Denis Gudovskiy

6

Papers

215

Total Citations

Papers (6)

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

Efficient Deweahter Mixture-of-Experts with Uncertainty-Aware Feature-Wise Linear Modulation

Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting

Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision

AutoDO: Robust AutoAugment for Biased Data With Label Noise via Scalable Probabilistic Implicit Differentiation

MTTrans: Cross-Domain Object Detection with Mean Teacher Transformer