Related papers: Dual-Stream Spectral Decoupling Distillation for R…

Unsupervised representation learning has proved to be a critical component of anomaly detection/localization in images. The challenges to learn such a representation are two-fold. Firstly, the sample size is not often large enough to learn…

Knowledge distillation is widely adopted in semantic segmentation to reduce the computation cost.The previous knowledge distillation methods for semantic segmentation focus on pixel-wise feature alignment and intra-class feature variation…

Discrete diffusion models (DDMs) have shown powerful generation ability for discrete data modalities like text and molecules. However, their practical application is hindered by inefficient sampling, requiring a large number of sampling…

Device-directed speech detection (DDSD) is a binary classification task that separates the user's queries to a voice assistant (VA) from background speech or side conversations. This is important for achieving naturalistic user experience.…

Model compression through knowledge distillation has seen extensive application in classification and segmentation tasks. However, its potential in image-to-image translation, particularly in image restoration, remains underexplored. To…

Most research in synthetic speech detection (SSD) focuses on improving performance on standard noise-free datasets. However, in actual situations, noise interference is usually present, causing significant performance degradation in SSD…

Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a…

In this paper, we propose a framework for predicting frame errors in the collaborative spectrally congested wireless environments of the DARPA Spectrum Collaboration Challenge (SC2) via a recently collected dataset. We employ distributed…

Knowledge distillation (KD) has been proven to be useful for training compact object detection models. However, we observe that KD is often effective when the teacher model and student counterpart share similar proposal information. This…

Knowledge distillation has shown great success in classification, however, it is still challenging for detection. In a typical image for detection, representations from different locations may have different contributions to detection…

Distribution matching distillation (DMD) facilitates few-step image generation by aligning a distilled student with a reference multi-step teacher. In practice, however, optimizing DMD can reduce sample diversity in few-step synthesis, and…

4D radar super-resolution, which aims to reconstruct sparse and noisy point clouds into dense and geometrically consistent representations, is a foundational problem in autonomous perception. However, existing methods often suffer from high…

Monocular 3D object detection is a promising yet ill-posed task for autonomous vehicles due to the lack of accurate depth information. Cross-modality knowledge distillation could effectively transfer depth information from LiDAR to…

Traditional object detection are ill-equipped for incremental learning. However, fine-tuning directly on a well-trained detection model with only new data will leads to catastrophic forgetting. Knowledge distillation is a straightforward…

Change detection, which aims to detect spatial changes from a pair of multi-temporal images due to natural or man-made causes, has been widely applied in remote sensing, disaster management, urban management, etc. Most existing change…

Score distillation sampling (SDS) demonstrates a powerful capability for text-conditioned 2D image and 3D object generation by distilling the knowledge from learned score functions. However, SDS often suffers from blurriness caused by noisy…

The remarkable breakthroughs in point cloud representation learning have boosted their usage in real-world applications such as self-driving cars and virtual reality. However, these applications usually have an urgent requirement for not…

Cross-modal learning has become a fundamental paradigm for integrating heterogeneous information sources such as images, text, and structured attributes. However, multimodal representations often suffer from modality dominance, redundant…

Facial forgery detection is a crucial but extremely challenging topic, with the fast development of forgery techniques making the synthetic artefact highly indistinguishable. Prior works show that by mining both spatial and frequency…

Person re-identification is a key challenge for surveillance across multiple sensors. Prompted by the advent of powerful deep learning models for visual recognition, and inexpensive RGB-D cameras and sensor-rich mobile robotic platforms,…