Related papers: SAM-Guided Masked Token Prediction for 3D Scene Un…
This work proposes a semantic segmentation network that produces high-quality uncertainty estimates in a single forward pass. We exploit general representations from foundation models and unlabelled datasets through a Masked Image Modeling…
Segmenting 3D objects into parts is a long-standing challenge in computer vision. To overcome taxonomy constraints and generalize to unseen 3D objects, recent works turn to open-world part segmentation. These approaches typically transfer…
Depth estimation and scene parsing are two particularly important tasks in visual scene understanding. In this paper we tackle the problem of simultaneous depth estimation and scene parsing in a joint CNN. The task can be typically treated…
Automated nodule segmentation is essential for computer-assisted diagnosis in ultrasound images. Nevertheless, most existing methods depend on precise pixel-level annotations by medical professionals, a process that is both costly and…
Leveraging the capabilities of Knowledge Distillation (KD) strategies, we devise a strategy to fight the recent retraction of face recognition datasets. Given a pretrained Teacher model trained on a real dataset, we show that carefully…
Vision-based 3D semantic occupancy prediction is a critical task in 3D vision that integrates volumetric 3D reconstruction with semantic understanding. Existing methods, however, often rely on modular pipelines. These modules are typically…
Knowledge distillation is an effective method for training small and efficient deep learning models. However, the efficacy of a single method can degenerate when transferring to other tasks, modalities, or even other architectures. To…
We introduce SAMPro3D for zero-shot instance segmentation of 3D scenes. Given the 3D point cloud and multiple posed RGB-D frames of 3D scenes, our approach segments 3D instances by applying the pretrained Segment Anything Model (SAM) to 2D…
Large-scale datasets are usually required to train deep neural networks, but it increases the computational complexity hindering the practical applications. Recently, dataset distillation for images and texts has been attracting a lot of…
Semantic segmentation of 3D LiDAR point clouds is important in urban remote sensing for understanding real-world street environments. This task, by projecting LiDAR point clouds and 3D semantic labels as sparse maps, can be reformulated as…
Knowledge distillation is a method of transferring the knowledge from a pretrained complex teacher model to a student model, so a smaller network can replace a large teacher network at the deployment stage. To reduce the necessity of…
3D object detection is one of the fundamental perception tasks for autonomous vehicles. Fulfilling such a task with a 4D millimeter-wave radar is very attractive since the sensor is able to acquire 3D point clouds similar to Lidar while…
There are various optimization techniques in the realm of 3D, including point cloud-based approaches that use mesh, texture, and voxels which optimize how you store, and how do calculate in 3D. These techniques employ methods such as…
The extensive amounts of data required for training deep neural networks pose significant challenges on storage and transmission fronts. Dataset distillation has emerged as a promising technique to condense the information of massive…
Efficient Multimodal Large Language Models (MLLMs) compress vision tokens to reduce resource consumption, but the loss of visual information can degrade comprehension capabilities. Although some priors introduce Knowledge Distillation to…
3D point cloud segmentation faces practical challenges due to the computational complexity and deployment limitations of large-scale transformer-based models. To address this, we propose a novel Structure- and Relation-aware Knowledge…
This paper presents a method to interpret the success of knowledge distillation by quantifying and analyzing task-relevant and task-irrelevant visual concepts that are encoded in intermediate layers of a deep neural network (DNN). More…
Knowledge distillation (KD) is a promising solution to compress large language models (LLMs) by transferring their knowledge to smaller models. During this process, white-box KD methods usually minimize the distance between the output…
Recently, large-scale pre-trained models have shown their advantages in many tasks. However, due to the huge computational complexity and storage requirements, it is challenging to apply the large-scale model to real scenes. A common…
Existing knowledge distillation methods mostly focus on distillation of teacher's prediction and intermediate activation. However, the structured representation, which arguably is one of the most critical ingredients of deep models, is…