Search Results for author:
Found 24 papers, 14 papers with code
Generalized Consistency Trajectory Models for Image Manipulation
Diffusion-based generative models excel in unconditional generation, as well as on applied tasks such as image editing and restoration.
Task-Oriented Diffusion Model Compression
As recent advancements in large-scale Text-to-Image (T2I) diffusion models have yielded remarkable high-quality image generation, diverse downstream Image-to-Image (I2I) applications have emerged.
Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models
Despite the remarkable performance of text-to-image diffusion models in image generation tasks, recent studies have raised the issue that generated images sometimes cannot capture the intended semantic contents of the text prompts, which phenomenon is often called semantic misalignment.
Unpaired Image-to-Image Translation via Neural Schrödinger Bridge
Diffusion models are a powerful class of generative models which simulate stochastic differential equations (SDEs) to generate data from noise.
Bridging Active Exploration and Uncertainty-Aware Deployment Using Probabilistic Ensemble Neural Network Dynamics
Active exploration, in which a robot directs itself to states that yield the highest information gain, is essential for efficient data collection and minimizing human supervision.
Minimizing Trajectory Curvature of ODE-based Generative Models
Based on the relationship between the forward process and the curvature, here we present an efficient method of training the forward process to minimize the curvature of generative trajectories without any ODE/SDE simulation.
Measuring and Improving Semantic Diversity of Dialogue Generation
In this paper, we introduce a new automatic evaluation metric to measure the semantic diversity of generated responses.
Denoising MCMC for Accelerating Diffusion-Based Generative Models
Diffusion models are powerful generative models that simulate the reverse of diffusion processes using score functions to synthesize data from noise.
Mitigating Out-of-Distribution Data Density Overestimation in Energy-Based Models
Deep energy-based models (EBMs), which use deep neural networks (DNNs) as energy functions, are receiving increasing attention due to their ability to learn complex distributions.
Meet Your Favorite Character: Open-domain Chatbot Mimicking Fictional Characters with only a Few Utterances
To better reflect the style of the character, PDP builds the prompts in the form of dialog that includes the character's utterances as dialog history.
Semi-Implicit Hybrid Gradient Methods with Application to Adversarial Robustness
Adversarial examples, crafted by adding imperceptible perturbations to natural inputs, can easily fool deep neural networks (DNNs).
Energy-Based Contrastive Learning of Visual Representations
Contrastive learning is a method of learning visual representations by training Deep Neural Networks (DNNs) to increase the similarity between representations of positive pairs (transformations of the same image) and reduce the similarity between representations of negative pairs (transformations of different images).
Understanding and Improving the Exemplar-based Generation for Open-domain Conversation
Extensive experiments demonstrate that our proposed training method alleviates the drawbacks of the existing exemplar-based generative models and significantly improves the performance in terms of appropriateness and informativeness.
Distilling the Knowledge of Large-scale Generative Models into Retrieval Models for Efficient Open-domain Conversation
G2R consists of two distinct techniques of distillation: the data-level G2R augments the dialogue dataset with additional responses generated by the large-scale generative model, and the model-level G2R transfers the response quality score assessed by the generative model to the score of the retrieval model by the knowledge distillation loss.
Disentangling Label Distribution for Long-tailed Visual Recognition
Although this method surpasses state-of-the-art methods on benchmark datasets, it can be further improved by directly disentangling the source label distribution from the model prediction in the training phase.
Ranked #20 on
Long-tail Learning
on Places-LT
Filter Style Transfer between Photos
Unlike conventional style transfer, new technique FST can extract and transfer custom filter style from a filtered style image to a content image.
MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
When there is a mismatch between the target identity and the driver identity, face reenactment suffers severe degradation in the quality of the result, especially in a few-shot setting.
Revisiting Classical Bagging with Modern Transfer Learning for On-the-fly Disaster Damage Detector
In this paper, we revisit the classical bootstrap aggregating approach in the context of modern transfer learning for data-efficient disaster damage detection.
Temporal Convolution for Real-time Keyword Spotting on Mobile Devices
In addition, we release the implementation of the proposed and the baseline models including an end-to-end pipeline for training models and evaluating them on mobile devices.
Ranked #14 on
Keyword Spotting
on Google Speech Commands
(Google Speech Commands V2 12 metric)
Bridging Adversarial Robustness and Gradient Interpretability
Adversarial training is a training scheme designed to counter adversarial attacks by augmenting the training dataset with adversarial examples.
Why are Saliency Maps Noisy? Cause of and Solution to Noisy Saliency Maps
Saliency Map, the gradient of the score function with respect to the input, is the most basic technique for interpreting deep neural network decisions.
Rectified Gradient: Layer-wise Thresholding for Sharp and Coherent Attribution Maps
In this paper, we identify the cause of noisy saliency maps.
Noise-adding Methods of Saliency Map as Series of Higher Order Partial Derivative
SmoothGrad and VarGrad are techniques that enhance the empirical quality of standard saliency maps by adding noise to input.
Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors
We propose methods of addressing two critical issues of pedestrian detection: (i) occlusion of target objects as false negative failure, and (ii) confusion with hard negative examples like vertical structures as false positive failure.
