Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Reevaluating the Intra-Modal Misalignment Hypothesis in CLIP
Jonas Herzog, Yue Wang
Recent research suggested that the embeddings produced by CLIP-like contrastive language-image training are suboptimal for image-only tasks. The main theory is that the inter-modal…
cs.CV2024
Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentation
Jonas Herzog
Few-shot segmentation performance declines substantially when facing images from a domain different than the training domain, effectively limiting real-world use cases. To alleviat…