Related papers: COLLAGE: Adaptive Fusion-based Retrieval for Augme…

Deep neural networks require a large amount of labeled training data during supervised learning. However, collecting and labeling so much data might be infeasible in many cases. In this paper, we introduce a source-target selective joint…

We propose a novel framework for image clustering that incorporates joint representation learning and clustering. Our method consists of two heads that share the same backbone network - a "representation learning" head and a "clustering"…

Class-incremental learning is a challenging problem, where the goal is to train a model that can classify data from an increasing number of classes over time. With the advancement of vision-language pre-trained models such as CLIP, they…

Image retrieval targets to find images from a database that are visually similar to the query image. Two-stage methods following retrieve-and-rerank paradigm have achieved excellent performance, but their separate local and global modules…

In-context learning (ICL) has emerged as a powerful paradigm for Large Visual Language Models (LVLMs), enabling them to leverage a few examples directly from input contexts. However, the effectiveness of this approach is heavily reliant on…

In this paper we explore few-shot imitation learning for control problems, which involves learning to imitate a target policy by accessing a limited set of offline rollouts. This setting has been relatively under-explored despite its…

The goal of few-shot classification is to classify new categories with few labeled examples within each class. Nowadays, the excellent performance in handling few-shot classification problems is shown by metric-based meta-learning methods.…

Training machine learning models on massive datasets incurs substantial computational costs. To alleviate such costs, there has been a sustained effort to develop data-efficient training methods that can carefully select subsets of the…

The purpose of few-shot recognition is to recognize novel categories with a limited number of labeled examples in each class. To encourage learning from a supplementary view, recent approaches have introduced auxiliary semantic modalities…

The novelty of this study consists in a multi-modality approach to scene classification, where image and audio complement each other in a process of deep late fusion. The approach is demonstrated on a difficult classification problem,…

The effectiveness of Retrieval-Augmented Generation (RAG) is highly dependent on how documents are chunked, that is, segmented into smaller units for indexing and retrieval. Yet, commonly used "one-size-fits-all" approaches often fail to…

We introduce MoRAG, a novel multi-part fusion based retrieval-augmented generation strategy for text-based human motion generation. The method enhances motion diffusion models by leveraging additional knowledge obtained through an improved…

Accurate cloud property retrieval is vital for understanding cloud behavior and its impact on climate, including applications in weather forecasting, climate modeling, and estimating Earth's radiation balance. The Independent Pixel…

We present a comprehensive framework for enhancing Retrieval-Augmented Generation (RAG) systems through dynamic retrieval strategies and reinforcement fine-tuning. This approach significantly improves large language models on…

The strong demand for efficient and performant deployment of Deep Learning (DL) applications prompts the rapid development of a rich DL ecosystem. To keep up with this fast advancement, it is crucial for modern DL frameworks to efficiently…

Imitation learning is the problem of recovering an expert policy without access to a reward signal. Behavior cloning and GAIL are two widely used methods for performing imitation learning. Behavior cloning converges in a few iterations but…

We introduce supervised contrastive active learning (SCAL) and propose efficient query strategies in active learning based on the feature similarity (featuresim) and principal component analysis based feature-reconstruction error (fre) to…

Traditional nearest points methods use all the samples in an image set to construct a single convex or affine hull model for classification. However, strong artificial features and noisy data may be generated from combinations of training…

Collage and packing techniques are widely used to organize geometric shapes into cohesive visual representations, facilitating the representation of visual features holistically, as seen in image collages and word clouds. Traditional…

Few-shot learning has been proposed and rapidly emerging as a viable means for completing various tasks. Many few-shot models have been widely used for relation learning tasks. However, each of these models has a shortage of capturing a…