Related papers: Sparse Depth-Guided Attention for Accurate Depth C…

Distilling the structured information captured in feature maps has contributed to improved results for object detection tasks, but requires careful selection of baseline architectures and substantial pre-training. Self-distillation…

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…

Existing depth completion methods are often targeted at a specific sparse depth type and generalize poorly across task domains. We present a method to complete sparse/semi-dense, noisy, and potentially low-resolution depth maps obtained by…

Knowledge distillation extracts general knowledge from a pre-trained teacher network and provides guidance to a target student network. Most studies manually tie intermediate features of the teacher and student, and transfer knowledge…

Diffusion distillation models effectively accelerate reverse sampling by compressing the process into fewer steps. However, these models still exhibit a performance gap compared to their pre-trained diffusion model counterparts, exacerbated…

Reconstructing 3D objects from extremely sparse views is a long-standing and challenging problem. While recent techniques employ image diffusion models for generating plausible images at novel viewpoints or for distilling pre-trained…

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.…

Recent advances in zero-shot monocular depth estimation(MDE) have significantly improved generalization by unifying depth distributions through normalized depth representations and by leveraging large-scale unlabeled data via pseudo-label…

Real-world sensors often produce incomplete, irregular, and noisy point clouds, making point cloud completion increasingly important. However, most existing completion methods rely on large paired datasets for training, which is…

Depth completion aims to recover dense depth maps from sparse depth measurements. It is of increasing importance for autonomous driving and draws increasing attention from the vision community. Most of existing methods directly train a…

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…

Transformer-based architectures have become the de-facto standard models for diverse vision tasks owing to their superior performance. As the size of the models continues to scale up, model distillation becomes extremely important in…

Depth completion upgrades sparse depth measurements into dense depth maps guided by a conventional image. Existing methods for this highly ill-posed task operate in tightly constrained settings and tend to struggle when applied to images…

Self-attention serves as the core foundation of large-scale transformer pretraining, but its quadratic token interaction cost makes inference expensive. Replacing attention with simpler sequential modules is appealing, yet naive…

Despite significant advancements of deep learning-based forgery detectors for distinguishing manipulated deepfake images, most detection approaches suffer from moderate to significant performance degradation with low-quality compressed…

Depth completion aims at predicting dense pixel-wise depth from an extremely sparse map captured from a depth sensor, e.g., LiDARs. It plays an essential role in various applications such as autonomous driving, 3D reconstruction, augmented…

Deep learning models have achieved significant results across various computer vision tasks. However, due to the large number of parameters in these models, deploying them in real-time scenarios is a critical challenge, specifically in…

Unsupervised anomaly detection encompasses diverse applications in industrial settings where a high-throughput and precision is imperative. Early works were centered around one-class-one-model paradigm, which poses significant challenges in…

Training large AI models typically requires large-scale datasets in the machine learning process, making training and parameter-tuning process both time-consuming and costly. Some researchers address this problem by carefully synthesizing a…

Pre-trained language models (e.g., BERT (Devlin et al., 2018) and its variants) have achieved remarkable success in varieties of NLP tasks. However, these models usually consist of hundreds of millions of parameters which brings challenges…