Search Results for author:
Found 17 papers, 11 papers with code
Learning a Category-level Object Pose Estimator without Pose Annotations
Instead of using manually annotated images, we leverage diffusion models (e. g., Zero-1-to-3) to generate a set of images under controlled pose differences and propose to learn our object pose estimator with those images.
Continual Adversarial Defense
In response to the rapidly evolving nature of adversarial attacks against visual classifiers on a monthly basis, numerous defenses have been proposed to generalize against as many known attacks as possible.
Prompt-Based Exemplar Super-Compression and Regeneration for Class-Incremental Learning
Replay-based methods in class-incremental learning (CIL) have attained remarkable success, as replaying the exemplars of old classes can significantly mitigate catastrophic forgetting.
Wakening Past Concepts without Past Data: Class-Incremental Learning from Online Placebos
In experiments, we show that our method 1) is surprisingly effective even when there is no class overlap between placebos and original old class data, 2) does not require any additional supervision or memory budget, and 3) significantly outperforms a number of top-performing CIL methods, in particular when using lower memory budgets for old class exemplars, e. g., five exemplars per class.
Generating Images with 3D Annotations Using Diffusion Models
With explicit 3D geometry control, we can easily change the 3D structures of the objects in the generated images and obtain ground-truth 3D annotations automatically.
Continual Learning for Abdominal Multi-Organ and Tumor Segmentation
The ability to dynamically extend a model to new data and classes is critical for multiple organ and tumor segmentation.
Continual Detection Transformer for Incremental Object Detection
Incremental object detection (IOD) aims to train an object detector in phases, each with annotations for new object categories.
Class-Incremental Object Detection
Knowledge Distillation
+3
Class-Incremental Exemplar Compression for Class-Incremental Learning
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-shot" abides by the limited memory budget.
RMM: Reinforced Memory Management for Class-Incremental Learning
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 space for the next phase.
Online Hyperparameter Optimization for Class-Incremental Learning
Class-incremental learning (CIL) aims to train a classification model while the number of classes increases phase-by-phase.
Wakening Past Concepts without Past Data: Class-incremental Learning from Placebos
However, we empirically observe that this both harms learning of new classes and also underperforms to distil old class knowledge from the previous phase model.
Adaptive Aggregation Networks for Class-Incremental Learning
Class-Incremental Learning (CIL) aims to learn a classification model with the number of classes increasing phase-by-phase.
Mnemonics Training: Multi-Class Incremental Learning without Forgetting
However, there is an inherent trade-off to effectively learning new concepts without catastrophic forgetting of previous ones.
Meta-Transfer Learning through Hard Tasks
In this paper, we propose a novel approach called meta-transfer learning (MTL) which learns to transfer the weights of a deep NN for few-shot learning tasks.
Learning to Self-Train for Semi-Supervised Few-Shot Classification
On each task, we train a few-shot model to predict pseudo labels for unlabeled data, and then iterate the self-training steps on labeled and pseudo-labeled data with each step followed by fine-tuning.
An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning
"Empirical" means that the hyperparameters, e. g., used for learning and ensembling the epoch-wise models, are generated by hyperprior learners conditional on task-specific data.
Meta-Transfer Learning for Few-Shot Learning
In this paper we propose a novel few-shot learning method called meta-transfer learning (MTL) which learns to adapt a deep NN for few shot learning tasks.
