arXiv subjects

Zeeshan Hayder

Publications and source records attributed to Zeeshan Hayder.

At least 19 recordsLinked to original sources

arXiv2026

Probing Diffusion Denoising Dynamics for Contrastive Representation Learning

Text-to-image diffusion models exhibit unprecedented generative capability and contain rich intermediate representations that can be useful for discriminative vision tasks. Motivated by this observation, we study a focused question: how can the denoising dynamics of a pretrained diffusion model be adapted to support discriminative representation learning while preserving its generative behavior under parameter-efficient updates? We present D$^3$CL as an investigation of this question. Our key observation is that noisy latents at different diffusion timesteps can be interpreted as stochastic views of the same underlying image, enabling a contrastive objective to be coupled with the standard denoising reconstruction loss. This formulation provides a simple way to probe the interaction between generative denoising and discriminative representation learning without training from scratch. To keep the adaptation lightweight, we apply LoRA updates to a pretrained Stable Diffusion backbone while freezing the original model parameters. D$^3$CL provides strong empirical evidence that reconstruction and noise-level contrastive objectives can be complementary: on ImageNet-1K, it obtains 80.1% linear-probing accuracy and an FID of 5.56 for $256 \times 256$ unconditional generation. Additional ablations on the design space suggest that the usefulness of diffusion features depends on where and how denoising states are sampled. These results establish D$^3$CL as a parameter-efficient adaptation framework for pretrained diffusion models, showing that noise-level contrastive learning can structure denoising representations for discriminative tasks while maintaining generative performance.

cs.CV↗

arXiv2026

BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generation

Recent diffusion and flow matching models have demonstrated strong capabilities in image generation and editing by progressively removing noise through iterative sampling. While this enables flexible inversion for semantic-preserving edits, few-step sampling regimes suffer from poor forward process approximation, leading to degraded editing quality. Existing few-step inversion methods often rely on pretrained generators and auxiliary modules, limiting scalability and generalization across different architectures. To address these limitations, we propose BiFM (Bidirectional Flow Matching), a unified framework that jointly learns generation and inversion within a single model. BiFM directly estimates average velocity fields in both ``image $\to$ noise" and ``noise $\to$ image" directions, constrained by a shared instantaneous velocity field derived from either predefined schedules or pretrained multi-step diffusion models. Additionally, BiFM introduces a novel training strategy using continuous time-interval supervision, stabilized by a bidirectional consistency objective and a lightweight time-interval embedding. This bidirectional formulation also enables one-step inversion and can integrate seamlessly into popular diffusion and flow matching backbones. Across diverse image editing and generation tasks, BiFM consistently outperforms existing few-step approaches, achieving superior performance and editability.

cs.CV↗

arXiv2026

Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation

Generating realistic 3D Human-Human Interaction (HHI) requires coherent modeling of the physical plausibility of the agents and their interaction semantics. Existing methods compress all motion information into a single latent representation, limiting their ability to capture fine-grained actions and inter-agent interactions. This often leads to semantic misalignment and physically implausible artifacts, such as penetration or missed contact. We propose Disentangled Hierarchical Variational Autoencoder (DHVAE) based latent diffusion for structured and controllable HHI generation. DHVAE explicitly disentangles the global interaction context and individual motion patterns into a decoupled latent structure by employing a CoTransformer module. To mitigate implausible and physically inconsistent contacts in HHI, we incorporate contrastive learning constraints with our DHVAE to promote a more discriminative and physically plausible latent interaction space. For high-fidelity interaction synthesis, DHVAE employs a DDIM-based diffusion denoising process in the hierarchical latent space, enhanced by a skip-connected AdaLN-Transformer denoiser. Extensive evaluations show that DHVAE achieves superior motion fidelity, text alignment, and physical plausibility with greater computational efficiency.

cs.CV↗

arXiv2025

ARMFlow: AutoRegressive MeanFlow for Online 3D Human Reaction Generation

3D human reaction generation faces three main challenges:(1) high motion fidelity, (2) real-time inference, and (3) autoregressive adaptability for online scenarios. Existing methods fail to meet all three simultaneously. We propose ARMFlow, a MeanFlow-based autoregressive framework that models temporal dependencies between actor and reactor motions. It consists of a causal context encoder and an MLP-based velocity predictor. We introduce Bootstrap Contextual Encoding (BSCE) in training, encoding generated history instead of the ground-truth ones, to alleviate error accumulation in autoregressive generation. We further introduce the offline variant ReMFlow, achieving state-of-the-art performance with the fastest inference among offline methods. Our ARMFlow addresses key limitations of online settings by: (1) enhancing semantic alignment via a global contextual encoder; (2) achieving high accuracy and low latency in a single-step inference; and (3) reducing accumulated errors through BSCE. Our single-step online generation surpasses existing online methods on InterHuman and InterX by about 30% in FID, while matching offline state-of-the-art performance despite using only partial sequence conditions.

cs.CV↗

arXiv2025

Quality-Driven and Diversity-Aware Sample Expansion for Robust Marine Obstacle Segmentation

Marine obstacle detection demands robust segmentation under challenging conditions, such as sun glitter, fog, and rapidly changing wave patterns. These factors degrade image quality, while the scarcity and structural repetition of marine datasets limit the diversity of available training data. Although mask-conditioned diffusion models can synthesize layout-aligned samples, they often produce low-diversity outputs when conditioned on low-entropy masks and prompts, limiting their utility for improving robustness. In this paper, we propose a quality-driven and diversity-aware sample expansion pipeline that generates training data entirely at inference time, without retraining the diffusion model. The framework combines two key components:(i) a class-aware style bank that constructs high-entropy, semantically grounded prompts, and (ii) an adaptive annealing sampler that perturbs early conditioning, while a COD-guided proportional controller regulates this perturbation to boost diversity without compromising layout fidelity. Across marine obstacle benchmarks, augmenting training data with these controlled synthetic samples consistently improves segmentation performance across multiple backbones and increases visual variation in rare and texture-sensitive classes.

cs.CV↗

arXiv2025

PSMamba: Progressive Self-supervised Vision Mamba for Plant Disease Recognition

Self-supervised Learning (SSL) has become a powerful paradigm for representation learning without manual annotations. However, most existing frameworks focus on global alignment and struggle to capture the hierarchical, multi-scale lesion patterns characteristic of plant disease imagery. To address this gap, we propose PSMamba, a progressive self-supervised framework that integrates the efficient sequence modelling of Vision Mamba (VM) with a dual-student hierarchical distillation strategy. Unlike conventional single teacher-student designs, PSMamba employs a shared global teacher and two specialised students: one processes mid-scale views to capture lesion distributions and vein structures, while the other focuses on local views to capture fine-grained cues such as texture irregularities and early-stage lesions. This multi-granular supervision facilitates the joint learning of contextual and detailed representations, with consistency losses ensuring coherent cross-scale alignment. Experiments on three benchmark datasets show that PSMamba consistently outperforms state-of-the-art SSL methods, delivering superior accuracy and robustness in both domain-shifted and fine-grained scenarios.

cs.CV↗

arXiv2025

StateSpace-SSL: Linear-Time Self-supervised Learning for Plant Disease Detection

Self-supervised learning (SSL) is attractive for plant disease detection as it can exploit large collections of unlabeled leaf images, yet most existing SSL methods are built on CNNs or vision transformers that are poorly matched to agricultural imagery. CNN-based SSL struggles to capture disease patterns that evolve continuously along leaf structures, while transformer-based SSL introduces quadratic attention cost from high-resolution patches. To address these limitations, we propose StateSpace-SSL, a linear-time SSL framework that employs a Vision Mamba state-space encoder to model long-range lesion continuity through directional scanning across the leaf surface. A prototype-driven teacher-student objective aligns representations across multiple views, encouraging stable and lesion-aware features from labelled data. Experiments on three publicly available plant disease datasets show that StateSpace-SSL consistently outperforms the CNN- and transformer-based SSL baselines in various evaluation metrics. Qualitative analyses further confirm that it learns compact, lesion-focused feature maps, highlighting the advantage of linear state-space modelling for self-supervised plant disease representation learning.

cs.CV↗

arXiv2025

EMUSE: Evolutionary Map of the Universe Search Engine

We present EMUSE (Evolutionary Map of the Universe Search Engine), a tool designed for searching specific radio sources within the extensive datasets of the EMU (Evolutionary Map of the Universe) survey, with potential applications to other Big Data challenges in astronomy. Built on a multimodal approach to radio source classification and retrieval, EMUSE fine-tunes the OpenCLIP model on curated radio galaxy datasets. Leveraging the power of foundation models, our work integrates visual and textual embeddings to enable efficient and flexible searches within large radio astronomical datasets. We fine-tune OpenCLIP using a dataset of 2,900 radio galaxies, encompassing various morphological classes, including FR-I, FR-II, FR-x, R-type, and other rare and peculiar sources. The model is optimized using adapter-based fine-tuning, ensuring computational efficiency while capturing the unique characteristics of radio sources. The fine-tuned model is then deployed in EMUSE, allowing for seamless image- and text-based queries over the EMU survey dataset. Our results demonstrate the model's effectiveness in retrieving and classifying radio sources, particularly in recognizing distinct morphological features. However, challenges remain in identifying rare or previously unseen radio sources, highlighting the need for expanded datasets and continuous refinement. This study showcases the potential of multimodal machine learning in radio astronomy, paving the way for more scalable and accurate search tools in the field. The search engine is accessible at https://askap-emuse.streamlit.app/ and can be used locally by cloning the repository at https://github.com/Nikhel1/EMUSE.

astro-ph.GA↗

arXiv2025

Discovery of Odd Radio Circles and Other Peculiars in the First Year of the EMU Survey using Object Detection

We present a systematic search for Odd Radio Circles (ORCs) and other unusual radio morphologies using data from the first year of the EMU (Evolutionary Map of the Universe) survey. ORCs are rare, enigmatic objects characterized by edge-brightened rings of radio emission, often found in association with distant galaxies. To identify these objects, we employ a hybrid methodology combining supervised object detection techniques and visual inspection of radio source candidates. This approach leads to the discovery of five new ORCs and two additional candidate ORCs, expanding the known population of these objects. In addition to ORCs, we also identify 55 Galaxies with Large-scale Ambient Radio Emission (GLAREs), which feature irregular, rectangular, or circular shapes of diffuse radio emission mostly surrounding central host galaxies. These GLAREs may represent different evolutionary stages of ORCs, and studying them could offer valuable insights into their evolutionary processes. We also highlight a subset of Starburst Radio Ring Galaxies (SRRGs), which are star-forming galaxies exhibiting edge-brightened radio rings surrounding their central star-forming regions. We emphasize the importance of multi-wavelength follow-up observations to better understand the physical properties, host galaxy characteristics, and evolutionary pathways of these radio sources.

astro-ph.GA↗

arXiv2025

ConMamba: Contrastive Vision Mamba for Plant Disease Detection

Plant Disease Detection (PDD) is a key aspect of precision agriculture. However, existing deep learning methods often rely on extensively annotated datasets, which are time-consuming and costly to generate. Self-supervised Learning (SSL) offers a promising alternative by exploiting the abundance of unlabeled data. However, most existing SSL approaches suffer from high computational costs due to convolutional neural networks or transformer-based architectures. Additionally, they struggle to capture long-range dependencies in visual representation and rely on static loss functions that fail to align local and global features effectively. To address these challenges, we propose ConMamba, a novel SSL framework specially designed for PDD. ConMamba integrates the Vision Mamba Encoder (VME), which employs a bidirectional State Space Model (SSM) to capture long-range dependencies efficiently. Furthermore, we introduce a dual-level contrastive loss with dynamic weight adjustment to optimize local-global feature alignment. Experimental results on three benchmark datasets demonstrate that ConMamba significantly outperforms state-of-the-art methods across multiple evaluation metrics. This provides an efficient and robust solution for PDD.

cs.CV↗

arXiv2025

UniHM: Universal Human Motion Generation with Object Interactions in Indoor Scenes

Human motion synthesis in complex scenes presents a fundamental challenge, extending beyond conventional Text-to-Motion tasks by requiring the integration of diverse modalities such as static environments, movable objects, natural language prompts, and spatial waypoints. Existing language-conditioned motion models often struggle with scene-aware motion generation due to limitations in motion tokenization, which leads to information loss and fails to capture the continuous, context-dependent nature of 3D human movement. To address these issues, we propose UniHM, a unified motion language model that leverages diffusion-based generation for synthesizing scene-aware human motion. UniHM is the first framework to support both Text-to-Motion and Text-to-Human-Object Interaction (HOI) in complex 3D scenes. Our approach introduces three key contributions: (1) a mixed-motion representation that fuses continuous 6DoF motion with discrete local motion tokens to improve motion realism; (2) a novel Look-Up-Free Quantization VAE (LFQ-VAE) that surpasses traditional VQ-VAEs in both reconstruction accuracy and generative performance; and (3) an enriched version of the Lingo dataset augmented with HumanML3D annotations, providing stronger supervision for scene-specific motion learning. Experimental results demonstrate that UniHM achieves comparative performance on the OMOMO benchmark for text-to-HOI synthesis and yields competitive results on HumanML3D for general text-conditioned motion generation.

cs.GR↗

arXiv2025

MoKD: Multi-Task Optimization for Knowledge Distillation

Compact models can be effectively trained through Knowledge Distillation (KD), a technique that transfers knowledge from larger, high-performing teacher models. Two key challenges in Knowledge Distillation (KD) are: 1) balancing learning from the teacher's guidance and the task objective, and 2) handling the disparity in knowledge representation between teacher and student models. To address these, we propose Multi-Task Optimization for Knowledge Distillation (MoKD). MoKD tackles two main gradient issues: a) Gradient Conflicts, where task-specific and distillation gradients are misaligned, and b) Gradient Dominance, where one objective's gradient dominates, causing imbalance. MoKD reformulates KD as a multi-objective optimization problem, enabling better balance between objectives. Additionally, it introduces a subspace learning framework to project feature representations into a high-dimensional space, improving knowledge transfer. Our MoKD is demonstrated to outperform existing methods through extensive experiments on image classification using the ImageNet-1K dataset and object detection using the COCO dataset, achieving state-of-the-art performance with greater efficiency. To the best of our knowledge, MoKD models also achieve state-of-the-art performance compared to models trained from scratch.

cs.CV↗

arXiv2025

Auto-Regressive Diffusion for Generating 3D Human-Object Interactions

Text-driven Human-Object Interaction (Text-to-HOI) generation is an emerging field with applications in animation, video games, virtual reality, and robotics. A key challenge in HOI generation is maintaining interaction consistency in long sequences. Existing Text-to-Motion-based approaches, such as discrete motion tokenization, cannot be directly applied to HOI generation due to limited data in this domain and the complexity of the modality. To address the problem of interaction consistency in long sequences, we propose an autoregressive diffusion model (ARDHOI) that predicts the next continuous token. Specifically, we introduce a Contrastive Variational Autoencoder (cVAE) to learn a physically plausible space of continuous HOI tokens, thereby ensuring that generated human-object motions are realistic and natural. For generating sequences autoregressively, we develop a Mamba-based context encoder to capture and maintain consistent sequential actions. Additionally, we implement an MLP-based denoiser to generate the subsequent token conditioned on the encoded context. Our model has been evaluated on the OMOMO and BEHAVE datasets, where it outperforms existing state-of-the-art methods in terms of both performance and inference speed. This makes ARDHOI a robust and efficient solution for text-driven HOI tasks

cs.GR↗

arXiv2024

NeFF-BioNet: Crop Biomass Prediction from Point Cloud to Drone Imagery

Crop biomass offers crucial insights into plant health and yield, making it essential for crop science, farming systems, and agricultural research. However, current measurement methods, which are labor-intensive, destructive, and imprecise, hinder large-scale quantification of this trait. To address this limitation, we present a biomass prediction network (BioNet), designed for adaptation across different data modalities, including point clouds and drone imagery. Our BioNet, utilizing a sparse 3D convolutional neural network (CNN) and a transformer-based prediction module, processes point clouds and other 3D data representations to predict biomass. To further extend BioNet for drone imagery, we integrate a neural feature field (NeFF) module, enabling 3D structure reconstruction and the transformation of 2D semantic features from vision foundation models into the corresponding 3D surfaces. For the point cloud modality, BioNet demonstrates superior performance on two public datasets, with an approximate 6.1% relative improvement (RI) over the state-of-the-art. In the RGB image modality, the combination of BioNet and NeFF achieves a 7.9% RI. Additionally, the NeFF-based approach utilizes inexpensive, portable drone-mounted cameras, providing a scalable solution for large field applications.

cs.CV↗

arXiv2024

Text-guided 3D Human Motion Generation with Keyframe-based Parallel Skip Transformer

Text-driven human motion generation is an emerging task in animation and humanoid robot design. Existing algorithms directly generate the full sequence which is computationally expensive and prone to errors as it does not pay special attention to key poses, a process that has been the cornerstone of animation for decades. We propose KeyMotion, that generates plausible human motion sequences corresponding to input text by first generating keyframes followed by in-filling. We use a Variational Autoencoder (VAE) with Kullback-Leibler regularization to project the keyframes into a latent space to reduce dimensionality and further accelerate the subsequent diffusion process. For the reverse diffusion, we propose a novel Parallel Skip Transformer that performs cross-modal attention between the keyframe latents and text condition. To complete the motion sequence, we propose a text-guided Transformer designed to perform motion-in-filling, ensuring the preservation of both fidelity and adherence to the physical constraints of human motion. Experiments show that our method achieves state-of-theart results on the HumanML3D dataset outperforming others on all R-precision metrics and MultiModal Distance. KeyMotion also achieves competitive performance on the KIT dataset, achieving the best results on Top3 R-precision, FID, and Diversity metrics.

cs.CV↗

arXiv2024

MMCBE: Multi-modality Dataset for Crop Biomass Prediction and Beyond

Crop biomass, a critical indicator of plant growth, health, and productivity, is invaluable for crop breeding programs and agronomic research. However, the accurate and scalable quantification of crop biomass remains inaccessible due to limitations in existing measurement methods. One of the obstacles impeding the advancement of current crop biomass prediction methodologies is the scarcity of publicly available datasets. Addressing this gap, we introduce a new dataset in this domain, i.e. Multi-modality dataset for crop biomass estimation (MMCBE). Comprising 216 sets of multi-view drone images, coupled with LiDAR point clouds, and hand-labelled ground truth, MMCBE represents the first multi-modality one in the field. This dataset aims to establish benchmark methods for crop biomass quantification and foster the development of vision-based approaches. We have rigorously evaluated state-of-the-art crop biomass estimation methods using MMCBE and ventured into additional potential applications, such as 3D crop reconstruction from drone imagery and novel-view rendering. With this publication, we are making our comprehensive dataset available to the broader community.

cs.CV↗

arXiv2024

Backpropagation-free Network for 3D Test-time Adaptation

Real-world systems often encounter new data over time, which leads to experiencing target domain shifts. Existing Test-Time Adaptation (TTA) methods tend to apply computationally heavy and memory-intensive backpropagation-based approaches to handle this. Here, we propose a novel method that uses a backpropagation-free approach for TTA for the specific case of 3D data. Our model uses a two-stream architecture to maintain knowledge about the source domain as well as complementary target-domain-specific information. The backpropagation-free property of our model helps address the well-known forgetting problem and mitigates the error accumulation issue. The proposed method also eliminates the need for the usually noisy process of pseudo-labeling and reliance on costly self-supervised training. Moreover, our method leverages subspace learning, effectively reducing the distribution variance between the two domains. Furthermore, the source-domain-specific and the target-domain-specific streams are aligned using a novel entropy-based adaptive fusion strategy. Extensive experiments on popular benchmarks demonstrate the effectiveness of our method. The code will be available at \url{https://github.com/abie-e/BFTT3D}.

cs.CV↗

arXiv2024

RG-CAT: Detection Pipeline and Catalogue of Radio Galaxies in the EMU Pilot Survey

We present source detection and catalogue construction pipelines to build the first catalogue of radio galaxies from the 270 $\rm deg^2$ pilot survey of the Evolutionary Map of the Universe (EMU-PS) conducted with the Australian Square Kilometre Array Pathfinder (ASKAP) telescope. The detection pipeline uses Gal-DINO computer-vision networks (Gupta et al., 2024) to predict the categories of radio morphology and bounding boxes for radio sources, as well as their potential infrared host positions. The Gal-DINO network is trained and evaluated on approximately 5,000 visually inspected radio galaxies and their infrared hosts, encompassing both compact and extended radio morphologies. We find that the Intersection over Union (IoU) for the predicted and ground truth bounding boxes is larger than 0.5 for 99% of the radio sources, and 98% of predicted host positions are within $3^{\prime \prime}$ of the ground truth infrared host in the evaluation set. The catalogue construction pipeline uses the predictions of the trained network on the radio and infrared image cutouts based on the catalogue of radio components identified using the Selavy source finder algorithm. Confidence scores of the predictions are then used to prioritize Selavy components with higher scores and incorporate them first into the catalogue. This results in identifications for a total of 211,625 radio sources, with 201,211 classified as compact and unresolved. The remaining 10,414 are categorized as extended radio morphologies, including 582 FR-I, 5,602 FR-II, 1,494 FR-x (uncertain whether FR-I or FR-II), 2,375 R (single-peak resolved) radio galaxies, and 361 with peculiar and other rare morphologies. We cross-match the radio sources in the catalogue with the infrared and optical catalogues, finding infrared cross-matches for 73% and photometric redshifts for 36% of the radio galaxies.

astro-ph.GA↗