Related papers: Black Box Few-Shot Adaptation for Vision-Language …

Vision-language models (VLMs) have demonstrated exceptional generalization capabilities for downstream tasks. Due to its efficiency, prompt learning has gradually become a more effective and efficient method for transferring VLMs to…

Few-shot learning (FSL) techniques seek to learn the underlying patterns in data using fewer samples, analogous to how humans learn from limited experience. In this limited-data scenario, the challenges associated with deep neural networks,…

Multimodal Large Language Models (MLLMs) have propelled the field of few-shot action recognition (FSAR). However, preliminary explorations in this area primarily focus on generating captions to form a suboptimal feature->caption->feature…

Few-shot learning (FSL) presents a challenging learning problem in which only a few samples are available for each class. Decision interpretation is more important in few-shot classification due to a greater chance of error compared to…

Vision-Language models (VLMs) that use contrastive language-image pre-training have shown promising zero-shot classification performance. However, their performance on imbalanced dataset is relatively poor, where the distribution of classes…

While humans can solve a visual puzzle that requires logical reasoning by observing only few samples, it would require training over large amount of data for state-of-the-art deep reasoning models to obtain similar performance on the same…

Text-to-image retrieval is a critical task for managing diverse visual content, but common benchmarks for the task rely on small, single-domain datasets that fail to capture real-world complexity. Pre-trained vision-language models tend to…

Vision-Language-Action (VLA) models typically map visual observations and linguistic instructions directly to control signals. This "black-box" mapping forces a single forward pass to simultaneously handle instruction interpretation,…

With the release of new large language models (LLMs) like Llama and Mistral, zero-shot cross-lingual transfer has become increasingly feasible due to their multilingual pretraining and strong generalization capabilities. However, adapting…

Few-shot learning (FSL) approaches are usually based on an assumption that the pre-trained knowledge can be obtained from base (seen) categories and can be well transferred to novel (unseen) categories. However, there is no guarantee,…

We introduce Context Tuning, a simple and effective method to significantly enhance few-shot adaptation of language models (LLMs) without fine-tuning model parameters. While prompt-based adaptation techniques have demonstrated the…

The core problem in zero-shot open vocabulary detection is how to align visual and text features, so that the detector performs well on unseen classes. Previous approaches train the feature pyramid and detection head from scratch, which…

Few-shot classification aims to recognize novel categories with only few labeled images in each class. Existing metric-based few-shot classification algorithms predict categories by comparing the feature embeddings of query images with…

Large-scale pre-trained Vision-Language Models (VLMs) have demonstrated strong few-shot learning capabilities. However, these methods typically learn holistic representations where an image's domain-invariant structure is implicitly…

Most previous few-shot learning algorithms are based on meta-training with fake few-shot tasks as training samples, where large labeled base classes are required. The trained model is also limited by the type of tasks. In this paper we…

Most of the existing deep neural nets on automatic facial expression recognition focus on a set of predefined emotion classes, where the amount of training data has the biggest impact on performance. However, in the standard setting…

Pre-trained Vision-Language Models (VLMs), such as CLIP, have shown enhanced performance across a range of tasks that involve the integration of visual and linguistic modalities. When CLIP is used for depth estimation tasks, the patches,…

Medical vision-language alignment through cross-modal contrastive learning shows promising performance in image-text matching tasks, such as retrieval and zero-shot classification. However, conventional cross-modal contrastive learning…

Segmenting images is critical for visual understanding but demands extensive pixel-level annotations. Foundational models have enabled new paradigms for predicting new classes guided by textual prompts, without annotations from the target…

Vision-language models (VLMs) can learn high-quality representations from a large-scale training dataset of image-text pairs. Prompt learning is a popular approach to fine-tuning VLM to adapt them to downstream tasks. Despite the satisfying…