Search Results for author:
Found 21 papers, 5 papers with code
CLIPtone: Unsupervised Learning for Text-based Image Tone Adjustment
Recent image tone adjustment (or enhancement) approaches have predominantly adopted supervised learning for learning human-centric perceptual assessment.
MedBN: Robust Test-Time Adaptation against Malicious Test Samples
In response to the emerging threat, we propose median batch normalization (MedBN), leveraging the robustness of the median for statistics estimation within the batch normalization layer during test-time inference.
Active Label Correction for Semantic Segmentation with Foundation Models
Training and validating models for semantic segmentation require datasets with pixel-wise annotations, which are notoriously labor-intensive.
Addressing Feature Imbalance in Sound Source Separation
Neural networks often suffer from a feature preference problem, where they tend to overly rely on specific features to solve a task while disregarding other features, even if those neglected features are essential for the task.
Adaptive Superpixel for Active Learning in Semantic Segmentation
Learning semantic segmentation requires pixel-wise annotations, which can be time-consuming and expensive.
Combating Label Distribution Shift for Active Domain Adaptation
We consider the problem of active domain adaptation (ADA) to unlabeled target data, of which subset is actively selected and labeled given a budget constraint.
Towards Sequence-Level Training for Visual Tracking
Despite the extensive adoption of machine learning on the task of visual object tracking, recent learning-based approaches have largely overlooked the fact that visual tracking is a sequence-level task in its nature; they rely heavily on frame-level training, which inevitably induces inconsistency between training and testing in terms of both data distributions and task objectives.
Ranked #16 on
Visual Object Tracking
on TrackingNet
Efficient Scheduling of Data Augmentation for Deep Reinforcement Learning
In deep reinforcement learning (RL), data augmentation is widely considered as a tool to induce a set of useful priors about semantic consistency and improve sample efficiency and generalization performance.
Few-Shot Unlearning by Model Inversion
We consider a practical scenario of machine unlearning to erase a target dataset, which causes unexpected behavior from the trained model.
MetaSSD: Meta-Learned Self-Supervised Detection
There are two major limitations in the supervised approaches: a) a model needs to be retrained from scratch when new train symbols come to adapt to a new channel status, and b) the length of the training symbols needs to be longer than a certain threshold to make the model generalize well on unseen symbols.
Robust Deep Learning from Crowds with Belief Propagation
Crowdsourcing systems enable us to collect large-scale dataset, but inherently suffer from noisy labels of low-paid workers.
Learning Continuous Representation of Audio for Arbitrary Scale Super Resolution
To obtain a continuous representation of audio and enable super resolution for arbitrary scale factor, we propose a method of implicit neural representation, coined Local Implicit representation for Super resolution of Arbitrary scale (LISA).
Gradient Inversion with Generative Image Prior
Federated Learning (FL) is a distributed learning framework, in which the local data never leaves clients devices to preserve privacy, and the server trains models on the data via accessing only the gradients of those local data.
Multi-armed Bandit Algorithm against Strategic Replication
We consider a multi-armed bandit problem in which a set of arms is registered by each agent, and the agent receives reward when its arm is selected.
Efficient Scheduling of Data Augmentation for Deep Reinforcement Learning
In deep reinforcement learning (RL), data augmentation is widely considered as a tool to induce a set of useful priors about semantic consistency and improve sample efficiency and generalization performance.
Transfer Learning in Bandits with Latent Continuity
To cope with the latent structural parameter, we consider a transfer learning setting in which an agent must learn to transfer the structural information from the prior tasks to the next task, which is inspired by practical problems such as rate adaptation in wireless link.
Optimal Clustering from Noisy Binary Feedback
The objective is to devise an algorithm with a minimal cluster recovery error rate.
Exploration in Structured Reinforcement Learning
For Lipschitz MDPs, the bounds are shown not to scale with the sizes $S$ and $A$ of the state and action spaces, i. e., they are smaller than $c\log T$ where $T$ is the time horizon and the constant $c$ only depends on the Lipschitz structure, the span of the bias function, and the minimal action sub-optimality gap.
Combinatorial Pure Exploration with Continuous and Separable Reward Functions and Its Applications (Extended Version)
Each decision has a reward according to the distributions of arms.
Iterative Bayesian Learning for Crowdsourced Regression
Crowdsourcing platforms emerged as popular venues for purchasing human intelligence at low cost for large volume of tasks.
Optimal Inference in Crowdsourced Classification via Belief Propagation
Crowdsourcing systems are popular for solving large-scale labelling tasks with low-paid workers.
