Related papers: Finding Distributed Object-Centric Properties in S…

Open-vocabulary object detection aims to recognize objects from an open set of categories, which leverages vision-language models (VLMs) pre-trained on large-scale image-text data. The cooperative paradigm combines an object detector with a…

Camouflaged object detection (COD) and salient object detection (SOD) are two distinct yet closely-related computer vision tasks widely studied during the past decades. Though sharing the same purpose of segmenting an image into binary…

Since Transformer has found widespread use in NLP, the potential of Transformer in CV has been realized and has inspired many new approaches. However, the computation required for replacing word tokens with image patches for Transformer…

Self-supervised learning (SSL) has emerged as a powerful technique for learning visual representations. While recent SSL approaches achieve strong results in global image understanding, they are limited in capturing the structured…

Vision Transformers (ViTs) have demonstrated remarkable performance across a wide range of vision tasks. In particular, self-distillation frameworks such as DINO have contributed significantly to these advances. Within such frameworks,…

Convolutional neural network (CNN) has led to significant progress in object detection. In order to detect the objects in various sizes, the object detectors often exploit the hierarchy of the multi-scale feature maps called feature…

Over the past decade, deep neural networks (DNNs) have demonstrated remarkable performance in a variety of applications. As we try to solve more advanced problems, increasing demands for computing and power resources has become inevitable.…

Self-Supervised Learning (SSL) has emerged as a promising approach in computer vision, enabling networks to learn meaningful representations from large unlabeled datasets. SSL methods fall into two main categories: instance discrimination…

Vision Transformers (ViTs) lack the hierarchical inductive biases inherent to Convolutional Neural Networks (CNNs), theoretically allowing them to maintain high-dimensional representations throughout all layers. However, recent observations…

In this work a novel approach for weakly supervised object detection that incorporates pointwise mutual information is presented. A fully convolutional neural network architecture is applied in which the network learns one filter per object…

Automatic polyp segmentation is crucial for improving the clinical identification of colorectal cancer (CRC). While Deep Learning (DL) techniques have been extensively researched for this problem, current methods frequently struggle with…

We propose global context vision transformer (GC ViT), a novel architecture that enhances parameter and compute utilization for computer vision. Our method leverages global context self-attention modules, joint with standard local…

Vision Transformers (ViTs) have demonstrated strong performance across a range of computer vision tasks by modeling long-range spatial interactions via self-attention. However, channel-wise mixing in ViTs remains static, relying on fixed…

We propose the Compact Clustering Attention (COCA) layer, an effective building block that introduces a hierarchical strategy for object-centric representation learning, while solving the unsupervised object discovery task on single images.…

We present an approach to efficiently and effectively adapt a masked image modeling (MIM) pre-trained vanilla Vision Transformer (ViT) for object detection, which is based on our two novel observations: (i) A MIM pre-trained vanilla ViT…

Reusable model design becomes desirable with the rapid expansion of computer vision and machine learning applications. In this paper, we focus on the reusability of pre-trained deep convolutional models. Specifically, different from…

Localizing objects in image collections without supervision can help to avoid expensive annotation campaigns. We propose a simple approach to this problem, that leverages the activation features of a vision transformer pre-trained in a…

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…

While deep neural networks have made remarkable progress in various vision tasks, their performance typically deteriorates when tested in out-of-distribution (OOD) scenarios. Many OOD methods focus on extracting domain-invariant features…

Convolutional Neural Networks (CNNs) excel in local spatial pattern recognition. For many vision tasks, such as object recognition and segmentation, salient information is also present outside CNN's kernel boundaries. However, CNNs struggle…