28 accepted papers
Attention-based multiple instance learning (MIL) has emerged as a powerful framework for whole slide image (WSI) diagnosis, leveraging attention to aggregate instance-level features into bag-level predictions. Despite this success, we find that such methods exhibit a new failure mode: unstable atte…
Dataset distillation (DD) aims to synthesize compact training sets that enable models to achieve high accuracy with significantly fewer samples. Recent diffusion-based DD methods commonly introduce semantic guidance through late-stage cross-attention, where textual prompts tend to dominate the gener
A clean map of the surrounding environment is essential for autonomous driving systems to ensure reliable localization and safe path planning. However, the existence of dynamic objects introduces ghost traces into the map, significantly degrading its quality. To address this issue, we propose Enhanc…
The robotic peg-in-hole assembly task remains challenging. Traditional force control methods struggle with complex parameter identification and contact state analysis, while deep reinforcement learning(DRL) suffers from low efficiency and poor adaptability. To address these shortcomings and to capit
Point-to-point navigation is an important ability for spherical robots. Traditional methods usually use a planner and a tracker for short-range target control. However, this hierarchical method suffers from a mismatch issue. In this work, we propose an end-to-end controller based on reinforcement le
Generative models have shown great potential in trajectory planning. Recent studies demonstrate that anchor-guided generative models are effective in modeling the uncertainty of driving behaviors and improving overall performance. However, these methods rely on discrete anchor vocabularies that must
Wide-angle videos in few-shot action recognition (FSAR) effectively express actions within specific scenarios. However, without a global understanding of both subjects and background, recognizing actions in such samples remains challenging because of the background distractions. Receptance Weighted
End-to-end autonomous driving policies based on Imitation Learning (IL) often struggle in closed-loop execution due to the misalignment between inadequate open-loop training objectives and real driving requirements. While Reinforcement Learning (RL) offers a solution by directly optimizing driving g
Achieving fully autonomous driving systems requires learning rational decisions in a wide span of scenarios, including safety-critical and out-of-distribution ones. However, such cases are underrepresented in real-world corpus collected by human experts. To complement for the lack of data diversity,
The significance of cross-view 3D geometric modeling capabilities for autonomous driving is self-evident, yet existing Vision-Language Models (VLMs) inherently lack this capability, resulting in their mediocre performance. While some promising approaches attempt to mitigate this by constructing Q&A
Vision-Language Models (VLMs) show promise for autonomous driving, yet their struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning. To overcome this, we introduce AgentThink , a pioneering unified framewor
This letter proposes a novel linear online identification framework for the spherical robot to address the modeling difficulties posed by nonlinearity and time-varying characteristics. Firstly, the Koopman theory is applied to the spherical robot to build a linear model to approximate the nonlineari
We propose a novel continual self-supervised learning method (CSSL) considering medical domain knowledge in chest CT images. Our approach addresses the challenge of sequential learning by effectively capturing the relationship between previously learned knowledge and new information at different sta…
Dataset distillation (DD) condenses large datasets into compact yet informative substitutes, preserving performance comparable to the original dataset while reducing storage, transmission costs, and computational consumption. However, previous DD methods mainly focus on distilling information from i…
Dataset distillation is an effective technique for reducing the cost and complexity of model training while maintaining performance by compressing large datasets into smaller, more efficient versions. In this paper, we present a novel generative dataset distillation method that can improve the accur…
To address the computational and storage challenges posed by large-scale datasets in deep learning, dataset distillation has been proposed to synthesize a compact dataset that replaces the original while maintaining comparable model performance. Unlike optimization-based approaches that require cost…
This paper proposes a new turning theory for spherical robots, which better describes the turning mechanism of spherical robots under turning constraints, using a pendulum-driven spherical robot as an example. Compared to the previous turning theory, the new theory shows greater alignment with real-
In few-shot action recognition (FSAR), long sub-sequences of video naturally express entire actions more effectively. However, the high computational complexity of mainstream Transformer-based methods limits their application. Recent Mamba demonstrates efficiency in modeling long sequences, but dire…
Capsule endoscopes, predominantly serving diagnostic functions, provide lucid internal imagery but are devoid of surgical or therapeutic capabilities. Consequently, despite lesion detection, physicians frequently resort to traditional endoscopic or open surgical procedures for treatment, resulting i…
Model Predictive Control (MPC)-based trajectory planning has been widely used in robotics, and incorporating Control Barrier Function (CBF) constraints into MPC can greatly improve its obstacle avoidance efficiency. Unfortunately, traditional optimizers are resource-consuming and slow to solve such
Taste sensation can be objectively measured using electroencephalography (EEG) or electromyography (EMG). How-ever, it is still challenging to effectively utilize the complementary information from EEG and EMG signals in taste sensation recognition. This paper proposes a bimodal fusion network (Bi-F…
In this letter, a general robust reference path selection method (RPSM) that can be integrated into current existing motion planning algorithms is proposed to improve the mobile performance of autonomous patrol robots. The proposed RPSM maintains a dynamic array of path candidates that contains newl
A spherical robot is a nonlinear, nonholonomic, and unstable system which increases the difficulty of the direction and trajectory tracking problem. In this study, we propose a new direction controller Hierarchical Terminal Sliding Mode Controller (HTSMC), an instruction planning controller called M
One controller cannot work on multiple and unknown terrains in the velocity control of the spherical robot, because the dynamic models of the robot vary on different terrains, and unmodeled dynamics and uncertainties exist in estimated dynamic models. Based on the above problem, a new velocity contr
The global outbreak of the Coronavirus 2019 (COVID-19) has overloaded worldwide healthcare systems. Computer-aided diagnosis for COVID-19 fast detection and patient triage is becoming critical. This paper proposes a novel self-knowledge distillation based self-supervised learning method for COVID-19…
This paper proposes a novel self-supervised learning method for learning better representations with small batch sizes. Many self-supervised learning methods based on certain forms of the siamese network have emerged and received significant attention. However, these methods need to use large batch…
In this paper, a fuzzy PID controller based on yaw angle prediction is applied to design an attitude controller for a spherical rolling robot. The robot consists of a 2-DOF pendulum located inside a spherical shell with freedom to rotate about the transversal and longitudinal axis. The proposed cont…
In image captioning, the typical attention mechanisms are arduous to identify the equivalent visual signals especially when predicting highly abstract words. This phenomenon is known as the semantic gap between vision and language. This problem can be overcome by providing semantic attributes that a…