Search Results for author:
Found 64 papers, 38 papers with code
Using a Deformation Field Model for Localizing Faces and Facial Points under Weak Supervision
Additionally, without any facial point annotation at the level of individual training images, our method can localize facial points with an accuracy similar to fully supervised approaches.
Object Classification with Adaptable Regions
In classification of objects substantial work has gone into improving the low level representation of an image by considering various aspects such as different features, a number of feature pooling and coding techniques and considering different kernels.
Weakly Supervised Object Detection With Convex Clustering
However, as learning appearance and localization are two interconnected tasks, the optimization is not convex and the procedure can easily get stuck in a poor local minimum, the algorithm "misses" the object in some images.
DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers
We generate hypotheses in a sliding-window fashion over different activation layers and show that the final convolutional layers can find the object of interest with high recall but poor localization due to the coarseness of the feature maps.
Towards Automatic Image Editing: Learning to See another You
Learning the distribution of images in order to generate new samples is a challenging task due to the high dimensionality of the data and the highly non-linear relations that are involved.
Learning Where to Position Parts in 3D
In this paper we propose a new method for the detection and pose estimation of 3D objects, that does not use any 3D CAD model or other 3D information.
DeepProposals: Hunting Objects and Actions by Cascading Deep Convolutional Layers
In this paper, a new method for generating object and action proposals in images and videos is proposed.
Areas of Attention for Image Captioning
We propose "Areas of Attention", a novel attention-based model for automatic image captioning.
Modeling Information Flow Through Deep Neural Networks
This paper proposes a principled information theoretic analysis of classification for deep neural network structures, e. g. convolutional neural networks (CNN).
An Attention Model for group-level emotion recognition
In this paper we propose a new approach for classifying the global emotion of images containing groups of people.
Deep clustering: On the link between discriminative models and K-means
Typically, they use multinomial logistic regression posteriors and parameter regularization, as is very common in supervised learning.
Ranked #2 on
Image Clustering
on YouTube Faces DB
Deep Co-Training for Semi-Supervised Image Segmentation
In this paper, we aim to improve the performance of semantic image segmentation in a semi-supervised setting in which training is effectuated with a reduced set of annotated images and additional non-annotated images.
Progressive Gradient Pruning for Classification, Detection and DomainAdaptation
Although deep neural networks (NNs) have achievedstate-of-the-art accuracy in many visual recognition tasks, the growing computational complexity and energy con-sumption of networks remains an issue, especially for ap-plications on platforms with limited resources and requir-ing real-time processing.
Multimodal Fusion with Deep Neural Networks for Audio-Video Emotion Recognition
This paper presents a novel deep neural network (DNN) for multimodal fusion of audio, video and text modalities for emotion recognition.
Discretely-constrained deep network for weakly supervised segmentation
An efficient strategy for weakly-supervised segmentation is to impose constraints or regularization priors on target regions.
Adversarial Learning of General Transformations for Data Augmentation
Data augmentation (DA) is fundamental against overfitting in large convolutional neural networks, especially with a limited training dataset.
Emotion Recognition with Spatial Attention and Temporal Softmax Pooling
Video-based emotion recognition is a challenging task because it requires to distinguish the small deformations of the human face that represent emotions, while being invariant to stronger visual differences due to different identities.
Information based Deep Clustering: An experimental study
The second, named Invariant Information Clustering (IIC), maximizes the mutual information between the clustering of a sample and its geometrically transformed version.
A Computing Kernel for Network Binarization on PyTorch
Deep Neural Networks have now achieved state-of-the-art results in a wide range of tasks including image classification, object detection and so on.
Convolutional STN for Weakly Supervised Object Localization
Weakly supervised object localization is a challenging task in which the object of interest should be localized while learning its appearance.
Mutual information deep regularization for semi-supervised segmentation
The scarcity of labeled data often limits the application of deep learning to medical image segmentation.
On the Texture Bias for Few-Shot CNN Segmentation
Despite the initial belief that Convolutional Neural Networks (CNNs) are driven by shapes to perform visual recognition tasks, recent evidence suggests that texture bias in CNNs provides higher performing models when learning on large labeled training datasets.
Ranked #2 on
Few-Shot Semantic Segmentation
on Pascal5i
Semi-supervised few-shot learning for medical image segmentation
To handle this new learning paradigm, we propose to include surrogate tasks that can leverage very powerful supervisory signals --derived from the data itself-- for semantic feature learning.
A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses
Second, we show that, more generally, minimizing the cross-entropy is actually equivalent to maximizing the mutual information, to which we connect several well-known pairwise losses.
Ranked #12 on
Metric Learning
on CARS196
(using extra training data)
Learning Data Augmentation with Online Bilevel Optimization for Image Classification
Data augmentation is a key practice in machine learning for improving generalization performance.
Self-paced and self-consistent co-training for semi-supervised image segmentation
Moreover, to encourage predictions from different networks to be both consistent and confident, we enhance this generalized JSD loss with an uncertainty regularizer based on entropy.
Temporal Stochastic Softmax for 3D CNNs: An Application in Facial Expression Recognition
The proposed softmax strategy provides several advantages: a reduced computational complexity due to efficient clip sampling, and an improved accuracy since temporal weighting focuses on more relevant clips during both training and inference.
Facial Expression Recognition
Facial Expression Recognition (FER)
Augmented Lagrangian Adversarial Attacks
Our attack enjoys the generality of penalty methods and the computational efficiency of distance-customized algorithms, and can be readily used for a wide set of distances.
Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization
In this method, we maximize the MI for intermediate feature embeddings that are taken from both the encoder and decoder of a segmentation network.
Incremental Multi-Target Domain Adaptation for Object Detection with Efficient Domain Transfer
Recent advances in unsupervised domain adaptation have significantly improved the recognition accuracy of CNNs by alleviating the domain shift between (labeled) source and (unlabeled) target data distributions.
Context-aware virtual adversarial training for anatomically-plausible segmentation
Despite their outstanding accuracy, semi-supervised segmentation methods based on deep neural networks can still yield predictions that are considered anatomically impossible by clinicians, for instance, containing holes or disconnected regions.
Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels
Pre-training a recognition model with contrastive learning on a large dataset of unlabeled data has shown great potential to boost the performance of a downstream task, e. g., image classification.
F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling
Interpolation is required to restore full size CAMs, yet it does not consider the statistical properties of objects, such as color and texture, leading to activations with inconsistent boundaries, and inaccurate localizations.
Diversified Multi-prototype Representation for Semi-supervised Segmentation
This work considers semi-supervised segmentation as a dense prediction problem based on prototype vector correlation and proposes a simple way to represent each segmentation class with multiple prototypes.
Negative Evidence Matters in Interpretable Histology Image Classification
The CNN is exploited to collect both positive and negative evidence at the pixel level to train the decoder.
Boundary-aware Information Maximization for Self-supervised Medical Image Segmentation
Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data.
A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition
Specifically, we propose a joint cross-attention model that relies on the complementary relationships to extract the salient features across A-V modalities, allowing for accurate prediction of continuous values of valence and arousal.
Semi-Weakly Supervised Object Detection by Sampling Pseudo Ground-Truth Boxes
Semi- and weakly-supervised learning have recently attracted considerable attention in the object detection literature since they can alleviate the cost of annotation needed to successfully train deep learning models.
Constrained Sampling for Class-Agnostic Weakly Supervised Object Localization
Then, foreground and background pixels are sampled from these regions in order to train a WSOL model for generating activation maps that can accurately localize objects belonging to a specific class.
Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization
In this paper, we propose a method to train deep weakly-supervised object localization (WSOL) models based only on image-class labels to locate object with high confidence.
Privacy-Preserving Person Detection Using Low-Resolution Infrared Cameras
In intelligent building management, knowing the number of people and their location in a room are important for better control of its illumination, ventilation, and heating with reduced costs and improved comfort.
OCR-VQGAN: Taming Text-within-Image Generation
To alleviate this problem, we present OCR-VQGAN, an image encoder, and decoder that leverages OCR pre-trained features to optimize a text perceptual loss, encouraging the architecture to preserve high-fidelity text and diagram structure.
Camera Alignment and Weighted Contrastive Learning for Domain Adaptation in Video Person ReID
In this scenario, the ReID model must adapt to a complex target domain defined by a network of diverse video cameras based on tracklet information.
Re-basin via implicit Sinkhorn differentiation
The recent emergence of new algorithms for permuting models into functionally equivalent regions of the solution space has shed some light on the complexity of error surfaces, and some promising properties like mode connectivity.
Cascaded Zoom-in Detector for High Resolution Aerial Images
Detecting objects in aerial images is challenging because they are typically composed of crowded small objects distributed non-uniformly over high-resolution images.
Ranked #1 on
2D Object Detection
on VisDrone
CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos
This paper proposes a novel CAM method for WSVOL that exploits spatiotemporal information in activation maps during training without constraining an object's position.
FigGen: Text to Scientific Figure Generation
The generative modeling landscape has experienced tremendous growth in recent years, particularly in generating natural images and art.
Balanced Mixture of SuperNets for Learning the CNN Pooling Architecture
To fully understand this problem, we analyse the performance of models independently trained with each pooling configurations on CIFAR10, using a ResNet20 network, and show that the position of the downsampling layers can highly influence the performance of a network and predefined downsampling configurations are not optimal.
Density Crop-guided Semi-supervised Object Detection in Aerial Images
One of the important bottlenecks in training modern object detectors is the need for labeled images where bounding box annotations have to be produced for each object present in the image.
Ranked #1 on
Object Detection
on VisDrone - 10% labeled data
Multi-Source Domain Adaptation for Object Detection with Prototype-based Mean-teacher
Given the use of prototypes, the number of parameters required for our PMT method does not increase significantly with the number of source domains, thus reducing memory issues and possible overfitting.
Multi-Source Unsupervised Domain Adaptation
object-detection
+2
Bag of Tricks for Fully Test-Time Adaptation
Fully Test-Time Adaptation (TTA), which aims at adapting models to data drifts, has recently attracted wide interest.
HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information
This model produces a new image representation that enhances objects of interest in the scene and greatly improves detection performance.
DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization
Subsequently, these proposals are used as pseudo-labels to train our new transformer-based WSOL model designed to perform classification and localization tasks.
Domain Generalization by Rejecting Extreme Augmentations
However, this holds for standard in-domain settings, in which the training and test data follow the same distribution.
Evaluating Supervision Levels Trade-Offs for Infrared-Based People Counting
Object detection models are commonly used for people counting (and localization) in many applications but require a dataset with costly bounding box annotations for training.
Subject-Based Domain Adaptation for Facial Expression Recognition
However, previous methods for MSDA adapt image classification models across datasets and do not scale well to a larger number of source domains.
Facial Expression Recognition
Facial Expression Recognition (FER)
+2
StarVector: Generating Scalable Vector Graphics Code from Images
These visual tokens are pre-pended to the SVG token embeddings, and the sequence is modeled by the StarCoder model using next-token prediction, effectively learning to align the visual and code tokens.
Distilling Privileged Multimodal Information for Expression Recognition using Optimal Transport
State-of-the-art knowledge distillation (KD) methods have been proposed to distill multiple teacher models (each trained on a modality) to a common student model.
Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues
In particular, using this aus codebook, input image expression label, and facial landmarks, a single action units heatmap is built to indicate the most discriminative regions of interest in the image w. r. t the facial expression.
Facial Expression Recognition
Facial Expression Recognition (FER)
Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptive Object Detection
Domain adaptation methods for object detection (OD) strive to mitigate the impact of distribution shifts by promoting feature alignment across source and target domains.
Joint Multimodal Transformer for Emotion Recognition in the Wild
In this paper, an MMER method is proposed that relies on a joint multimodal transformer for fusion with key-based cross-attention.
Do not trust what you trust: Miscalibration in Semi-supervised Learning
State-of-the-art semi-supervised learning (SSL) approaches rely on highly confident predictions to serve as pseudo-labels that guide the training on unlabeled samples.
Modality Translation for Object Detection Adaptation Without Forgetting Prior Knowledge
This opens the doors to a more flexible and efficient service-based detection pipeline in which, instead of using a different detector for each modality, a unique and unaltered server is constantly running, where multiple modalities with the corresponding translations can query it.
Realistic Model Selection for Weakly Supervised Object Localization
Our experimental results with several WSOL methods on ILSVRC and CUB-200-2011 datasets show that our noisy boxes allow selecting models with performance close to those selected using ground truth boxes, and better than models selected using only image-class labels.
