Abstract:The zero-shot performance of object detectors degrades when tested on different modalities, such as infrared and depth. While recent work has explored image translation techniques to adapt detectors to new modalities, these methods are limited to a single modality and apply only to traditional detectors. Recently, vision-language detectors, such as YOLO-World and Grounding DINO, have shown promising zero-shot capabilities, however, they have not yet been adapted for other visual modalities. Traditional fine-tuning approaches tend to compromise the zero-shot capabilities of the detectors. The visual prompt strategies commonly used for classification with vision-language models apply the same linear prompt translation to each image making them less effective. To address these limitations, we propose ModPrompt, a visual prompt strategy to adapt vision-language detectors to new modalities without degrading zero-shot performance. In particular, an encoder-decoder visual prompt strategy is proposed, further enhanced by the integration of inference-friendly task residuals, facilitating more robust adaptation. Empirically, we benchmark our method for modality adaptation on two vision-language detectors, YOLO-World and Grounding DINO, and on challenging infrared (LLVIP, FLIR) and depth (NYUv2) data, achieving performance comparable to full fine-tuning while preserving the model's zero-shot capability. Our code is available at: https://github.com/heitorrapela/ModPrompt
Abstract:Diffusion models have emerged as highly effective techniques for inpainting, however, they remain constrained by slow sampling rates. While recent advances have enhanced generation quality, they have also increased sampling time, thereby limiting scalability in real-world applications. We investigate the generative sampling process of diffusion-based inpainting models and observe that these models make minimal use of the input condition during the initial sampling steps. As a result, the sampling trajectory deviates from the data manifold, requiring complex synchronization mechanisms to realign the generation process. To address this, we propose Time-aware Diffusion Paint (TD-Paint), a novel approach that adapts the diffusion process by modeling variable noise levels at the pixel level. This technique allows the model to efficiently use known pixel values from the start, guiding the generation process toward the target manifold. By embedding this information early in the diffusion process, TD-Paint significantly accelerates sampling without compromising image quality. Unlike conventional diffusion-based inpainting models, which require a dedicated architecture or an expensive generation loop, TD-Paint achieves faster sampling times without architectural modifications. Experimental results across three datasets show that TD-Paint outperforms state-of-the-art diffusion models while maintaining lower complexity.
Abstract:Source-free domain adaptation (SFDA) is a challenging problem in object detection, where a pre-trained source model is adapted to a new target domain without using any source domain data for privacy and efficiency reasons. Most state-of-the-art SFDA methods for object detection have been proposed for Faster-RCNN, a detector that is known to have high computational complexity. This paper focuses on domain adaptation techniques for real-world vision systems, particularly for the YOLO family of single-shot detectors known for their fast baselines and practical applications. Our proposed SFDA method - Source-Free YOLO (SF-YOLO) - relies on a teacher-student framework in which the student receives images with a learned, target domain-specific augmentation, allowing the model to be trained with only unlabeled target data and without requiring feature alignment. A challenge with self-training using a mean-teacher architecture in the absence of labels is the rapid decline of accuracy due to noisy or drifting pseudo-labels. To address this issue, a teacher-to-student communication mechanism is introduced to help stabilize the training and reduce the reliance on annotated target data for model selection. Despite its simplicity, our approach is competitive with state-of-the-art detectors on several challenging benchmark datasets, even sometimes outperforming methods that use source data for adaptation.
Abstract:Human emotion is a complex phenomenon conveyed and perceived through facial expressions, vocal tones, body language, and physiological signals. Multimodal emotion recognition systems can perform well because they can learn complementary and redundant semantic information from diverse sensors. In real-world scenarios, only a subset of the modalities employed for training may be available at test time. Learning privileged information allows a model to exploit data from additional modalities that are only available during training. SOTA methods for PKD have been proposed to distill information from a teacher model (with privileged modalities) to a student model (without privileged modalities). However, such PKD methods utilize point-to-point matching and do not explicitly capture the relational information. Recently, methods have been proposed to distill the structural information. However, PKD methods based on structural similarity are primarily confined to learning from a single joint teacher representation, which limits their robustness, accuracy, and ability to learn from diverse multimodal sources. In this paper, a multi-teacher PKD (MT-PKDOT) method with self-distillation is introduced to align diverse teacher representations before distilling them to the student. MT-PKDOT employs a structural similarity KD mechanism based on a regularized optimal transport (OT) for distillation. The proposed MT-PKDOT method was validated on the Affwild2 and Biovid datasets. Results indicate that our proposed method can outperform SOTA PKD methods. It improves the visual-only baseline on Biovid data by 5.5%. On the Affwild2 dataset, the proposed method improves 3% and 5% over the visual-only baseline for valence and arousal respectively. Allowing the student to learn from multiple diverse sources is shown to increase the accuracy and implicitly avoids negative transfer to the student model.
Abstract:Systems for multimodal Emotion Recognition (ER) commonly rely on features extracted from different modalities (e.g., visual, audio, and textual) to predict the seven basic emotions. However, compound emotions often occur in real-world scenarios and are more difficult to predict. Compound multimodal ER becomes more challenging in videos due to the added uncertainty of diverse modalities. In addition, standard features-based models may not fully capture the complex and subtle cues needed to understand compound emotions. %%%% Since relevant cues can be extracted in the form of text, we advocate for textualizing all modalities, such as visual and audio, to harness the capacity of large language models (LLMs). These models may understand the complex interaction between modalities and the subtleties of complex emotions. Although training an LLM requires large-scale datasets, a recent surge of pre-trained LLMs, such as BERT and LLaMA, can be easily fine-tuned for downstream tasks like compound ER. This paper compares two multimodal modeling approaches for compound ER in videos -- standard feature-based vs. text-based. Experiments were conducted on the challenging C-EXPR-DB dataset for compound ER, and contrasted with results on the MELD dataset for basic ER. Our code is available
Abstract:Weakly-Supervised Video Object Localization (WSVOL) involves localizing an object in videos using only video-level labels, also referred to as tags. State-of-the-art WSVOL methods like Temporal CAM (TCAM) rely on class activation mapping (CAM) and typically require a pre-trained CNN classifier. However, their localization accuracy is affected by their tendency to minimize the mutual information between different instances of a class and exploit temporal information during training for downstream tasks, e.g., detection and tracking. In the absence of bounding box annotation, it is challenging to exploit precise information about objects from temporal cues because the model struggles to locate objects over time. To address these issues, a novel method called transformer based CAM for videos (TrCAM-V), is proposed for WSVOL. It consists of a DeiT backbone with two heads for classification and localization. The classification head is trained using standard classification loss (CL), while the localization head is trained using pseudo-labels that are extracted using a pre-trained CLIP model. From these pseudo-labels, the high and low activation values are considered to be foreground and background regions, respectively. Our TrCAM-V method allows training a localization network by sampling pseudo-pixels on the fly from these regions. Additionally, a conditional random field (CRF) loss is employed to align the object boundaries with the foreground map. During inference, the model can process individual frames for real-time localization applications. Extensive experiments on challenging YouTube-Objects unconstrained video datasets show that our TrCAM-V method achieves new state-of-the-art performance in terms of classification and localization accuracy.
Abstract:Confocal fluorescence microscopy is one of the most accessible and widely used imaging techniques for the study of biological processes. Scanning confocal microscopy allows the capture of high-quality images from 3D samples, yet suffers from well-known limitations such as photobleaching and phototoxicity of specimens caused by intense light exposure, which limits its use in some applications, especially for living cells. Cellular damage can be alleviated by changing imaging parameters to reduce light exposure, often at the expense of image quality. Machine/deep learning methods for single-image super-resolution (SISR) can be applied to restore image quality by upscaling lower-resolution (LR) images to produce high-resolution images (HR). These SISR methods have been successfully applied to photo-realistic images due partly to the abundance of publicly available data. In contrast, the lack of publicly available data partly limits their application and success in scanning confocal microscopy. In this paper, we introduce a large scanning confocal microscopy dataset named SR-CACO-2 that is comprised of low- and high-resolution image pairs marked for three different fluorescent markers. It allows the evaluation of performance of SISR methods on three different upscaling levels (X2, X4, X8). SR-CACO-2 contains the human epithelial cell line Caco-2 (ATCC HTB-37), and it is composed of 22 tiles that have been translated in the form of 9,937 image patches for experiments with SISR methods. Given the new SR-CACO-2 dataset, we also provide benchmarking results for 15 state-of-the-art methods that are representative of the main SISR families. Results show that these methods have limited success in producing high-resolution textures, indicating that SR-CACO-2 represents a challenging problem. Our dataset, code and pretrained weights are available: https://github.com/sbelharbi/sr-caco-2.
Abstract:Given the emergence of deep learning, digital pathology has gained popularity for cancer diagnosis based on histology images. Deep weakly supervised object localization (WSOL) models can be trained to classify histology images according to cancer grade and identify regions of interest (ROIs) for interpretation, using inexpensive global image-class annotations. A WSOL model initially trained on some labeled source image data can be adapted using unlabeled target data in cases of significant domain shifts caused by variations in staining, scanners, and cancer type. In this paper, we focus on source-free (unsupervised) domain adaptation (SFDA), a challenging problem where a pre-trained source model is adapted to a new target domain without using any source domain data for privacy and efficiency reasons. SFDA of WSOL models raises several challenges in histology, most notably because they are not intended to adapt for both classification and localization tasks. In this paper, 4 state-of-the-art SFDA methods, each one representative of a main SFDA family, are compared for WSOL in terms of classification and localization accuracy. They are the SFDA-Distribution Estimation, Source HypOthesis Transfer, Cross-Domain Contrastive Learning, and Adaptively Domain Statistics Alignment. Experimental results on the challenging Glas (smaller, breast cancer) and Camelyon16 (larger, colon cancer) histology datasets indicate that these SFDA methods typically perform poorly for localization after adaptation when optimized for classification.
Abstract:In this paper, we present a different way to use two modalities, in which either one modality or the other is seen by a single model. This can be useful when adapting an unimodal model to leverage more information while respecting a limited computational budget. This would mean having a single model that is able to deal with any modalities. To describe this, we coined the term anymodal learning. An example of this, is a use case where, surveillance in a room when the lights are off would be much more valuable using an infrared modality while a visible one would provide more discriminative information when lights are on. This work investigates how to efficiently leverage visible and infrared/thermal modalities for transformer-based object detection backbone to create an anymodal architecture. Our work does not create any inference overhead during the testing while exploring an effective way to exploit the two modalities during the training. To accomplish such a task, we introduce the novel anymodal training technique: Mixed Patches (MiPa), in conjunction with a patch-wise domain agnostic module, which is responsible of learning the best way to find a common representation of both modalities. This approach proves to be able to balance modalities by reaching competitive results on individual modality benchmarks with the alternative of using an unimodal architecture on three different visible-infrared object detection datasets. Finally, our proposed method, when used as a regularization for the strongest modality, can beat the performance of multimodal fusion methods while only requiring a single modality during inference. Notably, MiPa became the state-of-the-art on the LLVIP visible/infrared benchmark. Code: https://github.com/heitorrapela/MiPa
Abstract:Weakly Supervised Object Localization (WSOL) allows for training deep learning models for classification and localization, using only global class-level labels. The lack of bounding box (bbox) supervision during training represents a considerable challenge for hyper-parameter search and model selection. Earlier WSOL works implicitly observed localization performance over a test set which leads to biased performance evaluation. More recently, a better WSOL protocol has been proposed, where a validation set with bbox annotations is held out for model selection. Although it does not rely on the test set, this protocol is unrealistic since bboxes are not available in real-world applications, and when available, it is better to use them directly to fit model weights. Our initial empirical analysis shows that the localization performance of a model declines significantly when using only image-class labels for model selection (compared to using bounding-box annotations). This suggests that adding bounding-box labels is preferable for selecting the best model for localization. In this paper, we introduce a new WSOL validation protocol that provides a localization signal without the need for manual bbox annotations. In particular, we leverage noisy pseudo boxes from an off-the-shelf ROI proposal generator such as Selective-Search, CLIP, and RPN pretrained models for model selection. 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.