Deep Global Clustering for Hyperspectral Image Segmentation: Concepts, Applications, and Open Challenges

Hyperspectral imaging (HSI) analysis faces computational bottlenecks due to massive data volumes that exceed available memory. While foundation models pre-trained on large remote sensing datasets show promise, their learned representations often fail to transfer to domain-specific applications like close-range agricultural monitoring where spectral signatures, spatial scales, and semantic targets differ fundamentally. This report presents Deep Global Clustering (DGC), a conceptual framework for memory-efficient HSI segmentation that learns global clustering structure from local patch observations without pre-training. DGC operates on small patches with overlapping regions to enforce consistency, enabling training in under 30 minutes on consumer hardware while maintaining constant memory usage. On a leaf disease dataset, DGC achieves background-tissue separation (mean IoU 0.925) and demonstrates unsupervised disease detection through navigable semantic granularity. However, the framework suffers from optimization instability rooted in multi-objective loss balancing: meaningful representations emerge rapidly but degrade due to cluster over-merging in feature space. We position this work as intellectual scaffolding - the design philosophy has merit, but stable implementation requires principled approaches to dynamic loss balancing. Code and data are available at https://github.com/b05611038/HSI_global_clustering.

EB-gMCR: Energy-Based Generative Modeling for Signal Unmixing and Multivariate Curve Resolution

Signal unmixing analysis decomposes data into basic patterns and is widely applied in chemical and biological research. Multivariate curve resolution (MCR), a branch of signal unmixing, separates mixed chemical signals into base patterns (components) and their concentrations, playing a key role in understanding composition. Classical MCR is typically framed as matrix factorization (MF) and requires a user-specified component count, usually unknown in real data. As dataset size or component count increases, the scalability and reliability of MF-based MCR face significant challenges. This study reformulates MCR as a generative process (gMCR), and introduces an energy-based deep learning solver, EB-gMCR, that automatically discovers the smallest component set able to reconstruct the data faithfully. EB-gMCR starts from a large candidate pool (e.g., 1024 spectra) and employs a differentiable gating network to retain only active components while estimating their concentrations. On noisy synthetic datasets containing up to 256 latent sources, EB-gMCR maintained R^2 >= 0.98 and recovered the component count within 5% of the ground truth; at lower noise it achieved R^2 >= 0.99 with near exact component estimation. Additional chemical priors, such as non-negativity or nonlinear mixing, enter as simple plug-in functions, enabling adaptation to other instruments or domains without altering the core learning process. By uniting high-capacity generative modeling and hard component selection, EB-gMCR offers a practical route to large-scale signal unmixing analysis, including chemical library-driven scenarios. The source code is available at https://github.com/b05611038/ebgmcr_solver.

Improving Visual Object Tracking through Visual Prompting

Learning a discriminative model to distinguish a target from its surrounding distractors is essential to generic visual object tracking. Dynamic target representation adaptation against distractors is challenging due to the limited discriminative capabilities of prevailing trackers. We present a new visual Prompting mechanism for generic Visual Object Tracking (PiVOT) to address this issue. PiVOT proposes a prompt generation network with the pre-trained foundation model CLIP to automatically generate and refine visual prompts, enabling the transfer of foundation model knowledge for tracking. While CLIP offers broad category-level knowledge, the tracker, trained on instance-specific data, excels at recognizing unique object instances. Thus, PiVOT first compiles a visual prompt highlighting potential target locations. To transfer the knowledge of CLIP to the tracker, PiVOT leverages CLIP to refine the visual prompt based on the similarities between candidate objects and the reference templates across potential targets. Once the visual prompt is refined, it can better highlight potential target locations, thereby reducing irrelevant prompt information. With the proposed prompting mechanism, the tracker can generate improved instance-aware feature maps through the guidance of the visual prompt, thus effectively reducing distractors. The proposed method does not involve CLIP during training, thereby keeping the same training complexity and preserving the generalization capability of the pretrained foundation model. Extensive experiments across multiple benchmarks indicate that PiVOT, using the proposed prompting method can suppress distracting objects and enhance the tracker.