On Class Separability Pitfalls In Audio-Text Contrastive Zero-Shot Learning
원문 초록
Recent advances in audio-text cross-modal contrastive learning have shown its potential towards zero-shot learning. One possibility for this is by projecting item embeddings from pre-trained backbone neural networks into a cross-modal space in which item similarity can be calculated in either domain. This process relies on a strong unimodal pre-training of the backbone networks, and on a data-intensive training task for the projectors. These two processes can be biased by unintentional data leakage, which can arise from using supervised learning in pre-training or from inadvertently training the cross-modal projection using labels from the zero-shot learning evaluation. In this study, we show that a significant part of the measured zero-shot learning accuracy is due to strengths inherited from the audio and text backbones, that is, they are not learned in the cross-modal domain and are not transferred from one modality to another.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Efficient Medical Vision-Language Alignment Through Adapting Masked Vision Models
A Brain Graph Foundation Model: Pre-Training and Prompt-Tuning for Any Atlas and Disorder
AmorLIP: Efficient Language-Image Pretraining via Amortization
Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation
Image Classification Using a Diffusion Model as a Pre-Training Model
DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.