Search Results for author:
Found 35 papers, 22 papers with code
Semantic Residual Prompts for Continual Learning
Most of these methods organize these vectors in a pool of key-value pairs, and use the input image as query to retrieve the prompts (values).
StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Model
Despite the progress made in the style transfer task, most previous work focus on transferring only relatively simple features like color or texture, while missing more abstract concepts such as overall art expression or painter-specific traits.
SpectralCLIP: Preventing Artifacts in Text-Guided Style Transfer from a Spectral Perspective
However, directly using CLIP to guide style transfer leads to undesirable artifacts (mainly written words and unrelated visual entities) spread over the image.
One Transformer for All Time Series: Representing and Training with Time-Dependent Heterogeneous Tabular Data
There is a recent growing interest in applying Deep Learning techniques to tabular data, in order to replicate the success of other Artificial Intelligence areas in this structured domain.
Input Perturbation Reduces Exposure Bias in Diffusion Models
Denoising Diffusion Probabilistic Models have shown an impressive generation quality, although their long sampling chain leads to high computational costs.
Ranked #1 on
Image Generation
on FFHQ 128 x 128
Smooth image-to-image translations with latent space interpolations
Multi-domain image-to-image (I2I) translations can transform a source image according to the style of a target domain.
Unsupervised High-Resolution Portrait Gaze Correction and Animation
Solving this problem using an unsupervised method remains an open problem, especially for high-resolution face images in the wild, which are not easy to annotate with gaze and head pose labels.
Spatial Entropy as an Inductive Bias for Vision Transformers
In this work, we propose a different and complementary direction, in which a local bias is introduced using an auxiliary self-supervised task, performed jointly with standard supervised training.
Temporal Alignment for History Representation in Reinforcement Learning
Inspired by human memory, we propose to represent history with only important changes in the environment and, in our approach, to obtain automatically this representation using self-supervision.
3D-Aware Semantic-Guided Generative Model for Human Synthesis
However, they usually struggle to generate high-quality images representing non-rigid objects, such as the human body, which is of a great interest for many computer graphics applications.
A Unified Objective for Novel Class Discovery
In this paper, we study the problem of Novel Class Discovery (NCD).
Ranked #3 on
Novel Object Detection
on LVIS v1.0 val
Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation
In this paper, we propose a new training protocol based on three specific losses which help a translation network to learn a smooth and disentangled latent style space in which: 1) Both intra- and inter-domain interpolations correspond to gradual changes in the generated images and 2) The content of the source image is better preserved during the translation.
Efficient Training of Visual Transformers with Small Datasets
This task encourages the VTs to learn spatial relations within an image and makes the VT training much more robust when training data are scarce.
Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization
Moreover, we propose a novel Self-Training Part Replacement (STPR) strategy to refine the model for the texture-transfer task, which improves the quality of the generated clothes and the preservation ability of non-target regions.
Dual In-painting Model for Unsupervised Gaze Correction and Animation in the Wild
In this paper we address the problem of unsupervised gaze correction in the wild, presenting a solution that works without the need for precise annotations of the gaze angle and the head pose.
Online Continual Learning under Extreme Memory Constraints
Continual Learning (CL) aims to develop agents emulating the human ability to sequentially learn new tasks while being able to retain knowledge obtained from past experiences.
Whitening for Self-Supervised Representation Learning
Most of the current self-supervised representation learning (SSL) methods are based on the contrastive loss and the instance-discrimination task, where augmented versions of the same image instance ("positives") are contrasted with instances extracted from other images ("negatives").
TriGAN: Image-to-Image Translation for Multi-Source Domain Adaptation
In this paper we propose the first approach for Multi-Source Domain Adaptation (MSDA) based on Generative Adversarial Networks.
Coarse-to-Fine Gaze Redirection with Numerical and Pictorial Guidance
In this paper, we propose to alleviate these problems by means of a novel gaze redirection framework which exploits both a numerical and a pictorial direction guidance, jointly with a coarse-to-fine learning strategy.
Event Discovery for History Representation in Reinforcement Learning
To address this problem, a possible solution is to provide the agent with information about past observations.
Attention-based Fusion for Multi-source Human Image Generation
We present a generalization of the person-image generation task, in which a human image is generated conditioned on a target pose and a set X of source appearance images.
Whitening and Coloring transform for GANs
In this paper we propose to generalize both BN and cBN using a Whitening and Coloring based batch normalization.
Appearance and Pose-Conditioned Human Image Generation using Deformable GANs
Specifically, given an image xa of a person and a target pose P(xb), extracted from a different image xb, we synthesize a new image of that person in pose P(xb), while preserving the visual details in xa.
Metric-Learning based Deep Hashing Network for Content Based Retrieval of Remote Sensing Images
Hashing methods have been recently found very effective in retrieval of remote sensing (RS) images due to their computational efficiency and fast search speed.
Unsupervised Domain Adaptation using Feature-Whitening and Consensus Loss
A classifier trained on a dataset seldom works on other datasets obtained under different conditions due to domain shift.
Whitening and Coloring batch transform for GANs
In this paper we propose to generalize both BN and cBN using a Whitening and Coloring based batch normalization.
Deformable GANs for Pose-based Human Image Generation
Specifically, given an image of a person and a target pose, we synthesize a new image of that person in the novel pose.
Ranked #5 on
Gesture-to-Gesture Translation
on NTU Hand Digit
Generative Adversarial Network
Gesture-to-Gesture Translation
+2
Abnormal Event Detection in Videos using Generative Adversarial Nets
In this paper we address the abnormality detection problem in crowded scenes.
Ranked #4 on
Abnormal Event Detection In Video
on UCSD Ped2
Training Adversarial Discriminators for Cross-channel Abnormal Event Detection in Crowds
Abnormal crowd behaviour detection attracts a large interest due to its importance in video surveillance scenarios.
FOIL it! Find One mismatch between Image and Language caption
In this paper, we aim to understand whether current language and vision (LaVi) models truly grasp the interaction between the two modalities.
Plug-and-Play CNN for Crowd Motion Analysis: An Application in Abnormal Event Detection
In this paper, we show that keeping track of the changes in the CNN feature across time can facilitate capturing the local abnormality.
Self Paced Deep Learning for Weakly Supervised Object Detection
The main idea is to iteratively select a subset of images and boxes that are the most reliable, and use them for training.
Ranked #31 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
Unsupervised Tube Extraction Using Transductive Learning and Dense Trajectories
The combination of appearance-based static ''objectness'' (Selective Search), motion information (Dense Trajectories) and transductive learning (detectors are forced to "overfit" on the unsupervised data used for training) makes the proposed approach extremely robust.
