arXiv subjects

Abhijit Das

Publications and source records attributed to Abhijit Das.

At least 19 recordsLinked to original sources

arXiv2026

Counterfactual Anatomy-guided Spatial-Temporal Decoding for Annotation-Free Hallucination Mitigation in Medical VLMs

Medical vision-language models (Med-VLMs) have demonstrated strong performance on medical visual question answering, yet they remain prone to hallucination, generating clinically unsupported statements that are insufficiently grounded in image evidence. Mitigation methods applied during decoding offer a practical solution, but they typically lack anatomical awareness or rely heavily on ground truth annotations, which limits their applicability. We propose Counterfactual Anatomy-guided Spatial-Temporal decoding (CAST), a framework that operates entirely during inference and requires no manual annotations for anatomically grounded hallucination mitigation. CAST automatically discovers anatomical regions relevant to the given query through broad medical segmentation. It then selects a compact, causally informative area using counterfactual intervention based on the drop in answer likelihood under occlusion. Guided by this chosen region, CAST performs a unified contrastive decoding process, combining classifier-free guidance to correct spatial attention with stepwise temporal contrast to regulate generation dynamics. Experiments on the SLAKE and MIMIC-CXR datasets across three Med-VLMs demonstrate that CAST consistently outperforms strong baselines and surpasses decoding strategies reliant on ground truth. Our results indicate that compact, automatically selected regions provide highly effective contrastive guidance without expert annotations, offering a practical and generalizable solution for improving spatial grounding and reducing hallucinations. Code is available at https://github.com/csyifan/CAST.

cs.CV↗

arXiv2026

Graph-of-Differences: Anatomy-Structured Difference Alignment for Medical Image Re-Identification

Medical image re-identification (MedReID) enables longitudinal patient linkage but remains vulnerable to shortcut learning and often produces decisions that clinicians cannot audit against named anatomy. We propose Graph-of-Differences (GoD), which grounds identity comparisons in explicit anatomical structure. Each image is represented as an anatomy graph whose nodes correspond to named anatomical regions; given an image pair, soft node correspondence is established, and differences are computed over matched anatomy. A graph-level difference alignment objective ties these anatomy-matched differences to the global backbone difference, ensuring the retrieval signal is anchored in homologous structures rather than arbitrary spatial tokens. Explanations are defined over named graph nodes and quantitatively audited via node insertion/deletion tests, replacing unstable pixel heatmaps with verifiable structure-level evidence. On internal benchmarks, GoD improves Rank-1 by +7.1 pp on fundus and +3.1 pp on CXR over a strong frozen-backbone baseline, with further gains on zero-shot external transfers confirming that anatomy grounding improves both accuracy and generalization. Code is available at https://github.com/GenMI-Lab/GoD.git.

cs.CV↗

arXiv2026

EnTrust: Modeling Inter-Modal Conflict for Trustworthy Multimodal Medical Image Analysis

Multimodal medical imaging fuses complementary anatomical and functional information, yet modalities frequently disagree in pathologically heterogeneous regions. Current segmentation models handle this in one of two inadequate ways: deterministic fusion that averages away disagreement, or post-hoc uncertainty estimation decoupled from the fusion process that produces it. Both obscure the clinically critical question: why is this prediction unreliable? We present EnTrust, a framework that treats inter-modal conflict as the primary source of predictive uncertainty. Our EnFuse module decomposes multimodal features into three disentangled components: shared anatomical consensus (F_c), modality-specific cues (F_{u,m}), and spatially localized conflict signals (F_{cf}), with independence enforced via a cross-covariance objective. This structured decomposition conditions SegDiff, a diffusion-based generative segmentation model whose sampled hypotheses diverge specifically in regions of modal disagreement. TrustMap then translates this hypothesis divergence into calibrated, pixel-wise uncertainty using ensemble entropy, conflict-guided perturbation probing, and a learned calibration head, enabling clinicians to understand not only where predictions are uncertain, but why. Across four benchmarks spanning brain, cardiac, lesion, and oncology domains, EnTrust achieves state-of-the-art segmentation accuracy while reducing calibration error by 40% compared to the strongest baseline. Notably, it outperforms 5x deep ensembles using a single model at roughly half the memory footprint. Code and checkpoints are available at https://github.com/GenMI-Lab/EnTrust.git.

cs.CV↗

arXiv2026

PROTON: Prototype-Based Test-Time Online OOD Detection for Medical VLMs

Medical vision-language models (VLMs) enable zero-shot clinical image classification, yet reliably detecting out-of-distribution (OOD) inputs at deployment remains an open problem. No static scoring method works across all shift types: Maximum Concept Matching (MCM) on FLAIR achieves 76.4% AUROC for far-OOD but only 42.4% for covariate shifts such as ultra-wide-field fundus images, effectively random. We trace this to a structural mismatch: covariate-shifted inputs are indistinguishable from in-distribution samples in softmax space, yet occupy distinct regions in the VLM embedding space. To exploit this untapped signal, we propose PROTON (PROtotype-based Test-time ONline OOD detection), a lightweight post-hoc module that maintains an online prototype bank from high-confidence test predictions and adaptively fuses prototype distance with MCM scoring via stream-level variance statistics, requiring no model modification, training data, or prompt engineering. On the ophthalmology benchmark FLAIR + FIVES, PROTON improves MCM by +23.9 AUROC on covariate shift, +8.8 on semantic shift, and +8.1 on far-OOD, making it the only zero-shot method to improve all three without hierarchical prompts or labeled data. Code is available at https://github.com/GenMI-Lab/PROTON, and the project page is available at https://genmi-lab.github.io/PROTON.

cs.CV↗

arXiv2026

Weight-Decay Turns Transformer Loss Landscapes Villani: Functional-Analytic Foundations for Optimization and Generalization

Weight decay is widely used as a regularizer in large language models, yet its precise role in shaping Transformer loss landscapes remains theoretically underexplored. This paper provides the first rigorous functional-analytic characterization of the standard Transformer objective--cross-entropy loss with $L^2$ regularization--by proving it satisfies Villani's criteria for coercive energy functions. Specifically, we show that the regularized loss $\mathcal{F}$ is infinitely differentiable, grows at least quadratically, has Gaussian-integrable tails, and satisfies the differential growth condition $-\Delta\mathcal{F} + \tfrac{1}{s}\|\nabla\mathcal{F}\|^{2} \to \infty$ as $\|\theta\| \to \infty$ for all $s>0$. From this structure, we derive explicit log-Sobolev and Poincar\'e constants $C_{\mathrm{LS}} \leq \lambda^{-1} + d/\lambda^{2}$, linking the regularization strength $\lambda$ and model dimension $d$ to finite-time convergence guarantees for noisy stochastic gradient descent and PAC-Bayesian generalization bounds that tighten with increasing $\lambda$. To validate our theory, we introduce a scalable Villani diagnostic $\Psi_s(\theta) = -\Delta \mathcal{F} + s^{-1}\|\nabla \mathcal{F}\|^2$ and estimate it efficiently using Hutchinson trace probes in models with over 100M parameters. Experiments on GPT-Neo-125M across Penn Treebank and WikiText-103 confirm the predicted quadratic growth of $\Psi_s$, spectral inflation of the Hessian, and exponential convergence behavior consistent with our log-Sobolev analysis. These results demonstrate that weight decay not only improves generalization empirically but also establishes the mathematical conditions required for fast Langevin mixing and theoretically grounded curvature-aware optimization in deep learning.

cs.LG↗

arXiv2026

B-MoE: A Body-Part-Aware Mixture-of-Experts "All Parts Matter" Approach to Micro-Action Recognition

Micro-actions, fleeting and low-amplitude motions, such as glances, nods, or minor posture shifts, carry rich social meaning but remain difficult for current action recognition models to recognize due to their subtlety, short duration, and high inter-class ambiguity. In this paper, we introduce B-MoE, a Body-part-aware Mixture-of-Experts framework designed to explicitly model the structured nature of human motion. In B-MoE, each expert specializes in a distinct body region (head, body, upper limbs, lower limbs), and is based on the lightweight Macro-Micro Motion Encoder (M3E) that captures long-range contextual structure and fine-grained local motion. A cross-attention routing mechanism learns inter-region relationships and dynamically selects the most informative regions for each micro-action. B-MoE uses a dual-stream encoder that fuses these region-specific semantic cues with global motion features to jointly capture spatially localized cues and temporally subtle variations that characterize micro-actions. Experiments on three challenging benchmarks (MA-52, SocialGesture, and MPII-GroupInteraction) show consistent state-of-theart gains, with improvements in ambiguous, underrepresented, and low amplitude classes.

cs.CV↗

arXiv2026

A Backbone Benchmarking Study on Self-supervised Learning as a Auxiliary Task with Texture-based Local Descriptors for Face Analysis

In this work, we benchmark with different backbones and study their impact for self-supervised learning (SSL) as an auxiliary task to blend texture-based local descriptors into feature modelling for efficient face analysis. It is established in previous work that combining a primary task and a self-supervised auxiliary task enables more robust and discriminative representation learning. We employed different shallow to deep backbones for the SSL task of Masked Auto-Encoder (MAE) as an auxiliary objective to reconstruct texture features such as local patterns alongside the primary task in local pattern SSAT (L-SSAT), ensuring robust and unbiased face analysis. To expand the benchmark, we conducted a comprehensive comparative analysis across multiple model configurations within the proposed framework. To this end, we address the three research questions: "What is the role of the backbone in performance L-SSAT?", "What type of backbone is effective for different face analysis tasks?", and "Is there any generalized backbone for effective face analysis with L-SSAT?". Towards answering these questions, we provide a detailed study and experiments. The performance evaluation demonstrates that the backbone for the proposed method is highly dependent on the downstream task, achieving average accuracies of 0.94 on FaceForensics++, 0.87 on CelebA, and 0.88 on AffectNet. For consistency of feature representation quality and generalisation capability across various face analysis paradigms, including face attribute prediction, emotion classification, and deepfake detection, there is no unified backbone.

cs.CV↗

arXiv2026

Narrating For You: Prompt-guided Audio-visual Narrating Face Generation Employing Multi-entangled Latent Space

We present a novel approach for generating realistic speaking and talking faces by synthesizing a person's voice and facial movements from a static image, a voice profile, and a target text. The model encodes the prompt/driving text, the driving image, and the voice profile of an individual and then combines them to pass them to the multi-entangled latent space to foster key-value pairs and queries for the audio and video modality generation pipeline. The multi-entangled latent space is responsible for establishing the spatiotemporal person-specific features between the modalities. Further, entangled features are passed to the respective decoder of each modality for output audio and video generation.

cs.CV↗

arXiv2026

DenVisCoM: Dense Vision Correspondence Mamba for Efficient and Real-time Optical Flow and Stereo Estimation

In this work, we propose a novel Mamba block DenVisCoM, as well as a novel hybrid architecture specifically tailored for accurate and real-time estimation of optical flow and disparity estimation. Given that such multi-view geometry and motion tasks are fundamentally related, we propose a unified architecture to tackle them jointly. Specifically, the proposed hybrid architecture is based on DenVisCoM and a Transformer-based attention block that efficiently addresses real-time inference, memory footprint, and accuracy at the same time for joint estimation of motion and 3D dense perception tasks. We extensively analyze the benchmark trade-off of accuracy and real-time processing on a large number of datasets. Our experimental results and related analysis suggest that our proposed model can accurately estimate optical flow and disparity estimation in real time. All models and associated code are available at https://github.com/vimstereo/DenVisCoM.

cs.CV↗

arXiv2026

Continual-learning for Modelling Low-Resource Languages from Large Language Models

Modelling a language model for a multi-lingual scenario includes several potential challenges, among which catastrophic forgetting is the major challenge. For example, small language models (SLM) built for low-resource languages by adapting large language models (LLMs) pose the challenge of catastrophic forgetting. This work proposes to employ a continual learning strategy using parts-of-speech (POS)-based code-switching along with a replay adapter strategy to mitigate the identified gap of catastrophic forgetting while training SLM from LLM. Experiments conducted on vision language tasks such as visual question answering and language modelling task exhibits the success of the proposed architecture.

cs.CL↗

arXiv2026

Investigating the Viability of Employing Multi-modal Large Language Models in the Context of Audio Deepfake Detection

While Vision-Language Models (VLMs) and Multimodal Large Language Models (MLLMs) have shown strong generalisation in detecting image and video deepfakes, their use for audio deepfake detection remains largely unexplored. In this work, we aim to explore the potential of MLLMs for audio deepfake detection. Combining audio inputs with a range of text prompts as queries to find out the viability of MLLMs to learn robust representations across modalities for audio deepfake detection. Therefore, we attempt to explore text-aware and context-rich, question-answer based prompts with binary decisions. We hypothesise that such a feature-guided reasoning will help in facilitating deeper multimodal understanding and enable robust feature learning for audio deepfake detection. We evaluate the performance of two MLLMs, Qwen2-Audio-7B-Instruct and SALMONN, in two evaluation modes: (a) zero-shot and (b) fine-tuned. Our experiments demonstrate that combining audio with a multi-prompt approach could be a viable way forward for audio deepfake detection. Our experiments show that the models perform poorly without task-specific training and struggle to generalise to out-of-domain data. However, they achieve good performance on in-domain data with minimal supervision, indicating promising potential for audio deepfake detection.

cs.SD↗

arXiv2026

Fusion-SSAT: Unleashing the Potential of Self-supervised Auxiliary Task by Feature Fusion for Generalized Deepfake Detection

In this work, we attempted to unleash the potential of self-supervised learning as an auxiliary task that can optimise the primary task of generalised deepfake detection. To explore this, we examined different combinations of the training schemes for these tasks that can be most effective. Our findings reveal that fusing the feature representation from self-supervised auxiliary tasks is a powerful feature representation for the problem at hand. Such a representation can leverage the ultimate potential and bring in a unique representation of both the self-supervised and primary tasks, achieving better performance for the primary task. We experimented on a large set of datasets, which includes DF40, FaceForensics++, Celeb-DF, DFD, FaceShifter, UADFV, and our results showed better generalizability on cross-dataset evaluation when compared with current state-of-the-art detectors.

cs.CV↗

arXiv2025

Do You See What I Say? Generalizable Deepfake Detection based on Visual Speech Recognition

Deepfake generation has witnessed remarkable progress, contributing to highly realistic generated images, videos, and audio. While technically intriguing, such progress has raised serious concerns related to the misuse of manipulated media. To mitigate such misuse, robust and reliable deepfake detection is urgently needed. Towards this, we propose a novel network FauxNet, which is based on pre-trained Visual Speech Recognition (VSR) features. By extracting temporal VSR features from videos, we identify and segregate real videos from manipulated ones. The holy grail in this context has to do with zero-shot detection, i.e., generalizable detection, which we focus on in this work. FauxNet consistently outperforms the state-of-the-art in this setting. In addition, FauxNet is able to attribute - distinguish between generation techniques from which the videos stem. Finally, we propose new datasets, referred to as Authentica-Vox and Authentica-HDTF, comprising about 38,000 real and fake videos in total, the latter created with six recent deepfake generation techniques. We provide extensive analysis and results on the Authentica datasets and FaceForensics++, demonstrating the superiority of FauxNet. The Authentica datasets will be made publicly available.

cs.CV↗

arXiv2025

Beyond Real versus Fake Towards Intent-Aware Video Analysis

The rapid advancement of generative models has led to increasingly realistic deepfake videos, posing significant societal and security risks. While existing detection methods focus on distinguishing real from fake videos, such approaches fail to address a fundamental question: What is the intent behind a manipulated video? Towards addressing this question, we introduce IntentHQ: a new benchmark for human-centered intent analysis, shifting the paradigm from authenticity verification to contextual understanding of videos. IntentHQ consists of 5168 videos that have been meticulously collected and annotated with 23 fine-grained intent-categories, including "Financial fraud", "Indirect marketing", "Political propaganda", as well as "Fear mongering". We perform intent recognition with supervised and self-supervised multi-modality models that integrate spatio-temporal video features, audio processing, and text analysis to infer underlying motivations and goals behind videos. Our proposed model is streamlined to differentiate between a wide range of intent-categories.

cs.CV↗

arXiv2025

SCLARO: A Dataset for Grounded Scenario-Level Scene Understanding and ScenarioCLIP for Benchmarking

In the paradigm of computer vision-based precise real-world scene understanding, joint reasoning in terms of contextual understanding about the objects present in a scene, their inter-object relations, and the action being performed is an essential prerequisite. However, prior works have not addressed all three jointly, and no large-scale dataset provides grounded annotations at all three levels across diverse visual scenarios. Hence, this work introduces the SCLARO (Scene-Contextual Localisation of Actions, Relations & Objects) dataset, consisting of 615,805 images spanning indoor, outdoor, and driving scenarios, annotated with global action captions, object bounding boxes, and relation triplets that supply structured scene context beyond a free-text caption. To benchmark the dataset, we propose ScenarioCLIP, a tri-level reference model that jointly encodes global scene context, objects, and inter-object relations using disentangled encoders and EMA-based knowledge distillation. We benchmark across a comprehensive suite of tasks on the SCLARO Dataset, namely zero-shot retrieval, linear probe, object detection, predicate classification, scene-graph classification, and out-of-domain generalisation. ScenarioCLIP's disentangled encoders improve over the previous works, such as PyramidCLIP's shared encoder, most notably at the object and relation levels and on out-of-domain generalisation. Code for the data generation pipeline and ScenarioCLIP is available at https://github.com/scenario-clip/SCLARO-ScenarioCLIP

cs.CV↗

arXiv2025

DensePercept-NCSSD: Vision Mamba towards Real-time Dense Visual Perception with Non-Causal State Space Duality

In this work, we propose an accurate and real-time optical flow and disparity estimation model by fusing pairwise input images in the proposed non-causal selective state space for dense perception tasks. We propose a non-causal Mamba block-based model that is fast and efficient and aptly manages the constraints present in a real-time applications. Our proposed model reduces inference times while maintaining high accuracy and low GPU usage for optical flow and disparity map generation. The results and analysis, and validation in real-life scenario justify that our proposed model can be used for unified real-time and accurate 3D dense perception estimation tasks. The code, along with the models, can be found at https://github.com/vimstereo/DensePerceptNCSSD

cs.CV↗

arXiv2025

Towards Obstacle-Avoiding Control of Planar Snake Robots Exploring Neuro-Evolution of Augmenting Topologies

This work aims to develop a resource-efficient solution for obstacle-avoiding tracking control of a planar snake robot in a densely cluttered environment with obstacles. Particularly, Neuro-Evolution of Augmenting Topologies (NEAT) has been employed to generate dynamic gait parameters for the serpenoid gait function, which is implemented on the joint angles of the snake robot, thus controlling the robot on a desired dynamic path. NEAT is a single neural-network based evolutionary algorithm that is known to work extremely well when the input layer is of significantly higher dimension and the output layer is of a smaller size. For the planar snake robot, the input layer consists of the joint angles, link positions, head link position as well as obstacle positions in the vicinity. However, the output layer consists of only the frequency and offset angle of the serpenoid gait that control the speed and heading of the robot, respectively. Obstacle data from a LiDAR and the robot data from various sensors, along with the location of the end goal and time, are employed to parametrize a reward function that is maximized over iterations by selective propagation of superior neural networks. The implementation and experimental results showcase that the proposed approach is computationally efficient, especially for large environments with many obstacles. The proposed framework has been verified through a physics engine simulation study on PyBullet. The approach shows superior results to existing state-of-the-art methodologies and comparable results to the very recent CBRL approach with significantly lower computational overhead. The video of the simulation can be found here: https://sites.google.com/view/neatsnakerobot

cs.RO↗

arXiv2025

A Survey on Improving Human Robot Collaboration through Vision-and-Language Navigation

Vision-and-Language Navigation (VLN) is a multi-modal, cooperative task requiring agents to interpret human instructions, navigate 3D environments, and communicate effectively under ambiguity. This paper presents a comprehensive review of recent VLN advancements in robotics and outlines promising directions to improve multi-robot coordination. Despite progress, current models struggle with bidirectional communication, ambiguity resolution, and collaborative decision-making in the multi-agent systems. We review approximately 200 relevant articles to provide an in-depth understanding of the current landscape. Through this survey, we aim to provide a thorough resource that inspires further research at the intersection of VLN and robotics. We advocate that the future VLN systems should support proactive clarification, real-time feedback, and contextual reasoning through advanced natural language understanding (NLU) techniques. Additionally, decentralized decision-making frameworks with dynamic role assignment are essential for scalable, efficient multi-robot collaboration. These innovations can significantly enhance human-robot interaction (HRI) and enable real-world deployment in domains such as healthcare, logistics, and disaster response.

cs.RO↗