Combating noisy labels with sample selection by mining high-discrepancy examples
The sample selection approach is popular in learning with noisy labels. The state-of-the-art
methods train two deep networks simultaneously for sample selection, which aims to employ …
methods train two deep networks simultaneously for sample selection, which aims to employ …
Sylph: A hypernetwork framework for incremental few-shot object detection
We study the challenging incremental few-shot object detection (iFSD) setting. Recently,
hypernetwork-based approaches have been studied in the context of continuous and …
hypernetwork-based approaches have been studied in the context of continuous and …
Deta: Denoised task adaptation for few-shot learning
Test-time task adaptation in few-shot learning aims to adapt a pre-trained task-agnostic
model for capturing task-specific knowledge of the test task, rely only on few-labeled support …
model for capturing task-specific knowledge of the test task, rely only on few-labeled support …
From instance to metric calibration: A unified framework for open-world few-shot learning
Robust few-shot learning (RFSL), which aims to address noisy labels in few-shot learning,
has recently gained considerable attention. Existing RFSL methods are based on the …
has recently gained considerable attention. Existing RFSL methods are based on the …
Egotracks: A long-term egocentric visual object tracking dataset
Visual object tracking is a key component to many egocentric vision problems. However, the
full spectrum of challenges of egocentric tracking faced by an embodied AI is …
full spectrum of challenges of egocentric tracking faced by an embodied AI is …
Counterfactual generation framework for few-shot learning
Few-shot learning (FSL) that aims to recognize novel classes with few labeled samples is
troubled by its data scarcity. Though recent works tackle FSL with data augmentation-based …
troubled by its data scarcity. Though recent works tackle FSL with data augmentation-based …
Regularly truncated m-estimators for learning with noisy labels
The sample selection approach is very popular in learning with noisy labels. As deep
networks “learn pattern first”, prior methods built on sample selection share a similar training …
networks “learn pattern first”, prior methods built on sample selection share a similar training …
Modeling noisy annotations for point-wise supervision
Point-wise supervision is widely adopted in computer vision tasks such as crowd counting
and human pose estimation. In practice, the noise in point annotations may affect the …
and human pose estimation. In practice, the noise in point annotations may affect the …
Blessing few-shot segmentation via semi-supervised learning with noisy support images
Mainstream few-shot segmentation methods meet performance bottleneck due to the data
scarcity of novel classes with insufficient intra-class variations, which results in a biased …
scarcity of novel classes with insufficient intra-class variations, which results in a biased …
When noisy labels meet long tail dilemmas: A representation calibration method
Real-world large-scale datasets are both noisily labeled and class-imbalanced. The issues
seriously hurt the generalization of trained models. It is hence significant to address the …
seriously hurt the generalization of trained models. It is hence significant to address the …