AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding

Aligning visual features with language embeddings is a key challenge in vision-language models (VLMs). The performance of such models hinges on having a good connector that maps visual features generated by a vision encoder to a shared embedding space with the LLM while preserving semantic similarity. Existing connectors, such as multilayer perceptrons (MLPs), often produce out-of-distribution or noisy inputs, leading to misalignment between the modalities. In this work, we propose a novel vision-text alignment method, AlignVLM, that maps visual features to a weighted average of LLM text embeddings. Our approach leverages the linguistic priors encoded by the LLM to ensure that visual features are mapped to regions of the space that the LLM can effectively interpret. AlignVLM is particularly effective for document understanding tasks, where scanned document images must be accurately mapped to their textual content. Our extensive experiments show that AlignVLM achieves state-of-the-art performance compared to prior alignment methods. We provide further analysis demonstrating improved vision-text feature alignment and robustness to noise.

BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks

Multimodal AI has the potential to significantly enhance document-understanding tasks, such as processing receipts, understanding workflows, extracting data from documents, and summarizing reports. Code generation tasks that require long-structured outputs can also be enhanced by multimodality. Despite this, their use in commercial applications is often limited due to limited access to training data and restrictive licensing, which hinders open access. To address these limitations, we introduce BigDocs-7.5M, a high-quality, open-access dataset comprising 7.5 million multimodal documents across 30 tasks. We use an efficient data curation process to ensure our data is high-quality and license-permissive. Our process emphasizes accountability, responsibility, and transparency through filtering rules, traceable metadata, and careful content analysis. Additionally, we introduce BigDocs-Bench, a benchmark suite with 10 novel tasks where we create datasets that reflect real-world use cases involving reasoning over Graphical User Interfaces (GUI) and code generation from images. Our experiments show that training with BigDocs-Bench improves average performance up to 25.8% over closed-source GPT-4o in document reasoning and structured output tasks such as Screenshot2HTML or Image2Latex generation. Finally, human evaluations showed a preference for outputs from models trained on BigDocs over GPT-4o. This suggests that BigDocs can help both academics and the open-source community utilize and improve AI tools to enhance multimodal capabilities and document reasoning. The project is hosted at https://bigdocs.github.io .

Visual Modality Prompt for Adapting Vision-Language Object Detectors

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

Words Matter: Leveraging Individual Text Embeddings for Code Generation in CLIP Test-Time Adaptation

Vision-language foundation models, such as CLIP, have shown unprecedented zero-shot performance across a wide range of tasks. Nevertheless, these models may be unreliable under distributional shifts, as their performance is significantly degraded. In this work, we explore how to efficiently leverage class text information to mitigate these distribution drifts encountered by large pre-trained vision-language models (VLMs) during test-time inference. In particular, we propose to generate pseudo-labels for the test-time samples by exploiting generic class text embeddings as fixed centroids of a label assignment problem, which is efficiently solved with Optimal Transport. Furthermore, the proposed adaptation method (CLIP-OT) integrates a multiple template knowledge distillation approach, which replicates multi-view contrastive learning strategies in unsupervised representation learning but without incurring additional computational complexity. Extensive experiments on multiple popular test-time adaptation benchmarks presenting diverse complexity empirically show the superiority of CLIP-OT, achieving performance gains of up to 7% over recent state-of-the-art methods, yet being computationally and memory efficient.

IntentGPT: Few-shot Intent Discovery with Large Language Models

In today's digitally driven world, dialogue systems play a pivotal role in enhancing user interactions, from customer service to virtual assistants. In these dialogues, it is important to identify user's goals automatically to resolve their needs promptly. This has necessitated the integration of models that perform Intent Detection. However, users' intents are diverse and dynamic, making it challenging to maintain a fixed set of predefined intents. As a result, a more practical approach is to develop a model capable of identifying new intents as they emerge. We address the challenge of Intent Discovery, an area that has drawn significant attention in recent research efforts. Existing methods need to train on a substantial amount of data for correctly identifying new intents, demanding significant human effort. To overcome this, we introduce IntentGPT, a novel training-free method that effectively prompts Large Language Models (LLMs) such as GPT-4 to discover new intents with minimal labeled data. IntentGPT comprises an \textit{In-Context Prompt Generator}, which generates informative prompts for In-Context Learning, an \textit{Intent Predictor} for classifying and discovering user intents from utterances, and a \textit{Semantic Few-Shot Sampler} that selects relevant few-shot examples and a set of known intents to be injected into the prompt. Our experiments show that IntentGPT outperforms previous methods that require extensive domain-specific data and fine-tuning, in popular benchmarks, including CLINC and BANKING, among others.

Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy

Unsupervised object discovery is commonly interpreted as the task of localizing and/or categorizing objects in visual data without the need for labeled examples. While current object recognition methods have proven highly effective for practical applications, the ongoing demand for annotated data in real-world scenarios drives research into unsupervised approaches. Furthermore, existing literature in object discovery is both extensive and diverse, posing a significant challenge for researchers that aim to navigate and synthesize this knowledge. Motivated by the evidenced interest in this avenue of research, and the lack of comprehensive studies that could facilitate a holistic understanding of unsupervised object discovery, this survey conducts an in-depth exploration of the existing approaches and systematically categorizes this compendium based on the tasks addressed and the families of techniques employed. Additionally, we present an overview of common datasets and metrics, highlighting the challenges of comparing methods due to varying evaluation protocols. This work intends to provide practitioners with an insightful perspective on the domain, with the hope of inspiring new ideas and fostering a deeper understanding of object discovery approaches.

Source-Free Domain Adaptation for YOLO Object Detection

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.

Multi Teacher Privileged Knowledge Distillation for Multimodal Expression Recognition

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.

Text- and Feature-based Models for Compound Multimodal Emotion Recognition in the Wild

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

Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos

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.