all AI news
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
April 2, 2024, 7:47 p.m. | Sanghyun Jo, Soohyun Ryu, Sungyub Kim, Eunho Yang, Kyungsu Kim
cs.CV updates on arXiv.org arxiv.org
Abstract: We identify a critical bias in contemporary CLIP-based models, which we denote as \textit{single tag bias}. This bias manifests as a disproportionate focus on a singular tag (word) while neglecting other pertinent tags, stemming from CLIP's text embeddings that prioritize one specific tag in image-text relationships. When deconstructing text into individual tags, only one tag tends to have high relevancy with CLIP's image embedding, leading to an imbalanced tag relevancy. This results in an uneven …
alignment arxiv bias clip cs.cv distillation image tag text type
More from arxiv.org / cs.CV updates on arXiv.org
Retrieval-Augmented Egocentric Video Captioning
2 days, 17 hours ago |
arxiv.org
Mirror-Aware Neural Humans
2 days, 17 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US