for camera-based 3D semantic scene completion
• Structural Pruning via Latency-Saliency Knapsack
• Privacy Vulnerability of Split Computing to Data-Free Model Inversion Attacks
• Understanding The Robustness in Vision Transformers
• Panoptic SegFormer: Delving deeper into panoptic segmentation with transformers
• When to Prune? A Policy towards Early Structural Pruning
• M$^2$BEV: Multi-camera joint 3D detection and segmentation with unified birds-eye view representation
• SegFormer: Simple and efficient design for semantic segmentation with transformers
• Optimal Quantization Using Scaled Codebook