WARM-CAT: : Warm-Started Test-Time Comprehensive Knowledge Accumulation for Compositional Zero-Shot Learning

TL;DR

A novel approach that accumulates comprehensive knowledge in both textual and visual modalities from unsupervised data to update multimodal prototypes at test time is proposed and achieves state-of-the-art performance on four benchmark datasets under both closed-world and open-world settings.

Abstract

Compositional Zero-Shot Learning (CZSL) aims to recognize novel attribute-object compositions based on the knowledge learned from seen ones. Existing methods suffer from performance degradation caused by the distribution shift of label space at test time, which stems from the inclusion of unseen compositions recombined from attributes and objects. To overcome the challenge, we propose a novel approach that accumulates comprehensive knowledge in both textual and visual modalities from unsupervised data to update multimodal prototypes at test time. Building on this, we further design an adaptive update weight to control the degree of prototype adjustment, enabling the model to flexibly adapt to distribution shift during testing. Moreover, a dynamic priority queue is introduced that stores high-confidence images to acquire visual prototypes from historical images for inference. Since the model tends to favor compositions already stored in the queue during testing, we warm-start the queue by initializing it with training images for visual prototypes of seen compositions and generating unseen visual prototypes using the mapping learned between seen and unseen textual prototypes. Considering the semantic consistency of multimodal knowledge, we align textual and visual prototypes by multimodal collaborative representation learning. To provide a more reliable evaluation for CZSL, we introduce a new benchmark dataset, C-Fashion, and refine the widely used but noisy MIT-States dataset. Extensive experiments indicate that our approach achieves state-of-the-art performance on four benchmark datasets under both closed-world and open-world settings. The source code and datasets are available at https://github.com/xud-yan/WARM-CAT .

Figures (10)

• Figure 1: At test time, existing methods (top) fail to adapt using test images, resulting in biased prediction distributions due to label space shift. By contrast, WARM-CAT (bottom) progressively accumulates multimodal knowledge from unsupervised test data, enabling effective adaptation to address this challenge.
• Figure 2: Prompt tuning of the text encoder and adapter tuning of the visual encoder during training.
• Figure 3: The overall architecture of our proposed WARM-CAT at test time. The model accumulates multimodal knowledge to update prototypes to overcome the label distribution shift.
• Figure 4: Learning the mapping relationship between seen and unseen textual prototypes (top) and applying it to seen visual prototypes to obtain unseen visual prototypes (bottom).
• Figure 5: Image annotation generated by MLLM for C-Fashion benchmark dataset.