6 papers · 1 filter
Anti-Shortcut Distillation via Temporal Negative Knowledge Transfer
Syed Muhammad Raza, Omer Tariq, Jeongbae Son
Knowledge distillation (KD) trains a compact student by attracting it towards a converged teacher. It is silent about which directions the teacher itself learned to suppress: repul…
ProCache: Constraint-Aware Feature Caching with Selective Computation for Diffusion Transformer Acceleration
Fanpu Cao, Yaofo Chen, Zeng You +1
Diffusion Transformers (DiTs) have achieved state-of-the-art performance in generative modeling, yet their high computational cost hinders real-time deployment. While feature cachi…
Sensitivity-Aware Post-Training Quantization for Deep Neural Networks
Zekang Zheng, Haokun Li, Yaofo Chen +2
Model quantization reduces neural network parameter precision to achieve compression, but often compromises accuracy. Existing post-training quantization (PTQ) methods employ itera…
Towards Long Video Understanding via Fine-detailed Video Story Generation
Zeng You, Zhiquan Wen, Yaofo Chen +4
Long video understanding has become a critical task in computer vision, driving advancements across numerous applications from surveillance to content retrieval. Existing video und…
Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation
Yaofo Chen, Shuaicheng Niu, Yaowei Wang +3
The conventional deep learning paradigm often involves training a deep model on a server and then deploying the model or its distilled ones to resource-limited edge devices. Usuall…
Automated Dominative Subspace Mining for Efficient Neural Architecture Search
Yaofo Chen, Yong Guo, Daihai Liao +4
Neural Architecture Search (NAS) aims to automatically find effective architectures within a predefined search space. However, the search space is often extremely large. As a resul…