ZHZeeshan Hayder

Zeeshan Hayder

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zeeshan Hayder has a total of 44 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    PSMamba: Progressive self-supervised vision Mamba for plant disease recognition

    by Abdullah Al Mamun, Miaohua Zhang, David Ahmedt-Aristizabal, Zeeshan Hayder, Mohammad Awrangjeb


  • Top Cited Papers
    Open Access

    ConMamba: Contrastive vision Mamba for plant disease detection

    by Abdullah Al Mamun, Miaohua Zhang, David Ahmedt-Aristizabal, Zeeshan Hayder, Mohammad Awrangjeb


  • Open Access

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

    by Miaohua Zhang, Mohammad Ali Armin, Xuesong Li, Sisi Liang, Lars Petersson, Changming Sun, David Ahmedt-Aristizabal, Zeeshan Hayder

    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.

  • Open Access

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

    by Abdullah Al Mamun, Miaohua Zhang, David Ahmedt-Aristizabal, Zeeshan Hayder, Mohammad Awrangjeb

    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.


  • Open Access

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

    by Zichen Geng, Zeeshan Hayder, Wei Liu, Ajmal Saeed Mian

    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.


  • Open Access

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

    by Zichen Geng, Zeeshan Hayder, Wei Liu, Ajmal Saeed Mian

    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

  • Canonical Shape Projection Is All You Need for 3D Few-Shot Class Incremental Learning

    by Ali Cheraghian, Zeeshan Hayder, Sameera Ramasinghe, Shafin Rahman, Javad Jafaryahya, Lars Petersson, Mehrtash Harandi


  • Open Access

    Plant Disease Detection Using Self-Supervised Learning: A Systematic Review

    by Abdullah Al Mamun, David Ahmedt-Aristizabal, Miaohua Zhang, Ismail Hossen, Zeeshan Hayder, Mohammad Awrangjeb

    Agriculture has a crucial role in both the economy and food supply. However, the frequent occurrence of plant diseases can have a significant negative influence on the production of foods. Timely detection of a disease is important for its effective management, e.g., targeted use of pesticides. Conventional Plant Disease Detection (PDD) methods are manual, slow, tedious, and prone to errors, thereby increasing the risk of significant yield losses. Recently, various data-driven approaches, including Deep Learning and Computer Vision-based approaches, have been explored for PDD. However, the scarcity of large and annotated datasets and the limited scalability of these approaches have prompted researchers to turn to the Self-Supervised Learning (SSL) approach. In this review, we provide the very first conceptual grounding for the SSL approach in PDD. By reviewing a large body of recent related works in the literature, we thoroughly analyse and categorise them into generative, predictive, contrastive and hybrid SSL models. Moreover, this review analyses various recent datasets and performance metrics used in these models. Finally, we explain the research challenges and key research directions aimed at advancing PDD through the SSL approach.


  • Open Access

    Backpropagation-free Network for 3D Test-time Adaptation

    by Yanshuo Wang, Ali Cheraghian, Zeeshan Hayder, Jie Hong, Sameera Ramasinghe, Shafin Rahman, David Ahmedt-Aristizabal, Xuesong Li, Lars Petersson, Mehrtash Harandi

    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}.

  • Open Access

    DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation

    by Zeeshan Hayder, Xuming He

    Scene graph generation aims to capture detailed spatial and semantic relationships between objects in an image, which is challenging due to incomplete labelling, long-tailed relationship categories, and relational semantic overlap. Existing Transformer-based methods either employ distinct queries for objects and predicates or utilize holistic queries for relation triplets and hence often suffer from limited capacity in learning low-frequency relationships. In this paper, we present a new Transformer-based method, called DSGG, that views scene graph detection as a direct graph prediction problem based on a unique set of graph-aware queries. In particular, each graph-aware query encodes a compact representation of both the node and all of its relations in the graph, acquired through the utilization of a relaxed sub-graph matching during the training process. Moreover, to address the problem of relational semantic overlap, we utilize a strategy for relation distillation, aiming to efficiently learn multiple instances of semantic relationships. Extensive experiments on the VG and the PSG datasets show that our model achieves state-of-the-art results, showing a significant improvement of 3.5\% and 6.7\% in mR@50 and mR@100 for the scene-graph generation task and achieves an even more substantial improvement of 8.5\% and 10.3\% in mR@50 and mR@100 for the panoptic scene graph generation task. Code is available at \url{https://github.com/zeeshanhayder/DSGG}.