Search Results for author:
Found 41 papers, 20 papers with code
Mini but Mighty: Finetuning ViTs with Mini Adapters
Vision Transformers (ViTs) have become one of the dominant architectures in computer vision, and pre-trained ViT models are commonly adapted to new tasks via fine-tuning.
Rethinking Class-incremental Learning in the Era of Large Pre-trained Models via Test-Time Adaptation
Concretely, we propose "Test-Time Adaptation for Class-Incremental Learning" (TTACIL) that first fine-tunes Layer Norm parameters of the PTM on each test instance for learning task-specific features, and then resets them back to the base model to preserve stability.
Towards image compression with perfect realism at ultra-low bitrates
Image codecs are typically optimized to trade-off bitrate vs, distortion metrics.
Face Aging via Diffusion-based Editing
We propose FADING, a novel approach to address Face Aging via DIffusion-based editiNG.
The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation
Source-Free Video Unsupervised Domain Adaptation (SFVUDA) task consists in adapting an action recognition model, trained on a labelled source dataset, to an unlabelled target dataset, without accessing the actual source data.
Predictive Coding For Animation-Based Video Compression
We address the problem of efficiently compressing video for conferencing-type applications.
Zero-shot spatial layout conditioning for text-to-image diffusion models
Large-scale text-to-image diffusion models have significantly improved the state of the art in generative image modelling and allow for an intuitive and powerful user interface to drive the image generation process.
Test your samples jointly: Pseudo-reference for image quality evaluation
In this paper, we address the well-known image quality assessment problem but in contrast from existing approaches that predict image quality independently for every images, we propose to jointly model different images depicting the same content to improve the precision of quality estimation.
Few-shot Semantic Image Synthesis with Class Affinity Transfer
The class affinity matrix is introduced as a first layer to the source model to make it compatible with the target label maps, and the source model is then further finetuned for the target domain.
One-shot Unsupervised Domain Adaptation with Personalized Diffusion Models
Departing from the common notion of transferring only the target ``texture'' information, we leverage text-to-image diffusion models (e. g., Stable Diffusion) to generate a synthetic target dataset with photo-realistic images that not only faithfully depict the style of the target domain, but are also characterized by novel scenes in diverse contexts.
Data Augmentation
One-shot Unsupervised Domain Adaptation
+2
Plotting Behind the Scenes: Towards Learnable Game Engines
The key to learning such game AI is the exploitation of a large and diverse text corpus, collected in this work, describing detailed actions in a game and used to train our animation model.
Unifying conditional and unconditional semantic image synthesis with OCO-GAN
To allow for more control, image synthesis can be conditioned on semantic segmentation maps that instruct the generator the position of objects in the image.
Autoregressive GAN for Semantic Unconditional Head Motion Generation
In this work, we address the task of unconditional head motion generation to animate still human faces in a low-dimensional semantic space from a single reference pose.
Cooperative Self-Training for Multi-Target Adaptive Semantic Segmentation
In this work we address multi-target domain adaptation (MTDA) in semantic segmentation, which consists in adapting a single model from an annotated source dataset to multiple unannotated target datasets that differ in their underlying data distributions.
Custom Structure Preservation in Face Aging
In this work, we propose a novel architecture for face age editing that can produce structural modifications while maintaining relevant details present in the original image.
GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation
Our experiments show the effectiveness of our segmentation approach on thousands of real-world point clouds.
Online Unsupervised Domain Adaptation for Person Re-identification
Therefore, we present a new yet practical online setting for Unsupervised Domain Adaptation for person Re-ID with two main constraints: Online Adaptation and Privacy Protection.
Online unsupervised domain adaptation
Person Re-Identification
Playable Environments: Video Manipulation in Space and Time
We present Playable Environments - a new representation for interactive video generation and manipulation in space and time.
A Unified Objective for Novel Class Discovery
In this paper, we study the problem of Novel Class Discovery (NCD).
Click to Move: Controlling Video Generation with Sparse Motion
This paper introduces Click to Move (C2M), a novel framework for video generation where the user can control the motion of the synthesized video through mouse clicks specifying simple object trajectories of the key objects in the scene.
HEMP: High-order Entropy Minimization for neural network comPression
We formulate the entropy of a quantized artificial neural network as a differentiable function that can be plugged as a regularization term into the cost function minimized by gradient descent.
Playable Video Generation
This paper introduces the unsupervised learning problem of playable video generation (PVG).
Multi-Domain Image-to-Image Translation with Adaptive Inference Graph
Therefore, we propose to increase the network capacity by using an adaptive graph structure.
Ultra-low bitrate video conferencing using deep image animation
In this work we propose a novel deep learning approach for ultra-low bitrate video compression for video conferencing applications.
Learning Visual Voice Activity Detection with an Automatically Annotated Dataset
Visual voice activity detection (V-VAD) uses visual features to predict whether a person is speaking or not.
DR2S : Deep Regression with Region Selection for Camera Quality Evaluation
In this work, we tackle the problem of estimating a camera capability to preserve fine texture details at a given lighting condition.
Learning to Cluster under Domain Shift
While unsupervised domain adaptation methods based on deep architectures have achieved remarkable success in many computer vision tasks, they rely on a strong assumption, i. e. labeled source data must be available.
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.
Motion-supervised Co-Part Segmentation
To overcome this limitation, we propose a self-supervised deep learning method for co-part segmentation.
Ranked #2 on
Unsupervised Human Pose Estimation
on Tai-Chi-HD
First Order Motion Model for Image Animation
To achieve this, we decouple appearance and motion information using a self-supervised formulation.
Ranked #1 on
Video Reconstruction
on Tai-Chi-HD
Progressive Fusion for Unsupervised Binocular Depth Estimation using Cycled Networks
Extensive experiments on the publicly available datasets KITTI, Cityscapes and ApolloScape demonstrate the effectiveness of the proposed model which is competitive with other unsupervised deep learning methods for depth prediction.
Budget-Aware Adapters for Multi-Domain Learning
To implement this idea we derive specialized deep models for each domain by adapting a pre-trained architecture but, differently from other methods, we propose a novel strategy to automatically adjust the computational complexity of the network.
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.
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.
Online Adaptation through Meta-Learning for Stereo Depth Estimation
Our proposal is evaluated on the wellestablished KITTI dataset, where we show that our online method is competitive withstate of the art algorithms trained in a batch setting.
Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation
Therefore, recent works have proposed deep architectures for addressing the monocular depth prediction task as a reconstruction problem, thus avoiding the need of collecting ground-truth depth.
Extended Gaze Following: Detecting Objects in Videos Beyond the Camera Field of View
In this paper we address the problems of detecting objects of interest in a video and of estimating their locations, solely from the gaze directions of people present in the video.
Animating Arbitrary Objects via Deep Motion Transfer
This is achieved through a deep architecture that decouples appearance and motion information.
DeepGUM: Learning Deep Robust Regression with a Gaussian-Uniform Mixture Model
In this paper, we address the problem of how to robustly train a ConvNet for regression, or deep robust regression.
A Comprehensive Analysis of Deep Regression
Deep learning revolutionized data science, and recently its popularity has grown exponentially, as did the amount of papers employing deep networks.
Neural Network Based Reinforcement Learning for Audio-Visual Gaze Control in Human-Robot Interaction
Our approach enables a robot to learn and to adapt its gaze control strategy for human-robot interaction neither with the use of external sensors nor with human supervision.
