Related papers: Bridging the Gap between Classification and Locali…

Recent advances in supervised salient object detection has resulted in significant performance on benchmark datasets. Training such models, however, requires expensive pixel-wise annotations of salient objects. Moreover, many existing…

Weakly supervised object localization and semantic segmentation aim to localize objects using only image-level labels. Recently, a new paradigm has emerged by generating a foreground prediction map (FPM) to achieve pixel-level localization.…

Graph classification plays a pivotal role in various domains, including pathology, where images can be represented as graphs. In this domain, images can be represented as graphs, where nodes might represent individual nuclei, and edges…

The primary goal of this paper is to localize objects in a group of semantically similar images jointly, also known as the object co-localization problem. Most related existing works are essentially weakly-supervised, relying prominently on…

Weakly-supervised semantic segmentation aims to reduce labeling costs by training semantic segmentation models using weak supervision, such as image-level class labels. However, most approaches struggle to produce accurate localization maps…

We address a practical yet challenging problem of training robot agents to navigate in an environment following a path described by some language instructions. The instructions often contain descriptions of objects in the environment. To…

This paper proposes a novel transformer-based framework that aims to enhance weakly supervised semantic segmentation (WSSS) by generating accurate class-specific object localization maps as pseudo labels. Building upon the observation that…

Semi-weakly supervised semantic segmentation (SWSSS) aims to train a model to identify objects in images based on a small number of images with pixel-level labels, and many more images with only image-level labels. Most existing SWSSS…

Finding automatically multiple lesions in large images is a common problem in medical image analysis. Solving this problem can be challenging if, during optimization, the automated method cannot access information about the location of the…

Region search is widely used for object localization. Typically, the region search methods project the score of a classifier into an image plane, and then search the region with the maximal score. The recently proposed region search…

Pixel-level labels are particularly expensive to acquire. Hence, pretraining is a critical step to improve models on a task like semantic segmentation. However, prominent algorithms for pretraining neural networks use image-level…

Object counting and localization are key steps for quantitative analysis in large-scale microscopy applications. This procedure becomes challenging when target objects are overlapping, are densely clustered, and/or present fuzzy boundaries.…

Successful deployment of mobile robots in unstructured domains requires an understanding of the environment and terrain to avoid hazardous areas, getting stuck, and colliding with obstacles. Traversability estimation--which predicts where…

Unbiased confidence estimates of neural networks are crucial especially for safety-critical applications. Many methods have been developed to calibrate biased confidence estimates. Though there is a variety of methods for classification,…

Contrastive self-supervised learning has shown impressive results in learning visual representations from unlabeled images by enforcing invariance against different data augmentations. However, the learned representations are often…

When humans describe images they tend to use combinations of nouns and adjectives, corresponding to objects and their associated attributes respectively. To generate such a description automatically, one needs to model objects, attributes…

Image retrieval in realistic scenarios targets large dynamic datasets of unlabeled images. In these cases, training or fine-tuning a model every time new images are added to the database is neither efficient nor scalable. Convolutional…

Weakly supervised object detection (WSOD) using only image-level annotations has attracted growing attention over the past few years. Existing approaches using multiple instance learning easily fall into local optima, because such mechanism…

Semantic segmentation aims to classify every pixel of an input image. Considering the difficulty of acquiring dense labels, researchers have recently been resorting to weak labels to alleviate the annotation burden of segmentation. However,…

Class activation maps are widely used for explaining deep neural networks. Due to its ability to highlight regions of interest, it has evolved in recent years as a key step in weakly supervised learning. A major limitation to the…