Search Results for author:
Found 18 papers, 12 papers with code
The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion
Hence, we propose The Power of Sound (TPoS) model to incorporate audio input that includes both changeable temporal semantics and magnitude.
Addressing Selection Bias in Computerized Adaptive Testing: A User-Wise Aggregate Influence Function Approach
Indeed, when naively training the diagnostic model using CAT response data, we observe that item profiles deviate significantly from the ground-truth.
Addressing Negative Transfer in Diffusion Models
Through this, our approach addresses the issue of negative transfer in diffusion models by allowing for efficient computation of MTL methods.
Task-Adaptive Pseudo Labeling for Transductive Meta-Learning
As a result, the proposed method is able to deal with more examples in the adaptation process than inductive ones, which can result in better classification performance of the model.
DisCoHead: Audio-and-Video-Driven Talking Head Generation by Disentangled Control of Head Pose and Facial Expressions
We enhance the efficiency of DisCoHead by integrating a dense motion estimator and the encoder of a generator which are originally separate modules.
Clinical Decision Transformer: Intended Treatment Recommendation through Goal Prompting
For this, we conducted goal-conditioned sequencing, which generated a subsequence of treatment history with prepended future goal state, and trained the CDT to model sequential medications required to reach that goal state.
Towards Practical Plug-and-Play Diffusion Models
For that, the existing practice is to fine-tune the guidance models with labeled data corrupted with noises.
Evaluating the Knowledge Dependency of Questions
They fail to evaluate the MCQ's ability to assess the student's knowledge of the corresponding target fact.
CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localization
In addition, this paper points out the negative effects of biased features of pre-trained CNNs and emphasizes the importance of the adaptation to the target dataset.
Ranked #24 on
Anomaly Detection
on MVTec AD
FlexBlock: A Flexible DNN Training Accelerator with Multi-Mode Block Floating Point Support
While several prior works proposed such multi-precision support for DNN accelerators, not only do they focus only on the inference, but also their core utilization is suboptimal at a fixed precision and specific layer types when the training is considered.
Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning
EKG utilized for the following search iteration is composed of the ensemble knowledge of interim sub-networks, i. e., the by-products of the sub-network evaluation.
Vision Transformer for Small-Size Datasets
However, the high performance of the ViT results from pre-training using a large-size dataset such as JFT-300M, and its dependence on a large dataset is interpreted as due to low locality inductive bias.
Contextual Gradient Scaling for Few-Shot Learning
Experimental results show that CxGrad effectively encourages the backbone to learn task-specific knowledge in the inner-loop and improves the performance of MAML up to a significant margin in both same- and cross-domain few-shot classification.
Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble
Recent advance in deep offline reinforcement learning (RL) has made it possible to train strong robotic agents from offline datasets.
Interpretable Embedding Procedure Knowledge Transfer via Stacked Principal Component Analysis and Graph Neural Network
Knowledge distillation (KD) is one of the most useful techniques for light-weight neural networks.
Addressing Distribution Shift in Online Reinforcement Learning with Offline Datasets
As it turns out, fine-tuning offline RL agents is a non-trivial challenge, due to distribution shift – the agent encounters out-of-distribution samples during online interaction, which may cause bootstrapping error in Q-learning and instability during fine-tuning.
Conditions for bubbles to arise under heterogeneous beliefs
This paper studies the equilibrium price of a continuous time asset traded in a market with heterogeneous investors.
Graph-based Knowledge Distillation by Multi-head Attention Network
Knowledge distillation (KD) is a technique to derive optimal performance from a small student network (SN) by distilling knowledge of a large teacher network (TN) and transferring the distilled knowledge to the small SN.
