5 papers
Prompt-Based Continual Compositional Zero-Shot Learning
Sauda Maryam, Sara Nadeem, Faisal Qureshi +1
We tackle continual adaptation of vision-language models to new attributes, objects, and their compositions in Compositional Zero-Shot Learning (CZSL), while preventing forgetting…
CascadedViT: Cascaded Chunk-FeedForward and Cascaded Group Attention Vision Transformer
Srivathsan Sivakumar, Faisal Z. Qureshi
Vision Transformers (ViTs) have demonstrated remarkable performance across a range of computer vision tasks; however, their high computational, memory, and energy demands hinder de…
Compositional Zero-Shot Learning: A Survey
Ans Munir, Faisal Z. Qureshi, Mohsen Ali +1
Compositional Zero-Shot Learning (CZSL) is a critical task in computer vision that enables models to recognize unseen combinations of known attributes and objects during inference,…
TLAC: Two-stage LMM Augmented CLIP for Zero-Shot Classification
Ans Munir, Faisal Z. Qureshi, Muhammad Haris Khan +1
Contrastive Language-Image Pretraining (CLIP) has shown impressive zero-shot performance on image classification. However, state-of-the-art methods often rely on fine-tuning techni…
Attention Based Simple Primitives for Open World Compositional Zero-Shot Learning
Ans Munir, Faisal Z. Qureshi, Muhammad Haris Khan +1
Compositional Zero-Shot Learning (CZSL) aims to predict unknown compositions made up of attribute and object pairs. Predicting compositions unseen during training is a challenging…