English
Related papers

Related papers: CoWs on Pasture: Baselines and Benchmarks for Lang…

200 papers

Co-salient Object Detection (CoSOD) endeavors to replicate the human visual system's capacity to recognize common and salient objects within a collection of images. Despite recent advancements in deep learning models, these models still…

Computer Vision and Pattern Recognition · Computer Science 2024-01-15 Haoke Xiao , Lv Tang , Bo Li , Zhiming Luo , Shaozi Li

Navigating to a specified object in an unknown environment is a fundamental yet challenging capability of embodied intelligence. However, current methods struggle to balance decision frequency with intelligence, resulting in decisions…

The goal of this paper is to perform object detection in satellite imagery with only a few examples, thus enabling users to specify any object class with minimal annotation. To this end, we explore recent methods and ideas from…

Computer Vision and Pattern Recognition · Computer Science 2024-03-11 Xavier Bou , Gabriele Facciolo , Rafael Grompone von Gioi , Jean-Michel Morel , Thibaud Ehret

The zero-shot performance of existing vision-language models (VLMs) such as CLIP is limited by the availability of large-scale, aligned image and text datasets in specific domains. In this work, we leverage two complementary sources of…

Computer Vision and Pattern Recognition · Computer Science 2024-04-05 Oindrila Saha , Grant Van Horn , Subhransu Maji

The human language is one of the most natural interfaces for humans to interact with robots. This paper presents a robot system that retrieves everyday objects with unconstrained natural language descriptions. A core issue for the system is…

Robotics · Computer Science 2017-07-19 Mohit Shridhar , David Hsu

Transfer learning enables the sharing of common knowledge among models for a variety of downstream tasks, but traditional methods suffer in limited training data settings and produce narrow models incapable of effectively generalizing under…

Computer Vision and Pattern Recognition · Computer Science 2023-11-07 Kevin Vogt-Lowell , Noah Lee , Theodoros Tsiligkaridis , Marc Vaillant

In deployment scenarios such as homes and warehouses, mobile robots are expected to autonomously navigate for extended periods, seamlessly executing tasks articulated in terms that are intuitively understandable by human operators. We…

Multimodal pre-trained models, such as CLIP, are popular for zero-shot classification due to their open-vocabulary flexibility and high performance. However, vision-language models, which compute similarity scores between images and class…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Mia Chiquier , Utkarsh Mall , Carl Vondrick

General-purpose robots coexisting with humans in their environment must learn to relate human language to their perceptions and actions to be useful in a range of daily tasks. Moreover, they need to acquire a diverse repertoire of…

Robotics · Computer Science 2022-07-14 Oier Mees , Lukas Hermann , Erick Rosete-Beas , Wolfram Burgard

Compositional Zero-Shot Learning (CZSL) aims to recognize unseen combinations of seen attributes and objects. Current CLIP-based methods in CZSL, despite their advancements, often fail to effectively understand and link the attributes and…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Yun Li , Zhe Liu , Lina Yao

Robot navigation traditionally relies on building an explicit map that is used to plan collision-free trajectories to a desired target. In deformable, complex terrain, using geometric-based approaches can fail to find a path due to…

Robotics · Computer Science 2021-11-19 Adam Polevoy , Craig Knuth , Katie M. Popek , Kapil D. Katyal

Underwater navigation presents several challenges, including unstructured unknown environments, lack of reliable localization systems (e.g., GPS), and poor visibility. Furthermore, good-quality obstacle detection sensors for underwater…

Robotics · Computer Science 2022-12-09 Pengzhi Yang , Haowen Liu , Monika Roznere , Alberto Quattrini Li

Understanding human instructions and accomplishing Vision-Language Navigation tasks in unknown environments is essential for robots. However, existing modular approaches heavily rely on the quality of training data and often exhibit poor…

Robotics · Computer Science 2025-09-30 Yao Wang , Zhirui Sun , Wenzheng Chi , Baozhi Jia , Wenjun Xu , Jiankun Wang

Thanks to the impressive progress of large-scale vision-language pretraining, recent recognition models can classify arbitrary objects in a zero-shot and open-set manner, with a surprisingly high accuracy. However, translating this success…

Computer Vision and Pattern Recognition · Computer Science 2023-04-18 Xinyu Liu , Beiwen Tian , Zhen Wang , Rui Wang , Kehua Sheng , Bo Zhang , Hao Zhao , Guyue Zhou

We present Interactive Gibson Benchmark, the first comprehensive benchmark for training and evaluating Interactive Navigation: robot navigation strategies where physical interaction with objects is allowed and even encouraged to accomplish…

In this paper, we propose Lan-grasp, a novel approach towards more appropriate semantic grasping and placing. We leverage foundation models to equip the robot with a semantic understanding of object geometry, enabling it to identify the…

Contact is at the core of robotic manipulation. At times, it is desired (e.g. manipulation and grasping), and at times, it is harmful (e.g. when avoiding obstacles). However, traditional path planning algorithms focus solely on…

Robotics · Computer Science 2023-09-01 Amber Xie , Youngwoon Lee , Pieter Abbeel , Stephen James

Vision-language models (VLMs) excel in zero-shot recognition but their performance varies greatly across different visual concepts. For example, although CLIP achieves impressive accuracy on ImageNet (60-80%), its performance drops below…

Computer Vision and Pattern Recognition · Computer Science 2024-05-24 Shubham Parashar , Zhiqiu Lin , Tian Liu , Xiangjue Dong , Yanan Li , Deva Ramanan , James Caverlee , Shu Kong

Imitation learning is a popular approach for training visual navigation policies. However, collecting expert demonstrations for legged robots is challenging as these robots can be hard to control, move slowly, and cannot operate…

Artificial Intelligence · Computer Science 2020-03-05 Xinlei Pan , Tingnan Zhang , Brian Ichter , Aleksandra Faust , Jie Tan , Sehoon Ha

Zero-shot learning in Language & Vision is the task of correctly labelling (or naming) objects of novel categories. Another strand of work in L&V aims at pragmatically informative rather than ``correct'' object descriptions, e.g. in…

Computation and Language · Computer Science 2019-06-14 Sina Zarrieß , David Schlangen