This paper introduces VLAP, a novel approach that bridges pretrained vision models and large language models (LLMs) to make frozen LLMs understand the visual world. VLAP transforms the embedding space of pretrained vision models into the LLMs' word embedding space using a single linear layer for efficient and general-purpose visual and language understanding. Specifically, we harness well-established word embeddings to bridge two modality embedding spaces. The visual and text representations are simultaneously assigned to a set of word embeddings within pretrained LLMs by formulating the assigning procedure as an optimal transport problem. We predict the assignment of one modality from the representation of another modality data, enforcing consistent assignments for paired multimodal data. This allows vision and language representations to contain the same information, grounding the frozen LLMs' word embedding space in visual data. Moreover, a robust semantic taxonomy of LLMs can be preserved with visual data since the LLMs interpret and reason linguistic information from correlations between word embeddings. Experimental results show that VLAP achieves substantial improvements over the previous linear transformation-based approaches across a range of vision-language tasks, including image captioning, visual question answering, and cross-modal retrieval. We also demonstrate the learned visual representations hold a semantic taxonomy of LLMs, making visual semantic arithmetic possible.
Visual scenes are naturally organized in a hierarchy, where a coarse semantic is recursively comprised of several fine details. Exploring such a visual hierarchy is crucial to recognize the complex relations of visual elements, leading to a comprehensive scene understanding. In this paper, we propose a Visual Hierarchy Mapper (Hi-Mapper), a novel approach for enhancing the structured understanding of the pre-trained Deep Neural Networks (DNNs). Hi-Mapper investigates the hierarchical organization of the visual scene by 1) pre-defining a hierarchy tree through the encapsulation of probability densities; and 2) learning the hierarchical relations in hyperbolic space with a novel hierarchical contrastive loss. The pre-defined hierarchy tree recursively interacts with the visual features of the pre-trained DNNs through hierarchy decomposition and encoding procedures, thereby effectively identifying the visual hierarchy and enhancing the recognition of an entire scene. Extensive experiments demonstrate that Hi-Mapper significantly enhances the representation capability of DNNs, leading to an improved performance on various tasks, including image classification and dense prediction tasks.
Given the inevitability of domain shifts during inference in real-world applications, test-time adaptation (TTA) is essential for model adaptation after deployment. However, the real-world scenario of continuously changing target distributions presents challenges including catastrophic forgetting and error accumulation. Existing TTA methods for non-stationary domain shifts, while effective, incur excessive computational load, making them impractical for on-device settings. In this paper, we introduce a layer-wise auto-weighting algorithm for continual and gradual TTA that autonomously identifies layers for preservation or concentrated adaptation. By leveraging the Fisher Information Matrix (FIM), we first design the learning weight to selectively focus on layers associated with log-likelihood changes while preserving unrelated ones. Then, we further propose an exponential min-max scaler to make certain layers nearly frozen while mitigating outliers. This minimizes forgetting and error accumulation, leading to efficient adaptation to non-stationary target distribution. Experiments on CIFAR-10C, CIFAR-100C, and ImageNet-C show our method outperforms conventional continual and gradual TTA approaches while significantly reducing computational load, highlighting the importance of FIM-based learning weight in adapting to continuously or gradually shifting target domains.
Recent DETR-based video grounding models have made the model directly predict moment timestamps without any hand-crafted components, such as a pre-defined proposal or non-maximum suppression, by learning moment queries. However, their input-agnostic moment queries inevitably overlook an intrinsic temporal structure of a video, providing limited positional information. In this paper, we formulate an event-aware dynamic moment query to enable the model to take the input-specific content and positional information of the video into account. To this end, we present two levels of reasoning: 1) Event reasoning that captures distinctive event units constituting a given video using a slot attention mechanism; and 2) moment reasoning that fuses the moment queries with a given sentence through a gated fusion transformer layer and learns interactions between the moment queries and video-sentence representations to predict moment timestamps. Extensive experiments demonstrate the effectiveness and efficiency of the event-aware dynamic moment queries, outperforming state-of-the-art approaches on several video grounding benchmarks.
Aerial-to-ground image synthesis is an emerging and challenging problem that aims to synthesize a ground image from an aerial image. Due to the highly different layout and object representation between the aerial and ground images, existing approaches usually fail to transfer the components of the aerial scene into the ground scene. In this paper, we propose a novel framework to explore the challenges by imposing enhanced structural alignment and semantic awareness. We introduce a novel semantic-attentive feature transformation module that allows to reconstruct the complex geographic structures by aligning the aerial feature to the ground layout. Furthermore, we propose semantic-aware loss functions by leveraging a pre-trained segmentation network. The network is enforced to synthesize realistic objects across various classes by separately calculating losses for different classes and balancing them. Extensive experiments including comparisons with previous methods and ablation studies show the effectiveness of the proposed framework both qualitatively and quantitatively.
Compositional zero-shot learning (CZSL) aims to recognize unseen compositions with prior knowledge of known primitives (attribute and object). Previous works for CZSL often suffer from grasping the contextuality between attribute and object, as well as the discriminability of visual features, and the long-tailed distribution of real-world compositional data. We propose a simple and scalable framework called Composition Transformer (CoT) to address these issues. CoT employs object and attribute experts in distinctive manners to generate representative embeddings, using the visual network hierarchically. The object expert extracts representative object embeddings from the final layer in a bottom-up manner, while the attribute expert makes attribute embeddings in a top-down manner with a proposed object-guided attention module that models contextuality explicitly. To remedy biased prediction caused by imbalanced data distribution, we develop a simple minority attribute augmentation (MAA) that synthesizes virtual samples by mixing two images and oversampling minority attribute classes. Our method achieves SoTA performance on several benchmarks, including MIT-States, C-GQA, and VAW-CZSL. We also demonstrate the effectiveness of CoT in improving visual discrimination and addressing the model bias from the imbalanced data distribution. The code is available at https://github.com/HanjaeKim98/CoT.
Modern data augmentation using a mixture-based technique can regularize the models from overfitting to the training data in various computer vision applications, but a proper data augmentation technique tailored for the part-based Visible-Infrared person Re-IDentification (VI-ReID) models remains unexplored. In this paper, we present a novel data augmentation technique, dubbed PartMix, that synthesizes the augmented samples by mixing the part descriptors across the modalities to improve the performance of part-based VI-ReID models. Especially, we synthesize the positive and negative samples within the same and across different identities and regularize the backbone model through contrastive learning. In addition, we also present an entropy-based mining strategy to weaken the adverse impact of unreliable positive and negative samples. When incorporated into existing part-based VI-ReID model, PartMix consistently boosts the performance. We conduct experiments to demonstrate the effectiveness of our PartMix over the existing VI-ReID methods and provide ablation studies.
Recent progress in deterministic prompt learning has become a promising alternative to various downstream vision tasks, enabling models to learn powerful visual representations with the help of pre-trained vision-language models. However, this approach results in limited performance for dense prediction tasks that require handling more complex and diverse objects, since a single and deterministic description cannot sufficiently represent the entire image. In this paper, we present a novel probabilistic prompt learning to fully exploit the vision-language knowledge in dense prediction tasks. First, we introduce learnable class-agnostic attribute prompts to describe universal attributes across the object class. The attributes are combined with class information and visual-context knowledge to define the class-specific textual distribution. Text representations are sampled and used to guide the dense prediction task using the probabilistic pixel-text matching loss, enhancing the stability and generalization capability of the proposed method. Extensive experiments on different dense prediction tasks and ablation studies demonstrate the effectiveness of our proposed method.