A Memory-Efficient Framework for Deformable Transformer with Neural Architecture Search

Documenti analoghi

• Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer
  di: Shi, Huihong, et al.
  Pubblicazione: (2024)
• CDM-QTA: Quantized Training Acceleration for Efficient LoRA Fine-Tuning of Diffusion Model
  di: Lu, Jinming, et al.
  Pubblicazione: (2025)
• StripDet: Strip Attention-Based Lightweight 3D Object Detection from Point Cloud
  di: Wang, Weichao, et al.
  Pubblicazione: (2025)
• Chimera: A Block-Based Neural Architecture Search Framework for Event-Based Object Detection
  di: Silva, Diego A., et al.
  Pubblicazione: (2024)
• Flexiffusion: Training-Free Segment-Wise Neural Architecture Search for Efficient Diffusion Models
  di: Huang, Hongtao, et al.
  Pubblicazione: (2025)