Related papers: Object-Category Aware Reinforcement Learning

For an object classification system, the most critical obstacles towards real-world applications are often caused by large intra-class variability, arising from different lightings, occlusion and corruption, in limited sample sets. Most…

Classifying fine-grained visual concepts under open-world settings, i.e., without a predefined label set, demands models to be both accurate and specific. Recent reasoning Large Multimodal Models (LMMs) exhibit strong visual understanding…

Analyzing complex scenes with Deep Neural Networks is a challenging task, particularly when images contain multiple objects that partially occlude each other. Existing approaches to image analysis mostly process objects independently and do…

Using Reinforcement Learning (RL) to learn new robotic tasks from scratch is often inefficient. Leveraging prior knowledge has the potential to significantly enhance learning efficiency, which, however, raises two critical challenges: how…

Reasoning abilities, especially those for solving complex math problems, are crucial components of general intelligence. Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning…

Document layout analysis aims to detect and categorize structural elements (e.g., titles, tables, figures) in scanned or digital documents. Popular methods often rely on high-quality Optical Character Recognition (OCR) to merge visual…

Due to their adaptability and mobility, Unmanned Aerial Vehicles (UAVs) are becoming increasingly essential for wireless network services, particularly for data harvesting tasks. In this context, Artificial Intelligence (AI)-based…

Despite the broad application of deep reinforcement learning (RL), transferring and adapting the policy to unseen but similar environments is still a significant challenge. Recently, the language-conditioned policy is proposed to facilitate…

Hierarchical reinforcement learning has focused on discovering temporally extended actions, such as options, that can provide benefits in problems requiring extensive exploration. One promising approach that learns these options end-to-end…

Similar to humans perceiving visual scenes as objects, Object-Centric Learning (OCL) can abstract dense images or videos into sparse object-level features. Transformer-based OCL handles complex textures well due to the decoding guidance of…

Out-of-Distribution (OoD) segmentation is critical for safety-sensitive applications like autonomous driving. However, existing mask-based methods often suffer from boundary imprecision, inconsistent anomaly scores within objects, and false…

Object-Centric Learning (OCL) represents dense image or video pixels as sparse object features. Representative methods utilize discrete representation composed of Variational Autoencoder (VAE) template features to suppress pixel-level…

Multi-objective reinforcement learning (MORL) is an extension of ordinary, single-objective reinforcement learning (RL) that is applicable to many real-world tasks where multiple objectives exist without known relative costs. We study the…

Large-scale pre-trained Vision-Language Models (VLMs) have demonstrated strong few-shot learning capabilities. However, these methods typically learn holistic representations where an image's domain-invariant structure is implicitly…

Object-goal visual navigation aims to reach a specific target object using egocentric visual observations. Recent deep reinforcement learning (DRL) approaches have achieved promising success rates but often neglect collisions during…

Unsupervised out-of-distribution (OOD) Detection aims to separate the samples falling outside the distribution of training data without label information. Among numerous branches, contrastive learning has shown its excellent capability of…

Multi-Object Tracking (MOT) is a crucial computer vision task that aims to predict the bounding boxes and identities of objects simultaneously. While state-of-the-art methods have made remarkable progress by jointly optimizing the…

Camouflaged object detection (COD) primarily relies on semantic or instance segmentation methods. While these methods have made significant advancements in identifying the contours of camouflaged objects, they may be inefficient or…

The rise of multi-modal search requests from users has highlighted the importance of multi-modal retrieval (i.e. image-to-text or text-to-image retrieval), yet the more complex task of image-to-multi-modal retrieval, crucial for many…

This paper proposes a scalable and straightforward pre-training paradigm for efficient visual conceptual representation called occluded image contrastive learning (OCL). Our OCL approach is simple: we randomly mask patches to generate…