7 papers
A Mixed Diet Makes DINO An Omnivorous Vision Encoder
Rishabh Kabra, Maks Ovsjanikov, Drew A. Hudson +5
Pre-trained vision encoders like DINOv2 have demonstrated exceptional performance on unimodal tasks. However, we observe that their features are poorly aligned across different vis…
TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment
Bingyi Cao, Koert Chen, Kevis-Kokitsi Maninis +16
Recent progress in vision-language pretraining has enabled significant improvements to many downstream computer vision applications, such as classification, retrieval, segmentation…
EmbeddingGemma: Powerful and Lightweight Text Representations
Henrique Schechter Vera, Sahil Dua, Biao Zhang +86
We introduce EmbeddingGemma, a new lightweight, open text embedding model based on the Gemma 3 language model family. Our innovative training recipe strategically captures knowledg…
Learning Visual Composition through Improved Semantic Guidance
Austin Stone, Hagen Soltau, Robert Geirhos +6
Visual imagery does not consist of solitary objects, but instead reflects the composition of a multitude of fluid concepts. While there have been great advances in visual represent…
Gemini Embedding: Generalizable Embeddings from Gemini
Jinhyuk Lee, Feiyang Chen, Sahil Dua +44
In this report, we introduce Gemini Embedding, a state-of-the-art embedding model leveraging the power of Gemini, Google's most capable large language model. Capitalizing on Gemini…
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…