相关论文: From Saliency to DINO: Saliency-guided Vision Tran…

Fine-grained visual classification (FGVC) is a challenging computer vision problem, where the task is to automatically recognise objects from subordinate categories. One of its main difficulties is capturing the most discriminative…

Vision Transformers (ViTs) emerge to achieve impressive performance on many data-abundant computer vision tasks by capturing long-range dependencies among local features. However, under few-shot learning (FSL) settings on small datasets…

Learning with little data is challenging but often inevitable in various application scenarios where the labeled data is limited and costly. Recently, few-shot learning (FSL) gained increasing attention because of its generalizability of…

Shortcut learning is common but harmful to deep learning models, leading to degenerated feature representations and consequently jeopardizing the model's generalizability and interpretability. However, shortcut learning in the widely used…

Self-supervision has shown outstanding results for natural language processing, and more recently, for image recognition. Simultaneously, vision transformers and its variants have emerged as a promising and scalable alternative to…

Vision Transformer (ViT) has prevailed in computer vision tasks due to its strong long-range dependency modelling ability. \textcolor{blue}{However, its large model size and weak local feature modeling ability hinder its application in real…

Recent self-supervised Vision Transformers (ViTs), such as DINOv3, provide rich feature representations for dense vision tasks. This study investigates the intrinsic few-shot semantic segmentation (FSS) capabilities of frozen DINOv3…

Many models of visual attention have been proposed so far. Traditional bottom-up models, like saliency models, fail to replicate human gaze patterns, and deep gaze prediction models lack biological plausibility due to their reliance on…

Vision-based object tracking has boosted extensive autonomous applications for unmanned aerial vehicles (UAVs). However, the dynamic changes in flight maneuver and viewpoint encountered in UAV tracking pose significant difficulties, e.g. ,…

Current non-rigid object keypoint detectors perform well on a chosen kind of species and body parts, and require a large amount of labelled keypoints for training. Moreover, their heatmaps, tailored to specific body parts, cannot recognize…

Humans possess remarkable ability to accurately classify new, unseen images after being exposed to only a few examples. Such ability stems from their capacity to identify common features shared between new and previously seen images while…

We present SKD, a novel keypoint detector that uses saliency to determine the best candidates from a point cloud for tasks such as registration and reconstruction. The approach can be applied to any differentiable deep learning descriptor…

While previous CNN-based models have exhibited promising results for salient object detection (SOD), their ability to explore global long-range dependencies is restricted. Our previous work, the Visual Saliency Transformer (VST), addressed…

The few-shot learning ability of vision transformers (ViTs) is rarely investigated though heavily desired. In this work, we empirically find that with the same few-shot learning frameworks, \eg~Meta-Baseline, replacing the widely used CNN…

Video salient object detection models trained on pixel-wise dense annotation have achieved excellent performance, yet obtaining pixel-by-pixel annotated datasets is laborious. Several works attempt to use scribble annotations to mitigate…

Although vision Transformers have achieved excellent performance as backbone models in many vision tasks, most of them intend to capture global relations of all tokens in an image or a window, which disrupts the inherent spatial and local…

Existing state-of-the-art saliency detection methods heavily rely on CNN-based architectures. Alternatively, we rethink this task from a convolution-free sequence-to-sequence perspective and predict saliency by modeling long-range…

Recent works in self-supervised learning have shown impressive results on single-object images, but they struggle to perform well on complex multi-object images as evidenced by their poor visual grounding. To demonstrate this concretely, we…

LiDAR semantic segmentation models are typically trained from random initialization as universal pre-training is hindered by the lack of large, diverse datasets. Moreover, most point cloud segmentation architectures incorporate custom…

Self-supervised Vision Transformers (ViTs) like DINO show an emergent ability to discover objects, typically observed in [CLS] token attention maps of the final layer. However, these maps often contain spurious activations resulting in poor…