相关论文: Universal Few-shot Learning of Dense Prediction Ta…

Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation, which require dense labeling of the image. While few-shot object detection is about training a model on novel…

Open-world object counting leverages the robust text-image alignment of pre-trained vision-language models (VLMs) to enable counting of arbitrary categories in images specified by textual queries. However, widely adopted naive fine-tuning…

Visual SLAM (Simultaneous Localization and Mapping) methods typically rely on handcrafted visual features or raw RGB values for establishing correspondences between images. These features, while suitable for sparse mapping, often lead to…

Vision transformer has emerged as a new paradigm in computer vision, showing excellent performance while accompanied by expensive computational cost. Image token pruning is one of the main approaches for ViT compression, due to the facts…

Meta-learning has been widely used in recent years in areas such as few-shot learning and reinforcement learning. However, the questions of why and when it is better than other algorithms in few-shot classification remain to be explored. In…

Few-shot semantic segmentation (FSS) aims to enable models to segment novel/unseen object classes using only a limited number of labeled examples. However, current FSS methods frequently struggle with generalization due to incomplete and…

Pre-trained multi-modal vision-language models (VLMs) are becoming increasingly popular due to their exceptional performance on downstream vision applications, particularly in the few- and zero-shot settings. However, selecting the…

Vision Transformers (ViTs) can learn strong image-level representations while their patch representations become less effective for dense prediction during prolonged training. We revisit this dense degradation phenomenon and argue that it…

There is a growing interest in learning a model which could recognize novel classes with only a few labeled examples. In this paper, we propose Temporal Alignment Module (TAM), a novel few-shot learning framework that can learn to classify…

The quadratic computational complexity to the number of tokens limits the practical applications of Vision Transformers (ViTs). Several works propose to prune redundant tokens to achieve efficient ViTs. However, these methods generally…

In this work, we propose a novel meta-learning approach for few-shot classification, which learns transferable prior knowledge across tasks and directly produces network parameters for similar unseen tasks with training samples. Our…

Prompt tuning has become a popular strategy for adapting Vision-Language Models (VLMs) to zero/few-shot visual recognition tasks. Some prompting techniques introduce prior knowledge due to its richness, but when learnable tokens are…

Large vision-language models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding tasks. However, the increasing demand for high-resolution image and long-video understanding results in substantial token counts,…

Self-attention and transformers have been widely used in deep learning. Recent efforts have been devoted to incorporating transformer blocks into different neural architectures, including those with convolutions, leading to various visual…

Estimating the 3D world from 2D monocular images is a fundamental yet challenging task due to the labour-intensive nature of 3D annotations. To simplify label acquisition, this work proposes a novel approach that bridges 2D vision…

Transferring knowledge from one domain to another is of practical importance for many tasks in natural language processing, especially when the amount of available data in the target domain is limited. In this work, we propose a novel…

Recognizing discriminative details such as eyes and beaks is important for distinguishing fine-grained classes since they have similar overall appearances. In this regard, we introduce Task Discrepancy Maximization (TDM), a simple module…

We present DyMU, an efficient, training-free framework that dynamically reduces the computational burden of vision-language models (VLMs) while maintaining high task performance. Our approach comprises two key components. First, Dynamic…

Few-shot Node Classification (FSNC) is a challenge in graph representation learning where only a few labeled nodes per class are available for training. To tackle this issue, meta-learning has been proposed to transfer structural knowledge…

Vision-Language Models (VLMs) have shown remarkable capabilities across diverse visual tasks, including image recognition, video understanding, and Visual Question Answering (VQA) when explicitly trained for these tasks. Despite these…