Domain-specific knowledge can significantly contribute to addressing a wide variety of vision tasks. However, the generation of such knowledge entails considerable human labor and time costs. This study investigates the potential of Large Language Models (LLMs) in generating and providing domain-specific information through semantic embeddings. To achieve this, an LLM is integrated into a pipeline that utilizes Knowledge Graphs and pre-trained semantic vectors in the context of the Vision-based Zero-shot Object State Classification task. We thoroughly examine the behavior of the LLM through an extensive ablation study. Our findings reveal that the integration of LLM-based embeddings, in combination with general-purpose pre-trained embeddings, leads to substantial performance improvements. Drawing insights from this ablation study, we conduct a comparative analysis against competing models, thereby highlighting the state-of-the-art performance achieved by the proposed approach.
This paper studies the Bayesian regret of a variant of the Thompson-Sampling algorithm for bandit problems. It builds upon the information-theoretic framework of [Russo and Van Roy, 2015] and, more specifically, on the rate-distortion analysis from [Dong and Van Roy, 2020], where they proved a bound with regret rate of $O(d\sqrt{T \log(T)})$ for the $d$-dimensional linear bandit setting. We focus on bandit problems with a metric action space and, using a chaining argument, we establish new bounds that depend on the metric entropy of the action space for a variant of Thompson-Sampling. Under suitable continuity assumption of the rewards, our bound offers a tight rate of $O(d\sqrt{T})$ for $d$-dimensional linear bandit problems.
Hierarchical transformers have achieved significant success in medical image segmentation due to their large receptive field and capabilities of effectively leveraging global long-range contextual information. Convolutional neural networks (CNNs) can also deliver a large receptive field by using large kernels, enabling them to achieve competitive performance with fewer model parameters. However, CNNs incorporated with large convolutional kernels remain constrained in adaptively capturing multi-scale features from organs with large variations in shape and size due to the employment of fixed-sized kernels. Additionally, they are unable to utilize global contextual information efficiently. To address these limitations, we propose Dynamic Large Kernel (DLK) and Dynamic Feature Fusion (DFF) modules. The DLK module employs multiple large kernels with varying kernel sizes and dilation rates to capture multi-scale features. Subsequently, a dynamic selection mechanism is utilized to adaptively highlight the most important spatial features based on global information. Additionally, the DFF module is proposed to adaptively fuse multi-scale local feature maps based on their global information. We integrate DLK and DFF in a hierarchical transformer architecture to develop a novel architecture, termed D-Net. D-Net is able to effectively utilize a multi-scale large receptive field and adaptively harness global contextual information. Extensive experimental results demonstrate that D-Net outperforms other state-of-the-art models in the two volumetric segmentation tasks, including abdominal multi-organ segmentation and multi-modality brain tumor segmentation. Our code is available at https://github.com/sotiraslab/DLK.
Grape cluster architecture and compactness are complex traits influencing disease susceptibility, fruit quality, and yield. Evaluation methods for these traits include visual scoring, manual methodologies, and computer vision, with the latter being the most scalable approach. Most of the existing computer vision approaches for processing cluster images often rely on conventional segmentation or machine learning with extensive training and limited generalization. The Segment Anything Model (SAM), a novel foundation model trained on a massive image dataset, enables automated object segmentation without additional training. This study demonstrates out-of-the-box SAM's high accuracy in identifying individual berries in 2D cluster images. Using this model, we managed to segment approximately 3,500 cluster images, generating over 150,000 berry masks, each linked with spatial coordinates within their clusters. The correlation between human-identified berries and SAM predictions was very strong (Pearson r2=0.96). Although the visible berry count in images typically underestimates the actual cluster berry count due to visibility issues, we demonstrated that this discrepancy could be adjusted using a linear regression model (adjusted R2=0.87). We emphasized the critical importance of the angle at which the cluster is imaged, noting its substantial effect on berry counts and architecture. We proposed different approaches in which berry location information facilitated the calculation of complex features related to cluster architecture and compactness. Finally, we discussed SAM's potential integration into currently available pipelines for image generation and processing in vineyard conditions.
Fully-supervised category-level pose estimation aims to determine the 6-DoF poses of unseen instances from known categories, requiring expensive mannual labeling costs. Recently, various self-supervised category-level pose estimation methods have been proposed to reduce the requirement of the annotated datasets. However, most methods rely on synthetic data or 3D CAD model for self-supervised training, and they are typically limited to addressing single-object pose problems without considering multi-objective tasks or shape reconstruction. To overcome these challenges and limitations, we introduce a diffusion-driven self-supervised network for multi-object shape reconstruction and categorical pose estimation, only leveraging the shape priors. Specifically, to capture the SE(3)-equivariant pose features and 3D scale-invariant shape information, we present a Prior-Aware Pyramid 3D Point Transformer in our network. This module adopts a point convolutional layer with radial-kernels for pose-aware learning and a 3D scale-invariant graph convolution layer for object-level shape representation, respectively. Furthermore, we introduce a pretrain-to-refine self-supervised training paradigm to train our network. It enables proposed network to capture the associations between shape priors and observations, addressing the challenge of intra-class shape variations by utilising the diffusion mechanism. Extensive experiments conducted on four public datasets and a self-built dataset demonstrate that our method significantly outperforms state-of-the-art self-supervised category-level baselines and even surpasses some fully-supervised instance-level and category-level methods.
Cross-View Geo-Localization (CVGL) involves determining the geographical location of a query image by matching it with a corresponding GPS-tagged reference image. Current state-of-the-art methods predominantly rely on training models with labeled paired images, incurring substantial annotation costs and training burdens. In this study, we investigate the adaptation of frozen models for CVGL without requiring ground truth pair labels. We observe that training on unlabeled cross-view images presents significant challenges, including the need to establish relationships within unlabeled data and reconcile view discrepancies between uncertain queries and references. To address these challenges, we propose a self-supervised learning framework to train a learnable adapter for a frozen Foundation Model (FM). This adapter is designed to map feature distributions from diverse views into a uniform space using unlabeled data exclusively. To establish relationships within unlabeled data, we introduce an Expectation-Maximization-based Pseudo-labeling module, which iteratively estimates associations between cross-view features and optimizes the adapter. To maintain the robustness of the FM's representation, we incorporate an information consistency module with a reconstruction loss, ensuring that adapted features retain strong discriminative ability across views. Experimental results demonstrate that our proposed method achieves significant improvements over vanilla FMs and competitive accuracy compared to supervised methods, while necessitating fewer training parameters and relying solely on unlabeled data. Evaluation of our adaptation for task-specific models further highlights its broad applicability.
Knowledge graphs (KGs) have become vitally important in modern recommender systems, effectively improving performance and interpretability. Fundamentally, recommender systems aim to identify user interests based on historical interactions and recommend suitable items. However, existing works overlook two key challenges: (1) an interest corresponds to a potentially large set of related items, and (2) the lack of explicit, fine-grained exploitation of KG information and interest connectivity. This leads to an inability to reflect distinctions between entities and interests when modeling them in a single way. Additionally, the granularity of concepts in the knowledge graphs used for recommendations tends to be coarse, failing to match the fine-grained nature of user interests. This homogenization limits the precise exploitation of knowledge graph data and interest connectivity. To address these limitations, we introduce a novel embedding-based model called InBox. Specifically, various knowledge graph entities and relations are embedded as points or boxes, while user interests are modeled as boxes encompassing interaction history. Representing interests as boxes enables containing collections of item points related to that interest. We further propose that an interest comprises diverse basic concepts, and box intersection naturally supports concept combination. Across three training steps, InBox significantly outperforms state-of-the-art methods like HAKG and KGIN on recommendation tasks. Further analysis provides meaningful insights into the variable value of different KG data for recommendations. In summary, InBox advances recommender systems through box-based interest and concept modeling for sophisticated knowledge graph exploitation.
The problem of online social network manipulation for community canvassing is of real concern in today's world. Motivated by the study of voter models, opinion and polarization dynamics on networks, we model community canvassing as a dynamic process over a network enabled via gradient-based attacks on GNNs. Existing attacks on GNNs are all single-step and do not account for the dynamic cascading nature of information diffusion in networks. We consider the realistic scenario where an adversary uses a GNN as a proxy to predict and manipulate voter preferences, especially uncertain voters. Gradient-based attacks on the GNN inform the adversary of strategic manipulations that can be made to proselytize targeted voters. In particular, we explore $\textit{minimum budget attacks for community canvassing}$ (MBACC). We show that the MBACC problem is NP-Hard and propose Dynamic Multi-Step Adversarial Community Canvassing (MAC) to address it. MAC makes dynamic local decisions based on the heuristic of low budget and high second-order influence to convert and perturb target voters. MAC is a dynamic multi-step attack that discovers low-budget and high-influence targets from which efficient cascading attacks can happen. We evaluate MAC against single-step baselines on the MBACC problem with multiple underlying networks and GNN models. Our experiments show the superiority of MAC which is able to discover efficient multi-hop attacks for adversarial community canvassing. Our code implementation and data is available at https://github.com/saurabhsharma1993/mac.
With the recent advancements in single-image-based human mesh recovery, there is a growing interest in enhancing its performance in certain extreme scenarios, such as occlusion, while maintaining overall model accuracy. Although obtaining accurately annotated 3D human poses under occlusion is challenging, there is still a wealth of rich and precise 2D pose annotations that can be leveraged. However, existing works mostly focus on directly leveraging 2D pose coordinates to estimate 3D pose and mesh. In this paper, we present PostoMETRO($\textbf{Pos}$e $\textbf{to}$ken enhanced $\textbf{ME}$sh $\textbf{TR}$ansf$\textbf{O}$rmer), which integrates occlusion-resilient 2D pose representation into transformers in a token-wise manner. Utilizing a specialized pose tokenizer, we efficiently condense 2D pose data to a compact sequence of pose tokens and feed them to the transformer together with the image tokens. This process not only ensures a rich depiction of texture from the image but also fosters a robust integration of pose and image information. Subsequently, these combined tokens are queried by vertex and joint tokens to decode 3D coordinates of mesh vertices and human joints. Facilitated by the robust pose token representation and the effective combination, we are able to produce more precise 3D coordinates, even under extreme scenarios like occlusion. Experiments on both standard and occlusion-specific benchmarks demonstrate the effectiveness of PostoMETRO. Qualitative results further illustrate the clarity of how 2D pose can help 3D reconstruction. Code will be made available.
This paper presents GGRt, a novel approach to generalizable novel view synthesis that alleviates the need for real camera poses, complexity in processing high-resolution images, and lengthy optimization processes, thus facilitating stronger applicability of 3D Gaussian Splatting (3D-GS) in real-world scenarios. Specifically, we design a novel joint learning framework that consists of an Iterative Pose Optimization Network (IPO-Net) and a Generalizable 3D-Gaussians (G-3DG) model. With the joint learning mechanism, the proposed framework can inherently estimate robust relative pose information from the image observations and thus primarily alleviate the requirement of real camera poses. Moreover, we implement a deferred back-propagation mechanism that enables high-resolution training and inference, overcoming the resolution constraints of previous methods. To enhance the speed and efficiency, we further introduce a progressive Gaussian cache module that dynamically adjusts during training and inference. As the first pose-free generalizable 3D-GS framework, GGRt achieves inference at $\ge$ 5 FPS and real-time rendering at $\ge$ 100 FPS. Through extensive experimentation, we demonstrate that our method outperforms existing NeRF-based pose-free techniques in terms of inference speed and effectiveness. It can also approach the real pose-based 3D-GS methods. Our contributions provide a significant leap forward for the integration of computer vision and computer graphics into practical applications, offering state-of-the-art results on LLFF, KITTI, and Waymo Open datasets and enabling real-time rendering for immersive experiences.