Related papers: Efficient Feature Distillation for Zero-shot Annot…

In this work, we propose a method that leverages CLIP feature distillation, achieving efficient 3D segmentation through language guidance. Unlike previous methods that rely on multi-scale CLIP features and are limited by processing speed…

We present a novel vision-language prompt learning approach for few-shot out-of-distribution (OOD) detection. Few-shot OOD detection aims to detect OOD images from classes that are unseen during training using only a few labeled…

Recently, the rapid advancements of vision-language models, such as CLIP, leads to significant progress in zero-/few-shot anomaly detection (ZFSAD) tasks. However, most existing CLIP-based ZFSAD methods commonly assume prior knowledge of…

Zero-shot 3D object classification is crucial for real-world applications like autonomous driving, however it is often hindered by a significant domain gap between the synthetic data used for training and the sparse, noisy LiDAR scans…

Image Anomaly Detection has been a challenging task in Computer Vision field. The advent of Vision-Language models, particularly the rise of CLIP-based frameworks, has opened new avenues for zero-shot anomaly detection. Recent studies have…

In this paper, we study the problem of Compositional Zero-Shot Learning (CZSL), which is to recognize novel attribute-object combinations with pre-existing concepts. Recent researchers focus on applying large-scale Vision-Language…

The existing solutions for object detection distillation rely on the availability of both a teacher model and ground-truth labels. We propose a new perspective to relax this constraint. In our framework, a student is first trained with…

Segmenting or detecting objects in sparse Lidar point clouds are two important tasks in autonomous driving to allow a vehicle to act safely in its 3D environment. The best performing methods in 3D semantic segmentation or object detection…

Multi-label classification is crucial for comprehensive image understanding, yet acquiring accurate annotations is challenging and costly. To address this, a recent study suggests exploiting unsupervised multi-label classification…

Zero-shot learning (ZSL) aims to recognize the unseen classes in the open-world guided by the side-information (e.g., attributes). Its key task is how to infer the latent semantic knowledge between visual and attribute features on seen…

Few-shot object detection (FSOD) aims at extending a generic detector for novel object detection with only a few training examples. It attracts great concerns recently due to the practical meanings. Meta-learning has been demonstrated to be…

LiDAR-based 3D object detection plays a critical role for reliable and safe autonomous driving systems. However, existing detectors often produce overly confident predictions for objects not belonging to known categories, posing significant…

3D object detection is fundamental for spatial understanding. Real-world environments demand models capable of recognizing diverse, previously unseen objects, which remains a major limitation of closed-set methods. Existing open-vocabulary…

Zero-shot instance segmentation aims to detect and precisely segment objects of unseen categories without any training samples. Since the model is trained on seen categories, there is a strong bias that the model tends to classify all the…

Accurate multi-view 3D object detection is essential for applications such as autonomous driving. Researchers have consistently aimed to leverage LiDAR's precise spatial information to enhance camera-based detectors through methods like…

Recent Semi-Supervised Object Detection (SS-OD) methods are mainly based on self-training, i.e., generating hard pseudo-labels by a teacher model on unlabeled data as supervisory signals. Although they achieved certain success, the limited…

Recent approaches have shown that training deep neural networks directly on large-scale image-text pair collections enables zero-shot transfer on various recognition tasks. One central issue is how this can be generalized to object…

Visual anomaly classification and segmentation are vital for automating industrial quality inspection. The focus of prior research in the field has been on training custom models for each quality inspection task, which requires…

3D panoptic segmentation is a challenging perception task, especially in autonomous driving. It aims to predict both semantic and instance annotations for 3D points in a scene. Although prior 3D panoptic segmentation approaches have…

State-of-the-art CNN based recognition models are often computationally prohibitive to deploy on low-end devices. A promising high level approach tackling this limitation is knowledge distillation, which let small student model mimic…