TDANet: Target-Directed Attention Network For Object-Goal Visual Navigation With Zero-Shot Ability
- URL: http://arxiv.org/abs/2404.08353v1
- Date: Fri, 12 Apr 2024 09:44:18 GMT
- Title: TDANet: Target-Directed Attention Network For Object-Goal Visual Navigation With Zero-Shot Ability
- Authors: Shiwei Lian, Feitian Zhang,
- Abstract summary: A target-directed attention network (TDANet) is proposed to learn the end-to-end object-goal visual navigation policy.
TDANet features a novel target attention (TA) module that learns both the spatial and semantic relationships among objects to help TDANet focus on the most relevant observed objects to the target.
To evaluate the navigation performance of TDANet, extensive experiments are conducted in the AI2-THOR embodied AI environment.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The generalization of the end-to-end deep reinforcement learning (DRL) for object-goal visual navigation is a long-standing challenge since object classes and placements vary in new test environments. Learning domain-independent visual representation is critical for enabling the trained DRL agent with the ability to generalize to unseen scenes and objects. In this letter, a target-directed attention network (TDANet) is proposed to learn the end-to-end object-goal visual navigation policy with zero-shot ability. TDANet features a novel target attention (TA) module that learns both the spatial and semantic relationships among objects to help TDANet focus on the most relevant observed objects to the target. With the Siamese architecture (SA) design, TDANet distinguishes the difference between the current and target states and generates the domain-independent visual representation. To evaluate the navigation performance of TDANet, extensive experiments are conducted in the AI2-THOR embodied AI environment. The simulation results demonstrate a strong generalization ability of TDANet to unseen scenes and target objects, with higher navigation success rate (SR) and success weighted by length (SPL) than other state-of-the-art models.
Related papers
- Aligning Knowledge Graph with Visual Perception for Object-goal Navigation [16.32780793344835]
We propose the Aligning Knowledge Graph with Visual Perception (AKGVP) method for object-goal navigation.
Our approach introduces continuous modeling of the hierarchical scene architecture and leverages visual-language pre-training to align natural language description with visual perception.
The integration of a continuous knowledge graph architecture and multimodal feature alignment empowers the navigator with a remarkable zero-shot navigation capability.
arXiv Detail & Related papers (2024-02-29T06:31:18Z) - Zero-Shot Object Goal Visual Navigation With Class-Independent Relationship Network [3.0820097046465285]
"Zero-shot" means that the target the agent needs to find is not trained during the training phase.
We propose the Class-Independent Relationship Network (CIRN) to address the issue of coupling navigation ability with target features during training.
Our method outperforms the current state-of-the-art approaches in the zero-shot object goal visual navigation task.
arXiv Detail & Related papers (2023-10-15T16:42:14Z) - Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
Unsupervised object discovery is promising due to its ability to discover objects in a generic manner.
We design a semantic-guided self-supervised learning model to extract high-level semantic features from images.
We introduce Principal Component Analysis (PCA) to localize object regions.
arXiv Detail & Related papers (2023-07-07T04:03:48Z) - Can an Embodied Agent Find Your "Cat-shaped Mug"? LLM-Guided Exploration
for Zero-Shot Object Navigation [58.3480730643517]
We present LGX, a novel algorithm for Language-Driven Zero-Shot Object Goal Navigation (L-ZSON)
Our approach makes use of Large Language Models (LLMs) for this task.
We achieve state-of-the-art zero-shot object navigation results on RoboTHOR with a success rate (SR) improvement of over 27% over the current baseline.
arXiv Detail & Related papers (2023-03-06T20:19:19Z) - Network Comparison Study of Deep Activation Feature Discriminability
with Novel Objects [0.5076419064097732]
State-of-the-art computer visions algorithms have incorporated Deep Neural Networks (DNN) in feature extracting roles, creating Deep Convolutional Activation Features (DeCAF)
This study analyzes the general discriminability of novel object visual appearances encoded into the DeCAF space of six of the leading visual recognition DNN architectures.
arXiv Detail & Related papers (2022-02-08T07:40:53Z) - VTNet: Visual Transformer Network for Object Goal Navigation [36.15625223586484]
We introduce a Visual Transformer Network (VTNet) for learning informative visual representation in navigation.
In a nutshell, VTNet embeds object and region features with their location cues as spatial-aware descriptors.
Experiments in the artificial environment AI2-Thor demonstrate that VTNet significantly outperforms state-of-the-art methods in unseen testing environments.
arXiv Detail & Related papers (2021-05-20T01:23:15Z) - Salient Objects in Clutter [130.63976772770368]
This paper identifies and addresses a serious design bias of existing salient object detection (SOD) datasets.
This design bias has led to a saturation in performance for state-of-the-art SOD models when evaluated on existing datasets.
We propose a new high-quality dataset and update the previous saliency benchmark.
arXiv Detail & Related papers (2021-05-07T03:49:26Z) - Location-Sensitive Visual Recognition with Cross-IOU Loss [177.86369890708457]
This paper proposes a unified solution named location-sensitive network (LSNet) for object detection, instance segmentation, and pose estimation.
Based on a deep neural network as the backbone, LSNet predicts an anchor point and a set of landmarks which together define the shape of the target object.
arXiv Detail & Related papers (2021-04-11T02:17:14Z) - Object Goal Navigation using Goal-Oriented Semantic Exploration [98.14078233526476]
This work studies the problem of object goal navigation which involves navigating to an instance of the given object category in unseen environments.
We propose a modular system called, Goal-Oriented Semantic Exploration' which builds an episodic semantic map and uses it to explore the environment efficiently.
arXiv Detail & Related papers (2020-07-01T17:52:32Z) - Improving Target-driven Visual Navigation with Attention on 3D Spatial
Relationships [52.72020203771489]
We investigate target-driven visual navigation using deep reinforcement learning (DRL) in 3D indoor scenes.
Our proposed method combines visual features and 3D spatial representations to learn navigation policy.
Our experiments, performed in the AI2-THOR, show that our model outperforms the baselines in both SR and SPL metrics.
arXiv Detail & Related papers (2020-04-29T08:46:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.