Related papers: Adaptive Additive Parameter Updates of Vision Tran…

Multi-view learning (MVL) has gained great success in integrating information from multiple perspectives of a dataset to improve downstream task performance. To make MVL methods more practical in an open-ended environment, this paper…

Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new…

Graph Few-Shot Class-Incremental Learning (GFSCIL) enables models to continually learn from limited samples of novel tasks after initial training on a large base dataset. Existing GFSCIL approaches typically utilize Prototypical Networks…

This work addresses the task of class-incremental weakly supervised object localization (CI-WSOL). The goal is to incrementally learn object localization for novel classes using only image-level annotations while retaining the ability to…

We propose a few-shot adaptation framework, which bridges zero-shot learning and supervised many-shot learning, for semantic indexing of image and video data. Few-shot adaptation provides robust parameter estimation with few training…

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).…

We propose a low-rank adaptation method for training privacy-preserving vision transformer (ViT) models that efficiently freezes pre-trained ViT model weights. In the proposed method, trainable rank decomposition matrices are injected into…

Accurate classification plays a pivotal role in smart agriculture, enabling applications such as crop monitoring, fruit recognition, and pest detection. However, conventional centralized training often requires large-scale data collection,…

Vision transformers (ViTs) have achieved impressive results on various computer vision tasks in the last several years. In this work, we study the capability of frozen ViTs, pretrained only on visual data, to generalize to audio-visual data…

Few-shot class-incremental learning (FSCIL) faces challenges of memorizing old class distributions and estimating new class distributions given few training samples. In this study, we propose a learnable distribution calibration (LDC)…

In many real-world problems, collecting a large number of labeled samples is infeasible. Few-shot learning (FSL) is the dominant approach to address this issue, where the objective is to quickly adapt to novel categories in presence of a…

In the scenario of class-incremental learning (CIL), deep neural networks have to adapt their model parameters to non-stationary data distributions, e.g., the emergence of new classes over time. However, CIL models are challenged by the…

The continual learning literature has rapidly shifted from traditional class incremental learning (CIL) techniques to foundation model (FM)-based CIL methods without a clear understanding of how these newer approaches compare to strong,…

Few-shot, fine-grained classification in computer vision poses significant challenges due to the need to differentiate subtle class distinctions with limited data. This paper presents a novel method that enhances the Contrastive…

Vision Transformers (ViTs) have become one of the dominant architectures in computer vision, and pre-trained ViT models are commonly adapted to new tasks via fine-tuning. Recent works proposed several parameter-efficient transfer learning…

Few-shot classification (FSC) is a fundamental yet challenging task in computer vision that involves recognizing novel classes from limited data. While previous methods have focused on enhancing visual features or incorporating additional…

Class-incremental learning (CIL) enables models to learn new classes progressively while preserving knowledge of previously learned ones. Recent advances in this field have shifted towards parameter-efficient fine-tuning techniques, with…

Continual learning aims to acquire new knowledge while retaining past information. Class-incremental learning (CIL) presents a challenging scenario where classes are introduced sequentially. For video data, the task becomes more complex…

Few-shot segmentation (FSS) aims to segment unseen classes given only a few annotated samples. Existing methods suffer the problem of feature undermining, i.e. potential novel classes are treated as background during training phase. Our…

Model Agnostic Meta-Learning (MAML) is one of the most representative of gradient-based meta-learning algorithms. MAML learns new tasks with a few data samples using inner updates from a meta-initialization point and learns the…