4 papers · 1 filter
Robust Trajectory Distillation: Hybrid Reweighting Meets Teacher-Inspired Targets
Kaifeng Chen, Lechao Cheng, Jiyang Li +6
Dataset distillation (DD) condenses large corpora into compact, information-rich subsets for efficient training and reuse. However, under noisy supervision, DD risks condensing cor…
Infusing fine-grained visual knowledge to Vision-Language Models
Nikolaos-Antonios Ypsilantis, Kaifeng Chen, André Araujo +1
Large-scale contrastive pre-training produces powerful Vision-and-Language Models (VLMs) capable of generating representations (embeddings) effective for a wide variety of visual a…
TIPS: Text-Image Pretraining with Spatial awareness
Kevis-Kokitsi Maninis, Kaifeng Chen, Soham Ghosh +11
While image-text representation learning has become very popular in recent years, existing models tend to lack spatial awareness and have limited direct applicability for dense und…
UDON: Universal Dynamic Online distillatioN for generic image representations
Nikolaos-Antonios Ypsilantis, Kaifeng Chen, André Araujo +1
Universal image representations are critical in enabling real-world fine-grained and instance-level recognition applications, where objects and entities from any domain must be ide…