Related papers: Subobject-level Image Tokenization
Superpixels have become very popular in many computer vision applications. Nevertheless, they remain underexploited since the superpixel decomposition may produce irregular and non stable segmentation results due to the dependency to the…
We propose a novel method for unsupervised semantic image segmentation based on mutual information maximization between local and global high-level image features. The core idea of our work is to leverage recent progress in self-supervised…
We present a novel end-to-end single-shot method that segments countable object instances (things) as well as background regions (stuff) into a non-overlapping panoptic segmentation at almost video frame rate. Current state-of-the-art…
Semi-supervised semantic segmentation methods leverage unlabeled data by pseudo-labeling them. Thus the success of these methods hinges on the reliablility of the pseudo-labels. Existing methods mostly choose high-confidence pixels in an…
Training convolutional networks for semantic segmentation requires per-pixel ground truth labels, which are very time consuming and hence costly to obtain. Therefore, in this work, we research and develop a hierarchical deep network…
In this paper, we propose a novel self-supervised representation learning method, Self-EMD, for object detection. Our method directly trained on unlabeled non-iconic image dataset like COCO, instead of commonly used iconic-object image…
Object detection when provided image-level labels instead of instance-level labels (i.e., bounding boxes) during training is an important problem in computer vision, since large scale image datasets with instance-level labels are extremely…
While there has been significant progress in solving the problems of image pixel labeling, object detection and scene classification, existing approaches normally address them separately. In this paper, we propose to tackle these problems…
Enlarging input images is a straightforward and effective approach to promote small object detection. However, simple image enlargement is significantly expensive on both computations and GPU memory. In fact, small objects are usually…
The goal of unpaired image captioning (UIC) is to describe images without using image-caption pairs in the training phase. Although challenging, we except the task can be accomplished by leveraging a training set of images aligned with…
The Segment Anything Model (SAM) excels at generating precise object masks from input prompts but lacks semantic awareness, failing to associate its generated masks with specific object categories. To address this limitation, we propose…
Almost all existing deep learning approaches for semantic segmentation tackle this task as a pixel-wise classification problem. Yet humans understand a scene not in terms of pixels, but by decomposing it into perceptual groups and…
Most of the existing semantic segmentation approaches with image-level class labels as supervision, highly rely on the initial class activation map (CAM) generated from the standard classification network. In this paper, a novel…
Semi-supervised learning aims to leverage numerous unlabeled data to improve the model performance. Current semi-supervised 3D object detection methods typically use a teacher to generate pseudo labels for a student, and the quality of the…
We introduce SPARse Fine-grained Contrastive Alignment (SPARC), a simple method for pretraining more fine-grained multimodal representations from image-text pairs. Given that multiple image patches often correspond to single words, we…
Although deep learning greatly improves the performance of semantic segmentation, its success mainly lies in object central areas without accurate edges. As superpixels are a popular and effective auxiliary to preserve object edges, in this…
Weakly supervised segmentation requires assigning a label to every pixel based on training instances with partial annotations such as image-level tags, object bounding boxes, labeled points and scribbles. This task is challenging, as coarse…
Weakly supervised semantic segmentation (WSSS) aims to bypass the need for laborious pixel-level annotation by using only image-level annotation. Most existing methods rely on Class Activation Maps (CAM) to derive pixel-level pseudo-labels…
Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely on external models to…
While significant attention has been recently focused on designing supervised deep semantic segmentation algorithms for vision tasks, there are many domains in which sufficient supervised pixel-level labels are difficult to obtain. In this…