arXiv subjects

Jenifer Kalafatovich

Publications and source records attributed to Jenifer Kalafatovich.

6 recordsLinked to original sources

arXiv2026

Tree-of-Thoughts Reasoning for Text-to-Image In-Context Learning

In text-to-image in-context learning (T2I-ICL), a model has to infer a latent compositional pattern from fewshot demonstrations for generating a query image. Recent studies show that state-of-the-art multimodal large language models struggle with this setting, particularly due to limited compositional reasoning and sensitivity to prompt construction. In this work, we propose a Tree-of-Thoughts (ToT) reasoning framework for T2I-ICL that introduces a multi-stage reasoning and selection layer that generates, evaluates, and selects among multiple candidate hypotheses before constructing the final prompt for image synthesis. By exploring alternative reasoning branches and selecting a coherent interpretation, the proposed approach mitigates prompt ambiguity and compositional errors. We implement the proposed approach in a complete ToT-T2IICL inference pipeline and evaluate it on the CoBSAT benchmark. Both qualitative and quantitative results show that structured multi-branch reasoning leads to more consistent and semantically aligned image generation compared to baseline and Chain-of-Thought prompting strategies, without any additional training or fine-tuning.

cs.CV↗

arXiv2025

FARCLUSS: Fuzzy Adaptive Rebalancing and Contrastive Uncertainty Learning for Semi-Supervised Semantic Segmentation

Semi-supervised semantic segmentation (SSSS) faces persistent challenges in effectively leveraging unlabeled data, such as ineffective utilization of pseudo-labels, exacerbation of class imbalance biases, and neglect of prediction uncertainty. Current approaches often discard uncertain regions through strict thresholding favouring dominant classes. To address these limitations, we introduce a holistic framework that transforms uncertainty into a learning asset through four principal components: (1) fuzzy pseudo-labeling, which preserves soft class distributions from top-K predictions to enrich supervision; (2) uncertainty-aware dynamic weighting, that modulate pixel-wise contributions via entropy-based reliability scores; (3) adaptive class rebalancing, which dynamically adjust losses to counteract long-tailed class distributions; and (4) lightweight contrastive regularization, that encourage compact and discriminative feature embeddings. Extensive experiments on benchmarks demonstrate that our method outperforms current state-of-the-art approaches, achieving significant improvements in the segmentation of under-represented classes and ambiguous regions.

cs.CV↗

arXiv2025

CW-BASS: Confidence-Weighted Boundary-Aware Learning for Semi-Supervised Semantic Segmentation

Semi-supervised semantic segmentation (SSSS) aims to improve segmentation performance by utilizing large amounts of unlabeled data with limited labeled samples. Existing methods often suffer from coupling, where over-reliance on initial labeled data leads to suboptimal learning; confirmation bias, where incorrect predictions reinforce themselves repeatedly; and boundary blur caused by limited boundary-awareness and ambiguous edge cues. To address these issues, we propose CW-BASS, a novel framework for SSSS. In order to mitigate the impact of incorrect predictions, we assign confidence weights to pseudo-labels. Additionally, we leverage boundary-delineation techniques, which, despite being extensively explored in weakly-supervised semantic segmentation (WSSS), remain underutilized in SSSS. Specifically, our method: (1) reduces coupling via a confidence-weighted loss that adjusts pseudo-label influence based on their predicted confidence scores, (2) mitigates confirmation bias with a dynamic thresholding mechanism that learns to filter out pseudo-labels based on model performance, (3) tackles boundary blur using a boundary-aware module to refine segmentation near object edges, and (4) reduces label noise through a confidence decay strategy that progressively refines pseudo-labels during training. Extensive experiments on Pascal VOC 2012 and Cityscapes demonstrate that CW-BASS achieves state-of-the-art performance. Notably, CW-BASS achieves a 65.9% mIoU on Cityscapes under a challenging and underexplored 1/30 (3.3%) split (100 images), highlighting its effectiveness in limited-label settings. Our code is available at https://github.com/psychofict/CW-BASS.

cs.CV↗

arXiv2020

Decoding Visual Recognition of Objects from EEG Signals based on Attention-Driven Convolutional Neural Network

The ability to perceive and recognize objects is fundamental for the interaction with the external environment. Studies that investigate them and their relationship with brain activity changes have been increasing due to the possible application in an intuitive brain-machine interface (BMI). In addition, the distinctive patterns when presenting different visual stimuli that make data differentiable enough to be classified have been studied. However, reported classification accuracy still low or employed techniques for obtaining brain signals are impractical to use in real environments. In this study, we aim to decode electroencephalography (EEG) signals depending on the provided visual stimulus. Subjects were presented with 72 photographs belonging to 6 different semantic categories. We classified 6 categories and 72 exemplars according to visual stimuli using EEG signals. In order to achieve a high classification accuracy, we proposed an attention driven convolutional neural network and compared our results with conventional methods used for classifying EEG signals. We reported an accuracy of 50.37% and 26.75% for 6-class and 72-class, respectively. These results statistically outperformed other conventional methods. This was possible because of the application of the attention network using human visual pathways. Our findings showed that EEG signals are possible to differentiate when subjects are presented with visual stimulus of different semantic categories and at an exemplar-level with a high classification accuracy; this demonstrates its viability to be applied it in a real-world BMI.

eess.SP↗

arXiv2020

Prediction of Memory Retrieval Performance Using Ear-EEG Signals

Many studies have explored brain signals during the performance of a memory task to predict later remembered items. However, prediction methods are still poorly used in real life and are not practical due to the use of electroencephalography (EEG) recorded from the scalp. Ear-EEG has been recently used to measure brain signals due to its flexibility when applying it to real world environments. In this study, we attempt to predict whether a shown stimulus is going to be remembered or forgotten using ear-EEG and compared its performance with scalp-EEG. Our results showed that there was no significant difference between ear-EEG and scalp-EEG. In addition, the higher prediction accuracy was obtained using a convolutional neural network (pre-stimulus: 74.06%, on-going stimulus: 69.53%) and it was compared to other baseline methods. These results showed that it is possible to predict performance of a memory task using ear-EEG signals and it could be used for predicting memory retrieval in a practical brain-computer interface.

eess.SP↗

arXiv2020

Neural Oscillations for Encoding and Decoding Declarative Memory using EEG Signals

Declarative memory has been studied for its relationship with remembering daily life experiences. Previous studies reported changes in power spectra during encoding phase related to behavioral performance, however decoding phase still needs to be explored. This study investigates neural oscillations changes related to memory process. Participants were asked to perform a memory task for encoding and decoding phase while EEG signals were recorded. Results showed that for encoding phase, there was a significant decrease of power in low beta, high beta bands over fronto-central area and a decrease in low beta, high beta and gamma bands over left temporal area related to successful subsequent memory effects. For decoding phase, only significant decreases of alpha power were observed over fronto-central area. This finding showed relevance of beta and alpha band for encoding and decoding phase of a memory task respectively.

cs.NE↗