7 papers · 1 filter
GHOST: Geometry-Constrained Hybrid Diffusion for Open-Vocabulary 3D Scene Graph Generation
Changqun Feng, Wangxiandi Yin, Xin Hu +4
3D scene graph generation requires understanding both object semantics and metric spatial relations. However, existing open-vocabulary methods often struggle with spatial predicate…
UniDFKD: A Unified Semantic Prior Framework for Architecture-Agnostic Data-Free Knowledge Distillation
Xuewan He, Tong Chu, Zihan Cheng +5
Data-Free Knowledge Distillation (DFKD) transfers knowledge from a pretrained teacher model to a compact student model by synthesizing semantically informative data, eliminating th…
What to Remove, What to Preserve: Dual-Ambiguity Rectification for All-in-One Image Restoration
Cencen Liu, Wen Yin, Dongyang Zhang +6
All-in-one image restoration aims to handle diverse degradations within a unified framework. Existing methods commonly encode heterogeneous degradation conditions in a shared laten…
DIVER: Diving Deeper into Distilled Data via Expressive Semantic Recovery
Qianxin Xia, Zhiyong Shu, Wenbo Jiang +3
Dataset distillation aims to synthesize a compact proxy dataset that is unreadable or non-raw from the original dataset for privacy protection and highly efficient learning. Howeve…
FSCE: A Target-Aware Frequency-Spatial Collaborative Enhancement Framework for Noise-Resilient SAR ATR
Yansong Lin, Zihan Cheng, Ziyue Yang +5
Synthetic aperture radar automatic target recognition (SAR ATR) is severely challenged by coherent speckle noise, whose interference can be progressively amplified by hierarchical…
Efficient Dataset Distillation for Pre-Trained Self-Supervised Models via Statistical Flow Matching
Qianxin Xia, Jiawei Du, Xin Zhang +6
Dataset distillation seeks to synthesize a compact surrogate dataset that enables performance comparable to training on the original dataset for downstream tasks. For the scenario…
EDITS: Enhancing Dataset Distillation with Implicit Textual Semantics
Qianxin Xia, Jiawei Du, Guoming Lu +2
Dataset distillation aims to synthesize a compact dataset from the original large-scale one, enabling highly efficient learning while preserving competitive model performance. Howe…