arXiv subjects

Sira Sriswasdi

Publications and source records attributed to Sira Sriswasdi.

7 recordsLinked to original sources

arXiv2026

On the covering of $n + ε$ square with $n^2 + 1$ unit squares for $n \geq 4$

In 2006, Alexander Soifer conjectured that one cannot fully cover a square of side length $> n$ with $n^2 + O(1)$ unit squares. For small $n \in \{2, 3\}$, in 2009, Janusz Januszewski proved that it is impossible to fully cover a square of side length $> n$ with exactly $n^2 + 1$ unit squares. Recently in 2023, Baek and Lee proved that it is impossible to fully cover an equilateral triangle of side length $> n$ with exactly $n^2 + 1$ unit equilateral triangles whose sides are parallel to it. There were also some progress on a related problem: what is the largest square with side length $S(k)$ that can be fully covered by $k$ unit squares. However, there have been no improvement on the original conjecture. In this work, new tools have been developed that led to the proof of this conjecture for $n = 4$, with potential applications to related problems.

math.MG↗

arXiv2025

Distilling Two-Timed Flow Models by Separately Matching Initial and Terminal Velocities

A flow matching model learns a time-dependent vector field $v_t(x)$ that generates a probability path $\{ p_t \}_{0 \leq t \leq 1}$ that interpolates between a well-known noise distribution ($p_0$) and the data distribution ($p_1$). It can be distilled into a two-timed flow model (TTFM) $ϕ_{s,x}(t)$ that can transform a sample belonging to the distribution at an initial time $s$ to another belonging to the distribution at a terminal time $t$ in one function evaluation. We present a new loss function for TTFM distillation called the \emph{initial/terminal velocity matching} (ITVM) loss that extends the Lagrangian Flow Map Distillation (LFMD) loss proposed by Boffi et al. by adding redundant terms to match the initial velocities at time $s$, removing the derivative from the terminal velocity term at time $t$, and using a version of the model under training, stabilized by exponential moving averaging (EMA), to compute the target terminal average velocity. Preliminary experiments show that our loss leads to better few-step generation performance on multiple types of datasets and model architectures over baselines.

cs.LG↗

arXiv2022

ReCasNet: Improving consistency within the two-stage mitosis detection framework

Mitotic count (MC) is an important histological parameter for cancer diagnosis and grading, but the manual process for obtaining MC from whole-slide histopathological images is very time-consuming and prone to error. Therefore, deep learning models have been proposed to facilitate this process. Existing approaches utilize a two-stage pipeline: the detection stage for identifying the locations of potential mitotic cells and the classification stage for refining prediction confidences. However, this pipeline formulation can lead to inconsistencies in the classification stage due to the poor prediction quality of the detection stage and the mismatches in training data distributions between the two stages. In this study, we propose a Refine Cascade Network (ReCasNet), an enhanced deep learning pipeline that mitigates the aforementioned problems with three improvements. First, window relocation was used to reduce the number of poor quality false positives generated during the detection stage. Second, object re-cropping was performed with another deep learning model to adjust poorly centered objects. Third, improved data selection strategies were introduced during the classification stage to reduce the mismatches in training data distributions. ReCasNet was evaluated on two large-scale mitotic figure recognition datasets, canine cutaneous mast cell tumor (CCMCT) and canine mammary carcinoma (CMC), which resulted in up to 4.8% percentage point improvements in the F1 scores for mitotic cell detection and 44.1% reductions in mean absolute percentage error (MAPE) for MC prediction. Techniques that underlie ReCasNet can be generalized to other two-stage object detection networks and should contribute to improving the performances of deep learning models in broad digital pathology applications.

cs.CV↗

arXiv2020

High resolution weakly supervised localization architectures for medical images

In medical imaging, Class-Activation Map (CAM) serves as the main explainability tool by pointing to the region of interest. Since the localization accuracy from CAM is constrained by the resolution of the model's feature map, one may expect that segmentation models, which generally have large feature maps, would produce more accurate CAMs. However, we have found that this is not the case due to task mismatch. While segmentation models are developed for datasets with pixel-level annotation, only image-level annotation is available in most medical imaging datasets. Our experiments suggest that Global Average Pooling (GAP) and Group Normalization are the main culprits that worsen the localization accuracy of CAM. To address this issue, we propose Pyramid Localization Network (PYLON), a model for high-accuracy weakly-supervised localization that achieved 0.62 average point localization accuracy on NIH's Chest X-Ray 14 dataset, compared to 0.45 for a traditional CAM model. Source code and extended results are available at https://github.com/cmb-chula/pylon.

cs.CV↗

arXiv2012

Refining the Protein-Protein Interactome using Gene Expression Data

Proteins interact with other proteins within biological pathways, forming connected subgraphs in the protein-protein interactome (PPI). Proteins are often involved in multiple biological pathways which complicates interpretation of interactions between proteins. Gene expression data can assist our inference since genes within a particular pathway tend to have more correlated expression patterns than genes from distinct pathways. We provide an algorithm that uses gene expression information to remove inter-pathway protein-protein interactions, thereby simplifying the structure of the protein-protein interactome. This refined topology permits easier interpretation and greater biological coherence of multiple biological pathways simultaneously.

q-bio.MN↗

arXiv2011

Lower Bound for Convex Hull Area and Universal Cover Problems

In this paper, we provide a lower bound for an area of the convex hull of points and a rectangle in a plane. We then apply this estimate to establish a lower bound for a universal cover problem. We showed that a convex universal cover for a unit length curve has area at least 0.232239. In addition, we show that a convex universal cover for a unit closed curve has area at least 0.0879873.

math.MG↗

arXiv2009

An Improved Lower Bound for Moser's Worm Problem

We show that any convex region which contains a unit segment, an equilateral triangle of sides 1/2, and a square of side 1/3 always has area at least 0.227498. Using grid-search algorithm, we attempt to find a configuration of these three objects with minimal convex hull area. Consequently, we improve a lower bound for Moser's worm problem from 0.2194 to 0.227498.

math.MG↗