UniFine: A Unified and Fine-grained Approach for Zero-shot Vision-Language Understanding
It addresses the problem of improving zero-shot performance in vision-language tasks for AI researchers, but it is incremental as it builds on existing CLIP-based methods by incorporating fine-grained details.
The paper tackles zero-shot vision-language understanding by proposing a unified framework that leverages fine-grained visual and textual information, outperforming previous zero-shot methods on VQA and achieving substantial improvements on SNLI-VE and VCR tasks.
Vision-language tasks, such as VQA, SNLI-VE, and VCR are challenging because they require the model's reasoning ability to understand the semantics of the visual world and natural language. Supervised methods working for vision-language tasks have been well-studied. However, solving these tasks in a zero-shot setting is less explored. Since Contrastive Language-Image Pre-training (CLIP) has shown remarkable zero-shot performance on image-text matching, previous works utilized its strong zero-shot ability by converting vision-language tasks into an image-text matching problem, and they mainly consider global-level matching (e.g., the whole image or sentence). However, we find visual and textual fine-grained information, e.g., keywords in the sentence and objects in the image, can be fairly informative for semantics understanding. Inspired by this, we propose a unified framework to take advantage of the fine-grained information for zero-shot vision-language learning, covering multiple tasks such as VQA, SNLI-VE, and VCR. Our experiments show that our framework outperforms former zero-shot methods on VQA and achieves substantial improvement on SNLI-VE and VCR. Furthermore, our ablation studies confirm the effectiveness and generalizability of our proposed method.