arXiv subjects

Ranga Rodrigo

Publications and source records attributed to Ranga Rodrigo.

At least 19 recordsLinked to original sources

arXiv2026

M-PFT: Angular Margin for Calibrated Prompt-Tuning of Fine-Tuned Vision-Language Models

Prompt-tuning has emerged as a parameter-efficient technique for adapting large-scale vision-language models (VLMs) to downstream tasks while keeping the pre-trained weights frozen. However, prompt-tuned VLMs often suffer from a base-to-novel dual miscalibration problem, where models typically show underconfidence on base classes and overconfidence on novel classes. Current VLM calibration approaches address this dual miscalibration either separately or jointly, but lack a geometric understanding of the hyperspherical embedding space and thus fail to exploit angular discriminative properties to adjust distorted decision boundaries. To address this, we propose M-PFT, a novel angular-margin approach for prompt tuning that introduces two complementary objectives to promote class discriminability and semantic anchoring. This enlarges the angular margin by 1) minimizing the maximum cosine similarity between tunable class embeddings to reduce embedding collapse and 2) minimizing the angular distance between each tunable embedding and its corresponding zero-shot embedding to preserve semantic geometry. Extensive experiments across 9 prompt-tuning methods with various backbones on 15 diverse datasets show that our approach reduces the average calibration error on novel classes, while remaining competitive on base classes and maintaining comparable accuracy. Further analyses reveal that M-PFT effectively adjusts distorted decision boundaries induced by prompt tuning while preserving the pre-trained embedding space, improving calibration with negligible computational overhead.

cs.CV↗

arXiv2026

PathKGen: Pathology Knowledge Assisted MLLM for Explainable Histopathology

Whole Slide Image (WSI) analysis serves as the fundamental method for the clinical diagnosis of cancer in digital histopathology. Recent advances in Multimodal Large Language Models (MLLMs) have enabled state-of-the-art (SOTA) automated histopathology report generation. However, MLLMs reason purely through distributions encoded in their neural parameters, limiting the amount of knowledge and reasoning logic they can contain given the model scale. Their black-box reasoning poses another challenge to the human interpretation of intermediate reasoning. We address these issues by utilizing knowledge graphs to inject external structured knowledge for MLLMs to reason over, while making this reasoning component visible. Knowledge graphs are capable of partially externalizing the containment of medical knowledge, an area that remains underexplored in pathology report generation. We introduce PathKGen, a knowledge graph-assisted MLLM for histopathology report generation. PathKGen has two main branches: (1) a visual path that learns visual token inputs to the MLLM using pathology foundation models, and (2) a knowledge path that learns knowledge token inputs by extracting key morphological features of WSIs through querying a pathology-specific knowledge graph. A comprehensive evaluation on WSI-Bench dataset shows that PathKGen surpasses previous SOTA methods while revealing diagnostic reasoning as visually intuitive graphs. Due to its modular design, the proposed knowledge path is complementary to vision-aligned MLLMs and can be extended to other applications by curating domain-specific knowledge graphs to generate knowledge tokens.

cs.CV↗

arXiv2026

LoRASpace: A Pool-Wide Shared Substrate for Static and Dynamic Multi-LoRA Composition

Low-rank adaptation (LoRA) attaches small low-rank matrices to a frozen backbone, and public repositories host many LoRAs per backbone, each for a different concept or task. Combining several LoRAs in one generation forces a trade-off. Merging their weights into one update needs a single forward pass, but LoRAs trained for different concepts interfere and quality drops. Running each LoRA in its own forward pass (composite) preserves quality, but inference time grows linearly with the number of active LoRAs. We study a property of LoRA pools overlooked by prior multi-LoRA work. In real LoRA pools, the stacked low-rank factors need far fewer directions than their summed ranks. Using singular value decomposition, we find the minimal subspace that keeps 99% of the factor energy. On three diffusion pools, only 46% to 57% of the summed LoRA ranks is needed, and the subspace grows sub-linearly with pool size. A 48-LoRA sub-pool of LoRA-Hub on FLAN-T5 tasks shows comparable overlap (62%), while the diversity-curated LoRA-Retriever benchmark sits near the no-overlap baseline (96%), so pool composition rather than modality predicts where compression is large. We build on this overlap with LoRASpace, a training-free method that computes the subspace once per pool and reuses it in two inference modes, a static mode at merge cost and a dynamic mode for input-dependent routing. On the diffusion pools, static LoRASpace matches composite quality at merge cost, and dynamic LoRASpace is more than 6x faster than composite with six active LoRAs on a 17-LoRA pool, mainly because it runs one backbone pass instead of six. In an ablation, static variants at the same rank match LoRASpace, so the quality gain does not depend on the pool-wide basis. On the near-orthogonal LoRA-Retriever benchmark, compression is small and gains come from coupling with external retrieval.

cs.CV↗

arXiv2026

Frame-Consistent Feed-Forward 3D Gaussian Splatting from Sparse Unposed Images

Feed-forward Gaussian models have made novel view synthesis almost instantaneous. Feed-forward methods predict Gaussians directly, either in two stages or in a single merged pass. Using two separately trained models is attractive because each can specialize in its own objective: one for accurate pose estimation and the other for high-quality reconstruction, rather than forcing a single jointly trained network to compromise between the two. A natural instantiation pairs a frozen pose estimator, VGGT, with a frozen reconstruction backbone, TokenGS. Prior work, such as VGGT-X and 3R-GS, also adopts a two-stage design, but attributes the resulting quality degradation to noisy pose estimates and introduces learned refinement. We show that this is not the primary source of the problem. Through per-camera analysis across 107 scenes from two datasets, DL3DV and MipNeRF360, using COLMAP poses as the reference, we find that the rotation error after alignment is small (median 1.6 degrees), whereas the translation scale is offset by a large, dataset-consistent factor. Controlled ablations over 140 DL3DV scenes show that the primary obstacles are two integration failures rather than pose error: a coordinate-frame inconsistency and a translation-scale mismatch, both of which can be corrected deterministically. With these fixes, a frozen VGGT driving a frozen TokenGS achieves 22.47 PSNR, within 0.51 dB of the COLMAP reference, with no additional training, when poses are estimated from all scene views. In the sparse setting, where reconstruction uses only four context images under the standard pose-free protocol, the same pipeline matches this all-view quality, yielding a fully COLMAP-free pipeline without any refinement step.

cs.CV↗

arXiv2026

Sim-to-Real Transfer of Vision-Language Navigation in Continuous Environments Using an Ackermann-Steered Mobile Robot

Vision-Language Navigation (VLN) enables robots to navigate through environments using natural language instructions, making human-robot interaction intuitive. Traditional VLN models often rely on navigation graphs, 360-degree views, and perfect localization which pose significant challenges when adapting these models to real-world settings. This work addresses these limitations by performing a simulation-to-real domain shift of a VLN approach that operates in continuous environments without requiring navigation graphs or panoramic views. The proposed system integrates vision-language models that align visual inputs and linguistic instructions within a shared embedding space, facilitating natural language-driven navigation. We employ a Cross-Modal Attention (CMA) based architecture trained on an existing dataset in a simulated environment and fine-tune it using real-world data collected from a custom-built Ackermann-steered robot equipped with a camera and a LiDAR sensor. By utilising linear photometric adjustments and fine-tuning on a limited number of episodes, our model successfully adapts to real-world environments, achieving effective navigation while running offline on dedicated hardware. Experimental results, evaluated using Success weighted by Path Length (SPL) and Normalized Dynamic Time Warping (nDTW) metrics, demonstrate the robustness and adaptability of our approach. Keywords: Vision-Language Navigation, Cross-Modal Attention, Natural Language Instructions, Sim-to-Real Transfer, Autonomous Navigation, Ackermann-steering.

cs.AI↗

arXiv2026

CL4D: Contrastive Language-4D Pretraining for Vision-Language Reasoning in Dynamic Scenes

4D understanding and reasoning is a fundamental capability for embodied AI agents operating in dynamic physical environments. However, existing vision encoders are largely limited to static 2D images or 3D point clouds without temporal modeling, or to 2D videos that lack accurate geometric depth reasoning. Consequently, current approaches fail to jointly capture spatial structure and motion evolution in dynamic scenes. We present CL4D, the first foundational 4D vision encoder that directly operates on dynamic point clouds, trained with a contrastive learning objective to align spatio-temporal geometric representations with natural language descriptions. By learning a shared embedding space between text and 4D scene dynamics, CL4D enables zero-shot motion-to-text and text-to-motion retrieval in dynamic environments and serves as a foundational 4D vision encoder for downstream 4D vision-language tasks. Building on this encoder, we introduce 4DVLM, a 4D vision-language model that conditions language generation on dynamic geometric representations. 4DVLM is the first VLM designed to operate directly on 4D point clouds without relying on 2D images, 2D videos, or static 3D point clouds. We train CL4D and subsequently 4DVLM on a newly constructed dataset termed DynAction4D capturing diverse human motions across varying object interactions and scene environments. Extensive experiments across multiple 4D human action benchmarks demonstrate that CL4D achieves state-of-the-art performance, with improvements of approximately ~16.75% over prior methods. Furthermore, 4DVLM outperforms frontier video VLMs such as Gemini and GPT-5 even when these models are provided with RGB video sequences corresponding to the same scenes represented as 4D point clouds for 4DVLM.

cs.CV↗

arXiv2026

Radar and Acoustic Sensor Fusion using a Transformer Encoder for Robust Drone Detection and Classification

The use of drones in a wide range of applications is steadily increasing. However, this has also raised critical security concerns such as unauthorized drone intrusions into restricted zones. Therefore, robust and accurate drone detection and classification mechanisms are required despite significant challenges due to small size of drones, low-altitude flight, and environmental noise. In this letter, we propose a multi-modal approach combining radar and acoustic sensing for detecting and classifying drones. We employ radar due to its long-range capabilities, and robustness to different weather conditions. We utilize raw acoustic signals without converting them to other domains such as spectrograms or Mel-frequency cepstral coefficients. This enables us to use fewer number of parameters compared to the stateof-the-art approaches. Furthermore, we explore the effectiveness of the transformer encoder architecture in fusing these sensors. Experimental results obtained in outdoor settings verify the superior performance of the proposed approach compared to the state-of-the-art methods.

eess.SP↗

arXiv2026

Domain-Agnostic Feature Modulation for Semi-Supervised Domain Generalization

Semi-supervised domain generalization (SSDG) leverages a small fraction of labeled data alongside unlabeled data to enhance model generalization. Most of the existing SSDG methods rely on pseudo-labeling (PL) for unlabeled data, often assuming access to domain labels-a privilege not always available. However, domain shifts introduce domain noise, leading to inconsistent PLs that degrade model performance. Methods derived from FixMatch suffer particularly from lower PL accuracy, reducing the effectiveness of unlabeled data. To address this, we tackle the more challenging domain-label agnostic SSDG, where domain labels for unlabeled data are not available during training. First, we propose a feature modulation strategy that enhances class-discriminative features while suppressing domain-specific information. This modulation shifts features toward Similar Average Representations-a modified version of class prototypes-that are robust across domains, encouraging the classifier to distinguish between closely related classes and feature extractor to form tightly clustered, domain-invariant representations. Second, to mitigate domain noise and improve pseudo-label accuracy, we introduce a loss-scaling function that dynamically lowers the fixed confidence threshold for pseudo-labels, optimizing the use of unlabeled data. With these key innovations, our approach achieves significant improvements on four major domain generalization benchmarks-even without domain labels. We will make the code available.

cs.CV↗

arXiv2026

VC-FeS: Viewpoint-Conditioned Feature Selection for Vehicle Re-identification in Thermal Vision

Identification of less-articulated objects using single-channel images, such as thermal images, is important in many applications, such as surveillance. However, in this domain, existing methods show poor performance due to high similarity among objects of the same category in the absence of color information (overlooking shape information) and de-emphasized texture information. Furthermore, variability in viewpoint adds more complexity as the features vary from side to side. We address these issues by constructing viewpoint-conditioned feature vectors and area-specific feature comparisons in separate feature spaces. These interventions enable leveraging the advancements of existing RGB-pre-trained ViT feature extractors while effectively adapting them to address the challenges specific to the thermal domain. We test our system with RGBNT100 (IR) vehicle dataset and a thermal maritime dataset acquired by us. Our results surpass the state-of-the-art methods by 19.7% and 12.8% for the above datasets in mAP scores, respectively. We also plan to make our thermal dataset available, the first of its kind for maritime vessel identification.

cs.CV↗

arXiv2026

DARB-Splatting: Generalizing Splatting with Decaying Anisotropic Radial Basis Functions

Splatting-based 3D reconstruction methods have gained popularity with the advent of 3D Gaussian Splatting, efficiently synthesizing high-quality novel views. These methods commonly resort to using exponential family functions, such as the Gaussian function, as reconstruction kernels due to their anisotropic nature, ease of projection, and differentiability in rasterization. However, the field remains restricted to variations within the exponential family, leaving generalized reconstruction kernels largely underexplored, partly due to the lack of easy integrability in 3D to 2D projections. In this light, we show that a class of decaying anisotropic radial basis functions (DARBFs), which are non-negative functions of the Mahalanobis distance, supports splatting by approximating the Gaussian function's closed-form integration advantage. With this fresh perspective, we demonstrate varying performances across selected DARB reconstruction kernels, achieving comparable training convergence and memory footprints, with on-par PSNR, SSIM, and LPIPS results.

cs.CV↗

arXiv2026

A-TPT: Angular Diversity Calibration Properties for Test-Time Prompt Tuning of Vision-Language Models

Test-time prompt tuning (TPT) has emerged as a promising technique for adapting large vision-language models (VLMs) to unseen tasks without relying on labeled data. However, the lack of dispersion between textual features can hurt calibration performance, which raises concerns about VLMs' reliability, trustworthiness, and safety. Current TPT approaches primarily focus on improving prompt calibration by either maximizing average textual feature dispersion or enforcing orthogonality constraints to encourage angular separation. However, these methods may not always have optimal angular separation between class-wise textual features, which implies overlooking the critical role of angular diversity. To address this, we propose A-TPT, a novel TPT framework that introduces angular diversity to encourage uniformity in the distribution of normalized textual features induced by corresponding learnable prompts. This uniformity is achieved by maximizing the minimum pairwise angular distance between features on the unit hypersphere. We show that our approach consistently surpasses state-of-the-art TPT methods in reducing the aggregate average calibration error while maintaining comparable accuracy through extensive experiments with various backbones on different datasets. Notably, our approach exhibits superior zero-shot calibration performance on natural distribution shifts and generalizes well to medical datasets. We provide extensive analyses, including theoretical aspects, to establish the grounding of A-TPT. These results highlight the potency of promoting angular diversity to achieve well-dispersed textual features, significantly improving VLM calibration during test-time adaptation. Our code will be made publicly available.

cs.CV↗

arXiv2026

SemAlign: Language Guided Semi-supervised Domain Generalization

Semi-supervised Domain Generalization (SSDG) addresses the challenge of generalizing to unseen target domains with limited labeled data. Existing SSDG methods highlight the importance of achieving high pseudo-labeling (PL) accuracy and preventing model overfitting as the main challenges in SSDG. In this light, we show that the SSDG literature's excessive focus on PL accuracy, without consideration for maximum data utilization during training, limits potential performance improvements. We propose a novel approach to the SSDG problem by aligning the intermediate features of our model with the semantically rich and generalized feature space of a Vision Language Model (VLM) in a way that promotes domain-invariance. The above approach is enhanced with effective image-level augmentation and output-level regularization strategies to improve data utilization and minimize overfitting. Extensive experimentation across four benchmarks against existing SSDG baselines suggests that our method achieves SOTA results both qualitatively and quantitatively. The code will be made publicly available.

cs.CV↗

arXiv2025

CrossJEPA: Cross-Modal Joint-Embedding Predictive Architecture for Efficient 3D Representation Learning from 2D Images

Image-to-point cross-modal learning has emerged to address the scarcity of large-scale 3D datasets in 3D representation learning. However, current methods that leverage 2D data often result in large, slow-to-train models, making them computationally expensive and difficult to deploy in resource-constrained environments. The architecture design of such models is therefore critical, determining their performance, memory footprint, and compute efficiency. The Joint-embedding Predictive Architecture (JEPA) has gained wide popularity in self-supervised learning for its simplicity and efficiency, but has been under-explored in cross-modal settings, partly due to the misconception that masking is intrinsic to JEPA. In this light, we propose CrossJEPA, a simple Cross-modal Joint Embedding Predictive Architecture that harnesses the knowledge of an image foundation model and trains a predictor to infer embeddings of specific rendered 2D views from corresponding 3D point clouds, thereby introducing a JEPA-style pretraining strategy beyond masking. By conditioning the predictor on cross-domain projection information, CrossJEPA purifies the supervision signal from semantics exclusive to the target domain. We further exploit the frozen teacher design with a one-time target embedding caching mechanism, yielding amortized efficiency. CrossJEPA achieves a new state-of-the-art in linear probing on the synthetic ModelNet40 (94.2%) and the real-world ScanObjectNN (88.3%) benchmarks, using only 14.1M pretraining parameters (8.5M in the point encoder), and about 6 pretraining hours on a standard single GPU. These results position CrossJEPA as a performant, memory-efficient, and fast-to-train framework for 3D representation learning via knowledge distillation. We analyze CrossJEPA intuitively, theoretically, and empirically, and extensively ablate our design choices. Code will be made available.

cs.CV↗

arXiv2025

SENCA-st: Integrating Spatial Transcriptomics and Histopathology with Cross Attention Shared Encoder for Region Identification in Cancer Pathology

Spatial transcriptomics is an emerging field that enables the identification of functional regions based on the spatial distribution of gene expression. Integrating this functional information present in transcriptomic data with structural data from histopathology images is an active research area with applications in identifying tumor substructures associated with cancer drug resistance. Current histopathology-spatial-transcriptomic region segmentation methods suffer due to either making spatial transcriptomics prominent by using histopathology features just to assist processing spatial transcriptomics data or using vanilla contrastive learning that make histopathology images prominent due to only promoting common features losing functional information. In both extremes, the model gets either lost in the noise of spatial transcriptomics or overly smoothed, losing essential information. Thus, we propose our novel architecture SENCA-st (Shared Encoder with Neighborhood Cross Attention) that preserves the features of both modalities. More importantly, it emphasizes regions that are structurally similar in histopathology but functionally different on spatial transcriptomics using cross-attention. We demonstrate the superior performance of our model that surpasses state-of-the-art methods in detecting tumor heterogeneity and tumor micro-environment regions, a clinically crucial aspect.

cs.CV↗

arXiv2025

Uncertainty Awareness Enables Efficient Labeling for Cancer Subtyping in Digital Pathology

Machine-learning-assisted cancer subtyping is a promising avenue in digital pathology. Cancer subtyping models, however, require careful training using expert annotations so that they can be inferred with a degree of known certainty (or uncertainty). To this end, we introduce the concept of uncertainty awareness into a self-supervised contrastive learning model. This is achieved by computing an evidence vector at every epoch, which assesses the model's confidence in its predictions. The derived uncertainty score is then utilized as a metric to selectively label the most crucial images that require further annotation, thus iteratively refining the training process. With just 1-10% of strategically selected annotations, we attain state-of-the-art performance in cancer subtyping on benchmark datasets. Our method not only strategically guides the annotation process to minimize the need for extensive labeled datasets, but also improves the precision and efficiency of classifications. This development is particularly beneficial in settings where the availability of labeled data is limited, offering a promising direction for future research and application in digital pathology.

cs.CV↗

arXiv2025

Test-Time Optimization for Domain Adaptive Open Vocabulary Segmentation

We present Seg-TTO, a novel framework for zero-shot, open-vocabulary semantic segmentation (OVSS), designed to excel in specialized domain tasks. While current open-vocabulary approaches show impressive performance on standard segmentation benchmarks under zero-shot settings, they fall short of supervised counterparts on highly domain-specific datasets. We focus on segmentation-specific test-time optimization to address this gap. Segmentation requires an understanding of multiple concepts within a single image while retaining the locality and spatial structure of representations. We propose a novel self-supervised objective adhering to these requirements and use it to align the model parameters with input images at test time. In the textual modality, we learn multiple embeddings for each category to capture diverse concepts within an image, while in the visual modality, we calculate pixel-level losses followed by embedding aggregation operations specific to preserving spatial structure. Our resulting framework termed Seg-TTO is a plug-and-play module. We integrate Seg-TTO with three state-of-the-art OVSS approaches and evaluate across 22 challenging OVSS tasks covering a range of specialized domains. Our Seg-TTO demonstrates clear performance improvements (up to 27% mIoU increase on some datasets) establishing new state-of-the-art. Our code and models will be released publicly.

cs.CV↗

arXiv2024

A Feature Generator for Few-Shot Learning

Few-shot learning (FSL) aims to enable models to recognize novel objects or classes with limited labelled data. Feature generators, which synthesize new data points to augment limited datasets, have emerged as a promising solution to this challenge. This paper investigates the effectiveness of feature generators in enhancing the embedding process for FSL tasks. To address the issue of inaccurate embeddings due to the scarcity of images per class, we introduce a feature generator that creates visual features from class-level textual descriptions. By training the generator with a combination of classifier loss, discriminator loss, and distance loss between the generated features and true class embeddings, we ensure the generation of accurate same-class features and enhance the overall feature representation. Our results show a significant improvement in accuracy over baseline methods, with our approach outperforming the baseline model by 10% in 1-shot and around 5% in 5-shot approaches. Additionally, both visual-only and visual + textual generators have also been tested in this paper. The code is publicly available at https://github.com/heethanjan/Feature-Generator-for-FSL.

cs.CV↗

arXiv2024

LiverUSRecon: Automatic 3D Reconstruction and Volumetry of the Liver with a Few Partial Ultrasound Scans

3D reconstruction of the liver for volumetry is important for qualitative analysis and disease diagnosis. Liver volumetry using ultrasound (US) scans, although advantageous due to less acquisition time and safety, is challenging due to the inherent noisiness in US scans, blurry boundaries, and partial liver visibility. We address these challenges by using the segmentation masks of a few incomplete sagittal-plane US scans of the liver in conjunction with a statistical shape model (SSM) built using a set of CT scans of the liver. We compute the shape parameters needed to warp this canonical SSM to fit the US scans through a parametric regression network. The resulting 3D liver reconstruction is accurate and leads to automatic liver volume calculation. We evaluate the accuracy of the estimated liver volumes with respect to CT segmentation volumes using RMSE. Our volume computation is statistically much closer to the volume estimated using CT scans than the volume computed using Childs' method by radiologists: p-value of 0.094 (>0.05) says that there is no significant difference between CT segmentation volumes and ours in contrast to Childs' method. We validate our method using investigations (ablation studies) on the US image resolution, the number of CT scans used for SSM, the number of principal components, and the number of input US scans. To the best of our knowledge, this is the first automatic liver volumetry system using a few incomplete US scans given a set of CT scans of livers for SSM.

eess.IV↗