Related papers: Learning to discover and localize visual objects w…

Object category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised…

Open-World Object Detection (OWOD) extends object detection problem to a realistic and dynamic scenario, where a detection model is required to be capable of detecting both known and unknown objects and incrementally learning newly…

We investigate the use of deep neural networks for the novel task of class generic object detection. We show that neural networks originally designed for image recognition can be trained to detect objects within images, regardless of their…

Vision-language alignment learned from image-caption pairs has been shown to benefit tasks like object recognition and detection. Methods are mostly evaluated in terms of how well object class names are learned, but captions also contain…

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…

Many recent studies have shown that deep neural models are vulnerable to adversarial samples: images with imperceptible perturbations, for example, can fool image classifiers. In this paper, we present the first type-specific approach to…

Providing ground truth supervision to train visual models has been a bottleneck over the years, exacerbated by domain shifts which degenerate the performance of such models. This was the case when visual tasks relied on handcrafted features…

Most of the current boundary detection systems rely exclusively on low-level features, such as color and texture. However, perception studies suggest that humans employ object-level reasoning when judging if a particular pixel is a…

This paper addresses unsupervised discovery and localization of dominant objects from a noisy image collection with multiple object classes. The setting of this problem is fully unsupervised, without even image-level annotations or any…

Assessing the blurriness of an object image is fundamentally important to improve the performance for object recognition and retrieval. The main challenge lies in the lack of abundant images with reliable labels and effective learning…

In this paper, we propose a method for keypoint discovery from a 2D image using image-level supervision. Recent works on unsupervised keypoint discovery reliably discover keypoints of aligned instances. However, when the target instances…

Weakly-supervised semantic segmentation under image tags supervision is a challenging task as it directly associates high-level semantic to low-level appearance. To bridge this gap, in this paper, we propose an iterative bottom-up and…

The status quo approach to training object detectors requires expensive bounding box annotations. Our framework takes a markedly different direction: we transfer tracked object boxes from weakly-labeled videos to weakly-labeled images to…

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…

In this work, we study different approaches to self-supervised pretraining of object detection models. We first design a general framework to learn a spatially consistent dense representation from an image, by randomly sampling and…

Although existing semantic segmentation approaches achieve impressive results, they still struggle to update their models incrementally as new categories are uncovered. Furthermore, pixel-by-pixel annotations are expensive and…

We introduce a weakly supervised approach for inferring the property of abstractness of words and expressions in the complete absence of labeled data. Exploiting only minimal linguistic clues and the contextual usage of a concept as…

Visual object localization is the key step in a series of object detection tasks. In the literature, high localization accuracy is achieved with the mainstream strongly supervised frameworks. However, such methods require object-level…

We propose an end-to-end learning framework for segmenting generic objects in both images and videos. Given a novel image or video, our approach produces a pixel-level mask for all "object-like" regions---even for object categories never…

Weakly supervised object detection aims at reducing the amount of supervision required to train detection models. Such models are traditionally learned from images/videos labelled only with the object class and not the object bounding box.…