Related papers: PictSure: Pretraining Embeddings Matters for In-Co…

Image clustering is one of the crucial techniques in multimedia analytics and knowledge discovery. Recently, the Deep clustering method (DC), characterized by its ability to perform feature learning and cluster assignment jointly, surpasses…

Modern supervised semantic segmentation methods are usually finetuned based on the supervised or self-supervised models pre-trained on ImageNet. Recent work shows that transferring the knowledge from CLIP to semantic segmentation via prompt…

In-context learning (ICL) enables large language models to perform few-shot learning by conditioning on labeled examples in the prompt. Despite its flexibility, ICL suffers from instability -- especially as prompt length increases with more…

Verifying the authenticity of AI-generated images presents a growing challenge on social media platforms these days. While vision-language models (VLMs) like CLIP outdo in multimodal representation, their capacity for AI-generated image…

The advent of large pre-trained models has brought about a paradigm shift in both visual representation learning and natural language processing. However, clustering unlabeled images, as a fundamental and classic machine learning problem,…

Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable, but they often struggle in data-scarce settings where insufficient training samples lead to…

Modular approaches that use a different composition of modules for each problem are a promising direction in continual learning (CL). However, searching through the large, discrete space of module compositions is challenging, especially…

Image captioning is a computer vision task that involves generating natural language descriptions for images. This method has numerous applications in various domains, including image retrieval systems, medicine, and various industries.…

Image captioning evaluation remains a significant challenge, as vision-language models evolve toward more challenging capabilities such as generating long-form and context-rich descriptions. State-of-the-art evaluation metrics involve…

Implicit in-context learning (ICL) has newly emerged as a promising paradigm that simulates ICL behaviors in the representation space of Large Language Models (LLMs), aiming to attain few-shot performance at zero-shot cost. However,…

Few-shot class-incremental learning (FSCIL) aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data. However, many of these works lack effective exploration of prior knowledge, rendering them…

Many meta-learning approaches for few-shot learning rely on simple base learners such as nearest-neighbor classifiers. However, even in the few-shot regime, discriminatively trained linear predictors can offer better generalization. We…

Transformers can efficiently learn in-context from example demonstrations. Most existing theoretical analyses studied the in-context learning (ICL) ability of transformers for linear function classes, where it is typically shown that the…

Few-shot class-incremental learning (FSCIL) is challenging due to extremely limited training data; while aiming to reduce catastrophic forgetting and learn new information. We propose Diffusion-FSCIL, a novel approach that employs a…

Unsupervised image classification, or image clustering, aims to group unlabeled images into semantically meaningful categories. Early methods integrated representation learning and clustering within an iterative framework. However, the rise…

Continual learning (CL) is widely regarded as crucial challenge for lifelong AI. However, existing CL benchmarks, e.g. Permuted-MNIST and Split-CIFAR, make use of artificial temporal variation and do not align with or generalize to the…

Despite the advancement of supervised image recognition algorithms, their dependence on the availability of labeled data and the rapid expansion of image categories raise the significant challenge of zero-shot learning. Zero-shot learning…

In this work, we address in-context learning (ICL) for the task of image segmentation, introducing a novel approach that adapts a modern Video Object Segmentation (VOS) technique for visual in-context learning. This adaptation is inspired…

Semi-supervised medical image segmentation has attracted much attention in recent years because of the high cost of medical image annotations. In this paper, we propose a novel Inherent Consistent Learning (ICL) method, aims to learn robust…

Transformer-based multimodal large language models often exhibit in-context learning (ICL) abilities. Motivated by this phenomenon, we ask: how do transformers learn to associate information across modalities from in-context examples? We…