相关论文: Fast Object Class Labelling via Speech

An ML-based system for interactive labeling of image datasets is contributed in TensorBoard Projector to speed up image annotation performed by humans. The tool visualizes feature spaces and makes it directly editable by online integration…

Supervised learning based object detection frameworks demand plenty of laborious manual annotations, which may not be practical in real applications. Semi-supervised object detection (SSOD) can effectively leverage unlabeled data to improve…

The labels used to train machine learning (ML) models are of paramount importance. Typically for ML classification tasks, datasets contain hard labels, yet learning using soft labels has been shown to yield benefits for model…

Novel Object Captioning is a zero-shot Image Captioning task requiring describing objects not seen in the training captions, but for which information is available from external object detectors. The key challenge is to select and describe…

Existing machine learning models demonstrate excellent performance in image object recognition after training on a large-scale dataset under full supervision. However, these models only learn to map an image to a predefined class index,…

Huge image data sets are the fundament for the development of the perception of automated driving systems. A large number of images is necessary to train robust neural networks that can cope with diverse situations. A sufficiently large…

Natural language object retrieval is a highly useful yet challenging task for robots in human-centric environments. Previous work has primarily focused on commands specifying the desired object's type such as "scissors" and/or visual…

We tackle the problem of video object codetection by leveraging the weak semantic constraint implied by sentences that describe the video content. Unlike most existing work that focuses on codetecting large objects which are usually salient…

Generalizing Multimodal Large Language Models (MLLMs) to novel video domains is essential for real-world deployment but remains challenging due to the scarcity of labeled data. While In-Context Learning (ICL) offers a training-free…

Capturing the interesting components of an image is a key aspect of image understanding. When a speaker annotates an image, selecting labels that are informative greatly depends on the prior knowledge of a prospective listener. Motivated by…

Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both…

Recent advances in open-vocabulary object detection models will enable Automatic Target Recognition systems to be sustainable and repurposed by non-technical end-users for a variety of applications or missions. New, and potentially nuanced,…

Large amounts of annotated data have become more important than ever, especially since the rise of deep learning techniques. However, manual annotations are costly. We propose a tool that enables researchers to create large, high-quality,…

Manually labeling datasets with object masks is extremely time consuming. In this work, we follow the idea of Polygon-RNN to produce polygonal annotations of objects interactively using humans-in-the-loop. We introduce several important…

The great success that deep models have achieved in the past is mainly owed to large amounts of labeled training data. However, the acquisition of labeled data for new tasks aside from existing benchmarks is both challenging and costly.…

Document images often have intricate layout structures, with numerous content regions (e.g. texts, figures, tables) densely arranged on each page. This makes the manual annotation of layout datasets expensive and inefficient. These…

Much recent work on visual recognition aims to scale up learning to massive, noisily-annotated datasets. We address the problem of scaling- up the evaluation of such models to large-scale datasets with noisy labels. Current protocols for…

An examination of object recognition challenge leaderboards (ILSVRC, PASCAL-VOC) reveals that the top-performing classifiers typically exhibit small differences amongst themselves in terms of error rate/mAP. To better differentiate the top…

This paper proposes an approach for rapid bounding box annotation for object detection datasets. The procedure consists of two stages: The first step is to annotate a part of the dataset manually, and the second step proposes annotations…

Image captioning has received significant attention with remarkable improvements in recent advances. Nevertheless, images in the wild encapsulate rich knowledge and cannot be sufficiently described with models built on image-caption pairs…