Related papers: COCO-Stuff: Thing and Stuff Classes in Context
Instance segmentation in videos, which aims to segment and track multiple objects in video frames, has garnered a flurry of research attention in recent years. In this paper, we present a novel weakly supervised framework with…
A key algorithm for understanding the world is material segmentation, which assigns a label (metal, glass, etc.) to each pixel. We find that a model trained on existing data underperforms in some settings and propose to address this with a…
We present Pix2Cap-COCO, the first panoptic pixel-level caption dataset designed to advance fine-grained visual understanding. To achieve this, we carefully design an automated annotation pipeline that prompts GPT-4V to generate…
A comprehensive semantic understanding of a scene is important for many applications - but in what space should diverse semantic information (e.g., objects, scene categories, material types, texture, etc.) be grounded and what should be its…
For best performance, today's semantic segmentation methods use large and carefully labeled datasets, requiring expensive annotation budgets. In this work, we show that coarse annotation is a low-cost but highly effective alternative for…
Humans rely on properties of the materials that make up objects to guide our interactions with them. Grasping smooth materials, for example, requires care, and softness is an ideal property for fabric used in bedding. Even when these…
The recurring context in which objects appear holds valuable information that can be employed to predict their existence. This intuitive observation indeed led many researchers to endow appearance-based detectors with explicit reasoning…
In this paper, we study the problem of semantic part segmentation for animals. This is more challenging than standard object detection, object segmentation and pose estimation tasks because semantic parts of animals often have similar…
Scene labeling is the problem of assigning an object label to each pixel. It unifies the image segmentation and object recognition problems. The importance of using contextual information in scene labeling frameworks has been widely…
In most modern object detection pipelines, the detection proposals are processed independently given the feature map. Therefore, they overlook the underlying relationships between objects and the surrounding background, which could have…
The place recognition problem comprises two distinct subproblems; recognizing a specific location in the world ("specific" or "ordinary" place recognition) and recognizing the type of place (place categorization). Both are important…
We present an approach for jointly matching and segmenting object instances of the same category within a collection of images. In contrast to existing algorithms that tackle the tasks of semantic matching and object co-segmentation in…
In this paper, we present a semi supervised deep quick learning framework for instance detection and pixel-wise semantic segmentation of images in a dense clutter of items. The framework can quickly and incrementally learn novel items in an…
Detecting objects occupying only small areas in an image is difficult, even for humans. Therefore, annotating small-size object instances is hard and thus costly. This study questions common sense by asking the following: is annotating…
This paper aims to reduce the time to annotate images for panoptic segmentation, which requires annotating segmentation masks and class labels for all object instances and stuff regions. We formulate our approach as a collaborative process…
The use of explicit object detectors as an intermediate step to image captioning - which used to constitute an essential stage in early work - is often bypassed in the currently dominant end-to-end approaches, where the language model is…
Instance segmentation is essential for applications such as automated monitoring of plant health, growth, and yield. However, extensive effort is required to create large-scale datasets with pixel-level annotations of each object instance…
To what degree and under what conditions do VLMs rely on scene context when generating references to objects? To address this question, we introduce the $\textit{Common Objects Out-of-Context (COOCo)}$ dataset and conduct experiments on…
Many open-world applications require the detection of novel objects, yet state-of-the-art object detection and instance segmentation networks do not excel at this task. The key issue lies in their assumption that regions without any…
This paper studies the problem of learning semantic segmentation from image-level supervision only. Current popular solutions leverage object localization maps from classifiers as supervision signals, and struggle to make the localization…