Marco Pedersoli

Unsupervised object discovery is becoming an essential line of research for tackling recognition problems that require decomposing an image … (see more)into entities, such as semantic segmentation and object detection. Recently, object-centric methods that leverage self-supervision have gained popularity, due to their simplicity and adaptability to different settings and conditions. However, those methods do not exploit effective techniques already employed in modern self-supervised approaches. In this work, we consider an object-centric approach in which DINO ViT features are reconstructed via a set of queried representations called slots. Based on that, we propose a masking scheme on input features that selectively disregards the background regions, inducing our model to focus more on salient objects during the reconstruction phase. Moreover, we extend the slot attention to a multi-query approach, allowing the model to learn multiple sets of slots, producing more stable masks. During training, these multiple sets of slots are learned independently while, at test time, these sets are merged through Hungarian matching to obtain the final slots. Our experimental results and ablations on the PASCAL-VOC 2012 dataset show the importance of each component and highlight how their combination consistently improves object localization. Our source code is available at: github.com/rishavpramanik/maskedmultiqueryslot

2024-07-05

2024 International Joint Conference on Neural Networks (IJCNN) (published)

Joint Multimodal Transformer for Emotion Recognition in the Wild

Paul Waligora

Muhammad Haseeb Aslam

Muhammad Osama Zeeshan

Soufiane Belharbi

Alessandro Lameiras Koerich

Simon Bacon

Eric Granger

Multimodal emotion recognition (MMER) systems typically outperform unimodal systems by leveraging the inter-and intra-modal relationships be… (see more)tween, e.g., visual, textual, physiological, and auditory modalities. This paper proposes an MMER method that relies on a joint multi-modal transformer (JMT) for fusion with key-based cross-attention. This framework can exploit the complementary nature of diverse modalities to improve predictive accuracy. Separate backbones capture intra-modal spatiotemporal dependencies within each modality over video sequences. Subsequently, our JMT fusion architecture integrates the individual modality embeddings, allowing the model to effectively capture inter- and intra-modal relationships. Extensive experiments on two challenging expression recognition tasks – (1) dimensional emotion recognition on the Affwild2 dataset (with face and voice) and (2) pain estimation on the Biovid dataset (with face and biosensors) – indicate that our JMT fusion can provide a cost-effective solution for MMER. Empirical results show that MMER systems with our proposed fusion allow us to outperform relevant baseline and state-of-the-art methods. Code is available at: https://github.com/PoloWlg/Joint-Multimodal-Transformer-6th-ABAW

2024-06-17

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (published)

Distilling Privileged Multimodal Information for Expression Recognition using Optimal Transport

Muhammad Haseeb Aslam

Muhammad Osama Zeeshan

Soufiane Belharbi

Alessandro Lameiras Koerich

Simon Bacon

Eric Granger

Deep learning models for multimodal expression recognition have reached remarkable performance in controlled laboratory environments because… (see more) of their ability to learn complementary and redundant semantic information. However, these models struggle in the wild, mainly because of the unavailability and quality of modalities used for training. In practice, only a subset of the training-time modalities may be available at test time. Learning with privileged information enables models to exploit data from additional modalities that are only available during training. State-of-the-art knowledge distillation (KD) methods have been proposed to distill information from multiple teacher models (each trained on a modality) to a common student model. These privileged KD methods typically utilize point-to-point matching, yet have no explicit mechanism to capture the structural information in the teacher representation space formed by introducing the privileged modality. We argue that encoding this same structure in the student space may lead to enhanced student performance. This paper introduces a new structural KD mechanism based on optimal transport (OT), where entropy-regularized OT distills the structural dark knowledge. Our privileged KD with OT (PKDOT) method captures the local structures in the multimodal teacher representation by calculating a cosine similarity matrix and selecting the top-k anchors to allow for sparse OT solutions, resulting in a more stable distillation process. Experiments1 were performed on two challenging problems - pain estimation on the Biovid dataset (ordinal classification) and arousal-valance prediction on the Affwild2 dataset (regression). Results show that our proposed method can outperform state-of-the-art privileged KD methods on these problems. The diversity among modalities and fusion architectures indicates that PKDOT is modality-and model-agnostic.

2024-05-27

2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG) (published)

Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues

Soufiane Belharbi

Alessandro Lameiras Koerich

Simon Bacon

Eric Granger

Although state-of-the-art classifiers for facial expression recognition (FER) can achieve a high level of accuracy, they lack interpretabili… (see more)ty, an important feature for end-users. Experts typically associate spatial action units (AUs) from a codebook to facial regions for the visual interpretation of expressions. In this paper, the same expert steps are followed. A new learning strategy is proposed to explicitly incorporate AU cues into classifier training, allowing to train deep interpretable models. During training, this AU codebook is used, along with the input image expression label, and facial landmarks, to construct a AU heatmap that indicates the most discriminative image regions of interest w.r.t the facial expression. This valuable spatial cue is leveraged to train a deep interpretable classifier for FER. This is achieved by constraining the spatial layer features of a classifier to be correlated with AU heatmaps. Using a composite loss, the classifier is trained to correctly classify an image while yielding interpretable visual layer-wise attention correlated with AU maps, simulating the expert decision process. Our strategy only relies on image class expression for supervision, without additional manual annotations. Our new strategy is generic, and can be applied to any deep CNN - or transformer-based classifier without requiring any architectural change or significant additional training time. Our extensive evaluation11Our code is available at:https://github.com/sbelharbi/interpretable-fer-aus. on two public benchmarks RAF-DB, and AffectNet datasets shows that our proposed strategy can improve layer-wise interpretability without degrading classification performance. In addition, we explore a common type of interpretable classifiers that rely on class activation mapping (CAM) methods, and show that our approach can also improve CAM interpretability.

2024-05-27

2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG) (published)

Subject-Based Domain Adaptation for Facial Expression Recognition

Muhammad Osama Zeeshan

Muhammad Haseeb Aslam

Soufiane Belharbi

Alessandro Lameiras Koerich

Simon Bacon

Eric Granger

Adapting a deep learning model to a specific target individual is a challenging facial expression recognition (FER) task that may be achieve… (see more)d using unsupervised domain adaptation (UDA) methods. Although several UDA methods have been proposed to adapt deep FER models across source and target data sets, multiple subject-specific source domains are needed to accurately represent the intra-and inter-person variability in subject-based adaption. This paper considers the setting where domains correspond to individuals, not entire datasets. Unlike UDA, multi-source domain adaptation (MSDA) methods can leverage multiple source datasets to improve the accuracy and robustness of the target model. However, previous methods for MSDA adapt image classification models across datasets and do not scale well to a more significant number of source domains. This paper introduces a new MSDA method for subject-based domain adaptation in FER. It efficiently leverages information from multiple source subjects (labeled source domain data) to adapt a deep FER model to a single target individual (unlabeled target domain data). During adaptation, our subject-based MSDA first computes a between-source discrepancy loss to mitigate the domain shift among data from several source subjects. Then, a new strategy is employed to generate augmented confident pseudo-labels for the target subject, allowing a reduction in the domain shift between source and target subjects. Experiments1 performed on the challenging BioVid heat and pain dataset with 87 subjects and the UNBC-McMaster shoulder pain dataset with 25 subjects show that our subject-based MSDA can outperform state-of-the-art methods yet scale well to multiple subject-based source domains.

2024-05-27

2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG) (published)

MiPa: Mixed Patch Infrared-Visible Modality Agnostic Object Detection

Heitor R. Medeiros

David Latortue

Eric Granger

Fidel A. Guerrero Peña

2024-04-29

ArXiv (preprint)

A Realistic Protocol for Evaluation of Weakly Supervised Object Localization

Shakeeb Murtaza

Soufiane Belharbi

Eric Granger

Weakly Supervised Object Localization (WSOL) allows training deep learning models for classification and localization (LOC) using only globa… (see more)l class-level labels. The absence of bounding box (bbox) supervision during training raises challenges in the literature for hyper-parameter tuning, model selection, and evaluation. WSOL methods rely on a validation set with bbox annotations for model selection, and a test set with bbox annotations for threshold estimation for producing bboxes from localization maps. This approach, however, is not aligned with the WSOL setting as these annotations are typically unavailable in real-world scenarios. Our initial empirical analysis shows a significant decline in LOC performance when model selection and threshold estimation rely solely on class labels and the image itself, respectively, compared to using manual bbox annotations. This highlights the importance of incorporating bbox labels for optimal model performance. In this paper, a new WSOL evaluation protocol is proposed that provides LOC information without the need for manual bbox annotations. In particular, we generated noisy pseudo-boxes from a pretrained off-the-shelf region proposal method such as Selective Search, CLIP, and RPN for model selection. These bboxes are also employed to estimate the threshold from LOC maps, circumventing the need for test-set bbox annotations. Our experiments with several WSOL methods on ILSVRC and CUB datasets show that using the proposed pseudo-bboxes for validation facilitates the model selection and threshold estimation, with LOC performance comparable to those selected using GT bboxes on the validation set and threshold estimation on the test set. It also outperforms models selected using class-level labels, and then dynamically thresholded based solely on LOC maps.

2024-04-15

ArXiv (preprint)

Modality Translation for Object Detection Adaptation Without Forgetting Prior Knowledge

Heitor R. Medeiros

Masih Aminbeidokhti

Fidel A. Guerrero Peña

David Latortue

Eric Granger

A common practice in deep learning involves training large neural networks on massive datasets to achieve high accuracy across various domai… (see more)ns and tasks. While this approach works well in many application areas, it often fails drastically when processing data from a new modality with a significant distribution shift from the data used to pre-train the model. This paper focuses on adapting a large object detection model trained on RGB images to new data extracted from IR images with a substantial modality shift. We propose Modality Translator (ModTr) as an alternative to the common approach of fine-tuning a large model to the new modality. ModTr adapts the IR input image with a small transformation network trained to directly minimize the detection loss. The original RGB model can then work on the translated inputs without any further changes or fine-tuning to its parameters. Experimental results on translating from IR to RGB images on two well-known datasets show that our simple approach provides detectors that perform comparably or better than standard fine-tuning, without forgetting the knowledge of the original model. This opens the door to a more flexible and efficient service-based detection pipeline, where a unique and unaltered server, such as an RGB detector, runs constantly while being queried by different modalities, such as IR with the corresponding translations model. Our code is available at: https://github.com/heitorrapela/ModTr.

2024-04-01

ArXiv (preprint)

IntentGPT: Few-shot Intent Discovery with Large Language Models

Juan A. Rodriguez

Nicholas Botzer

David Vazquez

Chris Pal

Issam Hadj Laradji

2024-03-11

ICLR.cc/2024/Workshop/LLMAgents (poster)

openreview.net

IntentGPT: Few-shot Intent Discovery with Large Language Models

Juan A. Rodriguez

Nicholas Botzer

David Vazquez

Chris Pal

Issam Hadj Laradji

2024-03-11

ICLR.cc/2024/Workshop/LLMAgents (poster)

openreview.net

Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectors

Atif Belal

Akhil Meethal

Francisco Perdigon Romero

Eric Granger

Domain adaptation methods for object detection (OD) strive to mitigate the impact of distribution shifts by promoting feature alignment acro… (see more)ss source and target domains. Multi-source domain adaptation (MSDA) allows leveraging multiple annotated source datasets and unlabeled target data to improve the accuracy and robustness of the detection model. Most state-of-the-art MSDA methods for OD perform feature alignment in a class-agnostic manner. This is challenging since the objects have unique modality information due to variations in object appearance across domains. A recent prototype-based approach proposed a class-wise alignment, yet it suffers from error accumulation caused by noisy pseudo-labels that can negatively affect adaptation with imbalanced data. To overcome these limitations, we propose an attention-based class-conditioned alignment method for MSDA, designed to align instances of each object category across domains. In particular, an attention module combined with an adversarial domain classifier allows learning domain-invariant and class-specific instance representations. Experimental results on multiple benchmarking MSDA datasets indicate that our method outperforms state-of-the-art methods and exhibits robustness to class imbalance, achieved through a conceptually simple class-conditioning strategy. Our code is available at: https://github.com/imatif17/ACIA.

2024-03-01

arXiv (published)

Do not trust what you trust: Miscalibration in Semi-supervised Learning

Shambhavi Mishra

Balamurali Murugesan

Ismail Ben Ayed

Jose Dolz

State-of-the-art semi-supervised learning (SSL) approaches rely on highly confident predictions to serve as pseudo-labels that guide the tra… (see more)ining on unlabeled samples. An inherent drawback of this strategy stems from the quality of the uncertainty estimates, as pseudo-labels are filtered only based on their degree of uncertainty, regardless of the correctness of their predictions. Thus, assessing and enhancing the uncertainty of network predictions is of paramount importance in the pseudo-labeling process. In this work, we empirically demonstrate that SSL methods based on pseudo-labels are significantly miscalibrated, and formally demonstrate the minimization of the min-entropy, a lower bound of the Shannon entropy, as a potential cause for miscalibration. To alleviate this issue, we integrate a simple penalty term, which enforces the logit distances of the predictions on unlabeled samples to remain low, preventing the network predictions to become overconfident. Comprehensive experiments on a variety of SSL image classification benchmarks demonstrate that the proposed solution systematically improves the calibration performance of relevant SSL models, while also enhancing their discriminative power, being an appealing addition to tackle SSL tasks.

2024-03-01

arXiv (published)