Search Results for author:
Found 46 papers, 23 papers with code
Adaptive Blind All-in-One Image Restoration
Blind all-in-one image restoration models aim to recover a high-quality image from an input degraded with unknown distortions.
Ranked #1 on
Blind All-in-One Image Restoration
on 3-Degradations
NamedCurves: Learned Image Enhancement via Color Naming
A popular method for enhancing images involves learning the style of a professional photo editor using pairs of training images comprised of the original input with the editor-enhanced version.
Trust your Good Friends: Source-free Domain Adaptation by Reciprocal Neighborhood Clustering
We capture this intrinsic structure by defining local affinity of the target data, and encourage label consistency among data with high local affinity.
SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision
Accurate semantic segmentation models typically require significant computational resources, inhibiting their use in practical applications.
PeQuENet: Perceptual Quality Enhancement of Compressed Video with Adaptation- and Attention-based Network
In this paper we propose a generative adversarial network (GAN) framework to enhance the perceptual quality of compressed videos.
Slimmable Video Codec
Neural video compression has emerged as a novel paradigm combining trainable multilayer neural networks and machine learning, achieving competitive rate-distortion (RD) performances, but still remaining impractical due to heavy neural architectures, with large memory and computational demands.
Main Product Detection with Graph Networks for Fashion
Computer vision has established a foothold in the online fashion retail industry.
DCNGAN: A Deformable Convolutional-Based GAN with QP Adaptation for Perceptual Quality Enhancement of Compressed Video
Deformable convolutions can operate on multiple frames, thus leveraging more temporal information, which is beneficial for enhancing the perceptual quality of compressed videos.
A Novel Framework for Image-to-image Translation and Image Compression
Thus, we further propose a unified framework that allows both translation and autoencoding capabilities in a single codec.
Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image Recognition
We propose an approach to IML, which we call Episodic Replay Distillation (ERD), that mixes classes from the current task with class exemplars from previous tasks when sampling episodes for meta-learning.
HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification
To overcome forgetting in this benchmark, we propose Hierarchy-Consistency Verification (HCV) as an enhancement to existing continual learning methods.
Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation
In this paper, we address the challenging source-free domain adaptation (SFDA) problem, where the source pretrained model is adapted to the target domain in the absence of source data.
Ranked #7 on
Source-Free Domain Adaptation
on VisDA-2017
DVC-P: Deep Video Compression with Perceptual Optimizations
In this paper, we introduce deep video compression with perceptual optimizations (DVC-P), which aims at increasing perceptual quality of decoded videos.
Generalized Source-free Domain Adaptation
In this paper, we propose a new domain adaptation paradigm called Generalized Source-free Domain Adaptation (G-SFDA), where the learned model needs to perform well on both the target and source domains, with only access to current unlabeled target data during adaptation.
Ranked #8 on
Source-Free Domain Adaptation
on VisDA-2017
ACAE-REMIND for Online Continual Learning with Compressed Feature Replay
Methods are typically allowed to use a limited buffer to store some of the images in the stream.
MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains
Therefore, we propose a novel knowledge transfer method for generative models based on mining the knowledge that is most beneficial to a specific target domain, either from a single or multiple pretrained GANs.
DANICE: Domain adaptation without forgetting in neural image compression
Neural image compression (NIC) is a new coding paradigm where coding capabilities are captured by deep models learned from data.
Continual learning in cross-modal retrieval
We found that the indexing stage pays an important role and that simply avoiding reindexing the database with updated embedding networks can lead to significant gains.
Slimmable Compressive Autoencoders for Practical Neural Image Compression
Neural image compression leverages deep neural networks to outperform traditional image codecs in rate-distortion performance.
On Implicit Attribute Localization for Generalized Zero-Shot Learning
Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their attribute-based descriptions.
Casting a BAIT for Offline and Online Source-free Domain Adaptation
When adapting to the target domain, the additional classifier initialized from source classifier is expected to find misclassified features.
Source-Free Domain Adaptation
Unsupervised Domain Adaptation
Bookworm continual learning: beyond zero-shot learning and continual learning
We propose bookworm continual learning(BCL), a flexible setting where unseen classes can be inferred via a semantic model, and the visual model can be updated continually.
Simple and effective localized attribute representations for zero-shot learning
Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their semantic descriptions.
Distributed Learning and Inference with Compressed Images
Moreover, we may only have compressed images at training time but are able to use original images at inference time, or vice versa, and in such a case, the downstream model suffers from covariate shift.
Generative Feature Replay For Class-Incremental Learning
To prevent forgetting, we combine generative feature replay in the classifier with feature distillation in the feature extractor.
Semantic Drift Compensation for Class-Incremental Learning
The vast majority of methods have studied this scenario for classification networks, where for each new task the classification layer of the network must be augmented with additional weights to make room for the newly added classes.
Variable Rate Deep Image Compression with Modulated Autoencoder
Addressing these limitations, we formulate the problem of variable rate-distortion optimization for deep image compression, and propose modulated autoencoders (MAEs), where the representations of a shared autoencoder are adapted to the specific rate-distortion tradeoff via a modulation network.
MineGAN: effective knowledge transfer from GANs to target domains with few images
We propose a novel knowledge transfer method for generative models based on mining the knowledge that is most beneficial to a specific target domain, either from a single or multiple pretrained GANs.
Controlling biases and diversity in diverse image-to-image translation
The task of unpaired image-to-image translation is highly challenging due to the lack of explicit cross-domain pairs of instances.
Multifaceted Analysis of Fine-Tuning in Deep Model for Visual Recognition
In this paper, we introduce and systematically investigate several factors that influence the performance of fine-tuning for visual recognition.
Mix and match networks: cross-modal alignment for zero-pair image-to-image translation
This paper addresses the problem of inferring unseen cross-modal image-to-image translations between multiple modalities.
Cross-Modulation Networks for Few-Shot Learning
A family of recent successful approaches to few-shot learning relies on learning an embedding space in which predictions are made by computing similarities between examples.
Memory Replay GANs: Learning to Generate New Categories without Forgetting
In particular, we investigate generative adversarial networks (GANs) in the task of learning new categories in a sequential fashion.
Learning Effective RGB-D Representations for Scene Recognition
We show that this limitation can be addressed by using RGB-D videos, where more comprehensive depth information is accumulated as the camera travels across the scene.
Memory Replay GANs: learning to generate images from new categories without forgetting
In particular, we investigate generative adversarial networks (GANs) in the task of learning new categories in a sequential fashion.
LIUM-CVC Submissions for WMT18 Multimodal Translation Task
This paper describes the multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT18 Shared Task on Multimodal Translation.
Transferring GANs: generating images from limited data
Transferring the knowledge of pretrained networks to new domains by means of finetuning is a widely used practice for applications based on discriminative models.
Ranked #7 on
10-shot image generation
on Babies
Mix and match networks: encoder-decoder alignment for zero-pair image translation
We address the problem of image translation between domains or modalities for which no direct paired data is available (i. e. zero-pair translation).
Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting
In this paper we propose an approach to avoiding catastrophic forgetting in sequential task learning scenarios.
Food recognition and recipe analysis: integrating visual content, context and external knowledge
The central role of food in our individual and social life, combined with recent technological advances, has motivated a growing interest in applications that help to better monitor dietary habits as well as the exploration and retrieval of food-related information.
Scene recognition with CNNs: objects, scales and dataset bias
Thus, adapting the feature extractor to each particular scale (i. e. scale-specific CNNs) is crucial to improve recognition, since the objects in the scenes have their specific range of scales.
Depth CNNs for RGB-D scene recognition: learning from scratch better than transferring from RGB-CNNs
However, we show that this approach has the limitation of hardly reaching bottom layers, which is key to learn modality-specific features.
Domain-adaptive deep network compression
We show that domain transfer leads to large shifts in network activations and that it is desirable to take this into account when compressing.
LIUM-CVC Submissions for WMT17 Multimodal Translation Task
This paper describes the monomodal and multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT17 Shared Task on Multimodal Translation.
Joint Multi-Feature Spatial Context for Scene Recognition on the Semantic Manifold
An important advantage of modeling features in a semantic space, is that this space is feature independent.
