273 citations · 994 across the 18 of their papers we have counts for
18 papers
Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning
Zichen Tian, Yaoyao Liu, Qianru Sun
Training large foundation models from scratch for domain-specific applications is almost impossible due to data limits and long-tailed distributions -- taking remote sensing (RS) a…
FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction
Wei Cao, Hao Zhang, Fengrui Tian +5
Camera redirection aims to replay a dynamic scene from a single monocular video under a user-specified camera trajectory. However, large-angle redirection is inherently ill-posed:…
iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning
Tom Fischer, Yaoyao Liu, Artur Jesslen +6
Different from human nature, it is still common practice today for vision tasks to train deep learning models only initially and on fixed datasets. A variety of approaches have rec…
ImageNet3D: Towards General-Purpose Object-Level 3D Understanding
Wufei Ma, Guanning Zeng, Guofeng Zhang +5
A vision model with general-purpose object-level 3D understanding should be capable of inferring both 2D (e.g., class name and bounding box) and 3D information (e.g., 3D location a…
HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting
Yuanhao Cai, Zihao Xiao, Yixun Liang +5
High dynamic range (HDR) novel view synthesis (NVS) aims to create photorealistic images from novel viewpoints using HDR imaging techniques. The rendered HDR images capture a wider…
Wakening Past Concepts without Past Data: Class-Incremental Learning from Online Placebos
Yaoyao Liu, Yingying Li, Bernt Schiele +1
Not forgetting old class knowledge is a key challenge for class-incremental learning (CIL) when the model continuously adapts to new classes. A common technique to address this is…
Continual Learning for Abdominal Multi-Organ and Tumor Segmentation
Yixiao Zhang, Xinyi Li, Huimiao Chen +3
The ability to dynamically extend a model to new data and classes is critical for multiple organ and tumor segmentation. However, due to privacy regulations, accessing previous dat…
Generating Images with 3D Annotations Using Diffusion Models
Wufei Ma, Qihao Liu, Jiahao Wang +11
Diffusion models have emerged as a powerful generative method, capable of producing stunning photo-realistic images from natural language descriptions. However, these models lack e…
Class-Incremental Exemplar Compression for Class-Incremental Learning
Zilin Luo, Yaoyao Liu, Bernt Schiele +1
Exemplar-based class-incremental learning (CIL) finetunes the model with all samples of new classes but few-shot exemplars of old classes in each incremental phase, where the "few-…
Continual Detection Transformer for Incremental Object Detection
Yaoyao Liu, Bernt Schiele, Andrea Vedaldi +1
Incremental object detection (IOD) aims to train an object detector in phases, each with annotations for new object categories. As other incremental settings, IOD is subject to cat…
RMM: Reinforced Memory Management for Class-Incremental Learning
Yaoyao Liu, Bernt Schiele, Qianru Sun
Class-Incremental Learning (CIL) [40] trains classifiers under a strict memory budget: in each incremental phase, learning is done for new data, most of which is abandoned to free…
Online Hyperparameter Optimization for Class-Incremental Learning
Yaoyao Liu, Yingying Li, Bernt Schiele +1
Class-incremental learning (CIL) aims to train a classification model while the number of classes increases phase-by-phase. An inherent challenge of CIL is the stability-plasticity…
Adaptive Aggregation Networks for Class-Incremental Learning
Yaoyao Liu, Bernt Schiele, Qianru Sun
Class-Incremental Learning (CIL) aims to learn a classification model with the number of classes increasing phase-by-phase. An inherent problem in CIL is the stability-plasticity d…
Mnemonics Training: Multi-Class Incremental Learning without Forgetting
Yaoyao Liu, Yuting Su, An-An Liu +2
Multi-Class Incremental Learning (MCIL) aims to learn new concepts by incrementally updating a model trained on previous concepts. However, there is an inherent trade-off to effect…
Meta-Transfer Learning through Hard Tasks
Qianru Sun, Yaoyao Liu, Zhaozheng Chen +2
Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order t…
Learning to Self-Train for Semi-Supervised Few-Shot Classification
Xinzhe Li, Qianru Sun, Yaoyao Liu +4
Few-shot classification (FSC) is challenging due to the scarcity of labeled training data (e.g. only one labeled data point per class). Meta-learning has shown to achieve promising…
An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning
Yaoyao Liu, Bernt Schiele, Qianru Sun
Few-shot learning aims to train efficient predictive models with a few examples. The lack of training data leads to poor models that perform high-variance or low-confidence predict…
Meta-Transfer Learning for Few-Shot Learning
Qianru Sun, Yaoyao Liu, Tat-Seng Chua +1
Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order t…