相关论文: Adaptive Modality Balanced Online Knowledge Distil…
The success of large-scale visual language pretraining (VLP) models has driven widespread adoption of image-text retrieval tasks. However, their deployment on mobile devices remains limited due to large model sizes and computational…
Dense visual prediction tasks, such as detection and segmentation, are crucial for time-critical applications (e.g., autonomous driving and video surveillance). While deep models achieve strong performance, their efficiency remains a…
The widespread use of multi-sensor systems has increased research in multi-view action recognition. While existing approaches in multi-view setups with fully overlapping sensors benefit from consistent view coverage, partially overlapping…
Accurately detecting active objects undergoing state changes is essential for comprehending human interactions and facilitating decision-making. The existing methods for active object detection (AOD) primarily rely on visual appearance of…
It has been revealed that efficient dense image prediction (EDIP) models designed for AI chips, trained using the knowledge distillation (KD) framework, encounter two key challenges, including \emph{maintaining boundary region completeness}…
Most of recent attention-guided feature masking distillation methods perform knowledge transfer via global teacher attention maps without delving into fine-grained clues. Instead, performing distillation at finer granularity is conducive to…
As a general model compression paradigm, feature-based knowledge distillation allows the student model to learn expressive features from the teacher counterpart. In this paper, we mainly focus on designing an effective feature-distillation…
Developing accurate and efficient detectors for drone imagery is challenging due to the inherent complexity of aerial scenes. While some existing methods aim to achieve high accuracy by utilizing larger models, their computational cost is…
Cross-modal Knowledge Distillation has demonstrated promising performance on paired modalities with strong semantic connections, referred to as Symmetric Cross-modal Knowledge Distillation (SCKD). However, implementing SCKD becomes…
3D object detection from multiple image views is a fundamental and challenging task for visual scene understanding. Owing to its low cost and high efficiency, multi-view 3D object detection has demonstrated promising application prospects.…
Accurate brain tumor segmentation is essential for preoperative evaluation and personalized treatment. Multi-modal MRI is widely used due to its ability to capture complementary tumor features across different sequences. However, in…
In the surveillance and defense domain, multi-target detection and classification (MTD) is considered essential yet challenging due to heterogeneous inputs from diverse data sources and the computational complexity of algorithms designed…
Knowledge distillation (KD) is an effective method for compressing models in object detection tasks. Due to limited computational capability, UAV-based object detection (UAV-OD) widely adopt the KD technique to obtain lightweight detectors.…
Deep convolutional neural network with increased number of parameters has achieved improved precision in task of object detection on natural images, where objects of interests are annotated with horizontal boundary boxes. On aerial images…
Efficient object detection methods have recently received great attention in remote sensing. Although deep convolutional networks often have excellent detection accuracy, their deployment on resource-limited edge devices is difficult.…
Detecting 3D objects from multi-view images is a fundamental problem in 3D computer vision. Recently, significant breakthrough has been made in multi-view 3D detection tasks. However, the unprecedented detection performance of these vision…
Multi-view camera-based 3D object detection has become popular due to its low cost, but accurately inferring 3D geometry solely from camera data remains challenging and may lead to inferior performance. Although distilling precise 3D…
Knowledge distillation is an effective method to transfer the knowledge from the cumbersome teacher model to the lightweight student model. Online knowledge distillation uses the ensembled prediction results of multiple student models as…
Multispectral pedestrian detection has been shown to be effective in improving performance within complex illumination scenarios. However, prevalent double-stream networks in multispectral detection employ two separate feature extraction…
Electroencephalography (EEG) is a fundamental modality for cognitive state monitoring in brain-computer interfaces (BCIs). However, it is highly susceptible to intrinsic signal errors and human-induced labeling errors, which lead to label…