Related papers: From Local Details to Global Context: Advancing Vi…
While Multimodal Large Language Models (MLLMs) offer strong perception and reasoning capabilities for image-text input, Visual Question Answering (VQA) focusing on small image details still remains a challenge. Although visual cropping…
The rapid development of generative AI has made AI-generated images increasingly realistic and high-resolution. Most AI-generated image detection architectures typically downsample images before inputting them into models, risking the loss…
Transfer learning enables the sharing of common knowledge among models for a variety of downstream tasks, but traditional methods suffer in limited training data settings and produce narrow models incapable of effectively generalizing under…
Contrastive Language-Image Pre-training (CLIP) has been shown to learn visual representations with great transferability, which achieves promising accuracy for zero-shot classification. To further improve its downstream performance,…
Foundation vision-language models (VLMs) excel on natural images, but their utility for biomedical microscopy remains underexplored. In this paper, we investigate how in-context learning enables state-of-the-art VLMs to perform few-shot…
Recent progress in the few-shot adaptation of Vision-Language Models (VLMs) has further pushed their generalization capabilities, at the expense of just a few labeled samples within the target downstream task. However, this promising,…
Fine-tuning pre-trained vision-language models (VLMs), e.g., CLIP, for the open-world generalization has gained increasing popularity due to its practical value. However, performance advancements are limited when relying solely on intricate…
Vision-language models (VLMs) have demonstrated remarkable zero-shot performance across various classification tasks. Nonetheless, their reliance on hand-crafted text prompts for each task hinders efficient adaptation to new tasks. While…
Image Captioning for state-of-the-art VLMs has significantly improved over time; however, this comes at the cost of increased computational complexity, making them less accessible for resource-constrained applications such as mobile devices…
Vision-Language Models (VLMs) such as CLIP demonstrate strong zero-shot generalization, but their performance significantly degrades in cross-domain scenarios with scarce target-domain training data (Cross-Domain Few-Shot Learning, CDFSL).…
Recent advances in large-scale vision and language models have led to significant progress in zero-shot learning tasks. Methods such as CoOp and CoCoOp have shown that replacing handcrafted prompts with learnable vectors, known as prompt…
The visual classification performance of vision-language models such as CLIP has been shown to benefit from additional semantic knowledge from large language models (LLMs) such as GPT-3. In particular, averaging over LLM-generated class…
Foundation models have had a significant impact across various AI applications, enabling use cases that were previously impossible. Contrastive Visual Language Models (VLMs), in particular, have outperformed other techniques in many tasks.…
Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM). This unified input paradigm enables VLMs to…
Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated impressive zero-shot recognition capability, but still underperform in dense prediction tasks. Self-distillation recently is emerging as a promising approach for…
Aspect-based sentiment analysis (ABSA), a sequence labeling task, has attracted increasing attention in multilingual contexts. While previous research has focused largely on fine-tuning or training models specifically for ABSA, we evaluate…
Large vision-language models (LVLMs) are markedly proficient in deriving visual representations guided by natural language. Recent explorations have utilized LVLMs to tackle zero-shot visual anomaly detection (VAD) challenges by pairing…
Injecting world knowledge into pretrained multimodal large language models (MLLMs) is essential for domain-specific applications. Task-specific fine-tuning achieves this by tailoring MLLMs to high-quality in-domain data but encounters…
In-context Learning (ICL) utilizes structured demonstration-query inputs to induce few-shot learning on Language Models (LMs), which are not originally pre-trained on ICL-style data. To bridge the gap between ICL and pre-training, some…
Contextual cues related to a person's pose and interactions with objects and other people in the scene can provide valuable information for gaze following. While existing methods have focused on dedicated cue extraction methods, in this…