8 papers
Do Instance Priors Help Weakly Supervised Semantic Segmentation?
Anurag Das, Anna Kukleva, Xinting Hu +2
Semantic segmentation requires dense pixel-level annotations, which are costly and time-consuming to acquire. To address this, we present SeSAM, a framework that uses a foundationa…
TTA-Vid: Generalized Test-Time Adaptation for Video Reasoning
Soumya Shamarao Jahagirdar, Edson Araujo, Anna Kukleva +7
Recent video reasoning models have shown strong results on temporal and multimodal understanding, yet they depend on large-scale supervised data and multi-stage training pipelines,…
MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data
Siarhei Sheludzko, Dhimitrios Duka, Bernt Schiele +2
Contrastive learning has become a fundamental approach in both uni-modal and multi-modal frameworks. This learning paradigm pulls positive pairs of samples closer while pushing neg…
When LLaVA Meets Objects: Token Composition for Vision-Language-Models
Soumya Jahagirdar, Walid Bousselham, Anna Kukleva +1
Current autoregressive Vision Language Models (VLMs) usually rely on a large number of visual tokens to represent images, resulting in a need for more compute especially at inferen…
RefAM: Attention Magnets for Zero-Shot Referral Segmentation
Anna Kukleva, Enis Simsar, Alessio Tonioni +4
Most existing approaches to referring segmentation achieve strong performance only through fine-tuning or by composing multiple pre-trained models, often at the cost of additional…
Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs
Selim Kuzucu, Muhammad Ferjad Naeem, Anna Kukleva +2
The integration of Large Language Model (LLMs) blocks with Vision Transformers (ViTs) holds immense promise for vision-only tasks by leveraging the rich semantic knowledge and reas…