相关论文: UnseenNet: Fast Training Detector for Any Unseen C…

Great labels make great models. However, traditional labeling approaches for tasks like object detection have substantial costs at scale. Furthermore, alternatives to fully-supervised object detection either lose functionality or require…

Machine unlearning is a prominent and challenging field, driven by regulatory demands for user data deletion and heightened privacy awareness. Existing approaches involve retraining model or multiple finetuning steps for each deletion…

Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation, which require dense labeling of the image. While few-shot object detection is about training a model on novel…

Recent successes in visual recognition can be primarily attributed to feature representation, learning algorithms, and the ever-increasing size of labeled training data. Extensive research has been devoted to the first two, but much less…

Since the rise of deep learning, many computer vision tasks have seen significant advancements. However, the downside of deep learning is that it is very data-hungry. Especially for segmentation problems, training a deep neural net requires…

One object class may show large variations due to diverse illuminations, backgrounds and camera viewpoints. Traditional object detection methods often perform worse under unconstrained video environments. To address this problem, many…

We aim for domestic robots to perform long-term indoor service. Under the object-level scene dynamics induced by daily human activities, a robot needs to robustly localize itself in the environment subject to scene uncertainties. Previous…

Pretraining on large labeled datasets is a prerequisite to achieve good performance in many computer vision tasks like 2D object recognition, video classification etc. However, pretraining is not widely used for 3D recognition tasks where…

Zero-shot learning (ZSL) endeavors to transfer knowledge from seen categories to recognize unseen categories, which mostly relies on the semantic-visual interactions between image and attribute tokens. Recently, prompt learning has emerged…

Recent works on zero-shot learning make use of side information such as visual attributes or natural language semantics to define the relations between output visual classes and then use these relationships to draw inference on new unseen…

Neural networks for image classification tasks assume that any given image during inference belongs to one of the training classes. This closed-set assumption is challenged in real-world applications where models may encounter inputs of…

Generalized Category Discovery (GCD) aims to classify unlabelled images from both `seen' and `unseen' classes by transferring knowledge from a set of labelled `seen' class images. A key theme in existing GCD approaches is adapting…

Fake face detection is a significant challenge for intelligent systems as generative models become more powerful every single day. As the quality of fake faces increases, the trained models become more and more inefficient to detect the…

We present a simple yet efficient approach capable of training deep neural networks on large-scale weakly-supervised web images, which are crawled raw from the Internet by using text queries, without any human annotation. We develop a…

This paper proposes a learning-based visual peg-in-hole that enables training with several shapes in simulation, and adapting to arbitrary unseen shapes in real world with minimal sim-to-real cost. The core idea is to decouple the…

In recent years, the performance of object detection has advanced significantly with the evolving deep convolutional neural networks. However, the state-of-the-art object detection methods still rely on accurate bounding box annotations…

In the area of computer vision, deep learning has produced a variety of state-of-the-art models that rely on massive labeled data. However, collecting and annotating images from the real world has a great demand for labor and money…

Despite significant progress in object categorization, in recent years, a number of important challenges remain; mainly, the ability to learn from limited labeled data and to recognize object classes within large, potentially open, set of…

Training a computer vision system to segment a novel class typically requires collecting and painstakingly annotating lots of images with objects from that class. Few-shot segmentation techniques reduce the required number of images to…

This paper presents how we can achieve the state-of-the-art accuracy in multi-category object detection task while minimizing the computational cost by adapting and combining recent technical innovations. Following the common pipeline of…