arXiv subjects

Nikos Giakoumoglou

Publications and source records attributed to Nikos Giakoumoglou.

12 recordsLinked to original sources

arXiv2026

Discriminative and Consistent Representation Distillation

Knowledge Distillation (KD) transfers knowledge from a large teacher to a smaller student model. While contrastive objectives have proven effective for learning structured representations in self-supervised settings, their use in distillation is hindered by two practical shortcomings: the reliance on external memory banks for negative sampling, and fixed temperature hyperparameters that limit adaptability across training stages and teacher-student pairs. We therefore propose Discriminative and Consistent Representation Distillation (DCD), which combines contrastive instance discrimination with a consistency regularization term over the cross-model similarity matrix. The contrastive term aligns each student representation with its teacher counterpart, while the consistency term penalizes asymmetry between the row-normalized and column-normalized views of that matrix, constraining the off-diagonal structure that instance discrimination alone leaves free; we show that it vanishes precisely when this matrix is symmetric. We further introduce an efficient in-batch sampling that eliminates external memory banks, and learnable scale and bias parameters that adapt during training to control the sharpness and offset of the distillation signal. The method matches the training speed of standard KD while adding only 66K additional parameters. Through extensive experiments on CIFAR-100, ImageNet, and MS-COCO, together with cross-dataset transfer to STL-10 and Tiny ImageNet, we show that our approach achieves competitive performance in classification, object detection, and transfer, while substantially reducing memory consumption and training time compared to existing contrastive distillation methods.

cs.CV↗

arXiv2026

Open-World Semantic Segmentation with Sensitivity Modeling

Modern vision systems must operate in "open-world" settings, where models must recognize known categories and detect unseen or anomalous content. Conventional semantic segmentation models operate under a "closed-world" assumption, often producing overconfident misclassifications on novel content. We address open-world semantic segmentation, the joint task of segmenting known classes while detecting and grouping novel or anomalous content without additional supervision, by extending a dual-decoder baseline with a third, complementary decoder within a unified encoder-decoder design. The first decoder performs closed-set segmentation using Gaussian prototypes for known categories. The second uses contrastive feature learning to isolate unknown regions in embedding space. The third, our key contribution, is a sensitivity decoder that captures fine-grained texture irregularities and activation instabilities indicative of semantic uncertainty, which neither semantic prototypes nor contrastive norms can reliably detect. The three decoders provide genuinely complementary signals: class-level OOD distance in logit space, global feature energy in embedding space, and local activation instability across encoder scales. Experiments on Cityscapes and BDD-Anomaly show that our method improves anomaly segmentation and novel-class discovery while maintaining competitive closed-set accuracy, with gains of +2.4% AUROC and a 2.5 pp. reduction in FPR@95TPR on BDD-Anomaly over the baseline.

cs.CV↗

arXiv2026

Three Necessary Principles for Self-Supervised Visual Representation Learning

We argue that learning visual representations without labels requires a training signal jointly complete across three non-overlapping objectives: semantic invariance across augmented views, patch-level spatial prediction, and representational non-degeneracy. We formalize these as the observation, prediction, and regularization principles and prove (i) that combining observation and prediction without regularization admits the constant encoder as a global minimizer under negative-free alignment; (ii) that the two objectives are gradient-complementary and structurally non-conflicting at the encoder output; and (iii) that the momentum encoder converges to the same fixed point as the online encoder and provides no collapse guarantee at convergence. Contrastive alignment provides only self-limiting collapse resistance, formalized via an explicit gradient-decay argument. Dropping prediction withholds the spatial training signal by construction; dropping observation forfeits cross-view semantic invariance by construction; at the scale we study, no pair substitutes for the third. Every major self-supervised method is a special case of a single unified energy decomposition. We pair every theoretical claim with a controlled experiment, including a patch-retrieval evaluation for the spatial consequence of prediction.

cs.CV↗

arXiv2026

Relational Representation Distillation

Knowledge distillation transfers knowledge from large teacher models to more compact student networks. The standard approach minimizes the Kullback-Leibler (KL) divergence between the probabilistic outputs of the teacher and student, aligning predictions but neglecting the structural relationships encoded within the teacher's internal representations. Recent advances have adopted contrastive learning objectives to address this limitation; however, such instance-discrimination-based methods induce a "class collision problem", in which semantically related samples are inappropriately pushed apart despite belonging to similar classes. To overcome this, we propose Relational Representation Distillation (RRD) that preserves the relative relationships among instances rather than enforcing absolute separation. Our method introduces separate temperature parameters for teacher and student distributions, with a sharper teacher (low $τ_t$) emphasizing primary relationships and a softer student (high $τ_s$) maintaining secondary similarities. This dual-temperature formulation creates an implicit information bottleneck that preserves fine-grained relational structure while avoiding the over-separation characteristic of contrastive losses. We establish theoretical connections showing that InfoNCE emerges as a limiting case of our objective when $τ_t \rightarrow 0$, and empirically demonstrate that this relaxed formulation yields superior relational alignment and generalization across classification and detection tasks.

cs.CV↗

arXiv2026

SynCo: Synthetic Hard Negatives for Contrastive Visual Representation Learning

Contrastive learning relies on informative negatives to shape the representation space, yet obtaining hard negatives is costly, often requiring large batch sizes or extensive memory banks. We propose SynCo (Synthetic negatives in Contrastive learning), an approach that synthesizes hard negatives directly in the representation space from cached queue embeddings, with no additional forward passes or input-space processing. We find that six lightweight synthesis strategies, exhaustively covering the geometric, stochastic, and adversarial perturbation families, consistently improve learned representations at negligible computational cost. Although applicable to any InfoNCE-based contrastive objective, we demonstrate SynCo within the MoCo framework. On ImageNet ILSVRC-2012 linear evaluation at 200 epochs, SynCo yields improvements of +0.4% over MoCo-v2 and +1.0% over MoCHi. Unlike MoCHi, which degrades at extended pretraining schedules (underperforming MoCo-v2 by 2.4% at 800 epochs), SynCo does not: with a simple synthetic negative schedule, performance improves by +0.5% over MoCo-v2 at 800 epochs. SynCo also transfers well to a range of downstream tasks.

cs.CV↗

arXiv2026

ViTAMINS: An Empirical Study of Training Self-Supervised Vision Transformers with Synthetic Hard Negatives

We introduce ViTAMINS, a method that integrates synthetic hard negatives into unsupervised vision transformer pretraining to improve representation quality. Our approach is thoroughly benchmarked on ImageNet and transfer learning, image retrieval, copy detection, and image, video segmentation tasks. Notably, our proposed negatives give rise to emergent properties, where learned representations contain explicit information about the semantic content of an image and serve as excellent classifiers (up to +11.3% over baselines). ViTAMINS achieves these benefits through simple modifications to existing contrastive frameworks and outperforms competing methods while being more resource efficient, e.g., our ViT-B surpasses V-JEPA with ViT-L. Our findings motivate reconsidering contrastive learning as a simpler yet powerful alternative to dominant generative and self-distillation approaches.

cs.CV↗

arXiv2026

Caption-Matching: A Multimodal Approach for Cross-Domain Image Retrieval

Cross-Domain Image Retrieval (CDIR) is a challenging task in computer vision, aiming to match images across different visual domains such as sketches, paintings, and photographs. Existing CDIR methods rely either on supervised learning with labeled cross-domain correspondences or on methods that require training or fine-tuning on target datasets, often struggling with substantial domain gaps and limited generalization to unseen domains. This paper introduces a novel CDIR approach that incorporates textual context by leveraging publicly available pre-trained vision-language models. Our method, Caption-Matching (CM), uses generated image captions as a domain-agnostic intermediate representation, enabling effective cross-domain similarity computation without the need for labeled data or further training. We evaluate our method on standard CDIR benchmark datasets, demonstrating state-of-the-art performance in plug-and-play settings with consistent improvements on Office-Home and DomainNet over previous methods. We also demonstrate our method's effectiveness on a dataset of AI-generated images from Midjourney, showcasing its ability to handle complex, multi-domain queries.

cs.CV↗

arXiv2025

Unsupervised Training of Vision Transformers with Synthetic Negatives

This paper does not introduce a novel method per se. Instead, we address the neglected potential of hard negative samples in self-supervised learning. Previous works explored synthetic hard negatives but rarely in the context of vision transformers. We build on this observation and integrate synthetic hard negatives to improve vision transformer representation learning. This simple yet effective technique notably improves the discriminative power of learned representations. Our experiments show performance improvements for both DeiT-S and Swin-T architectures.

cs.CV↗

arXiv2025

Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives

This paper does not introduce a new method per se. Instead, we build on existing self-supervised learning approaches for vision, drawing inspiration from the adage "fake it till you make it". While contrastive self-supervised learning has achieved remarkable success, it typically relies on vast amounts of real-world data and carefully curated hard negatives. To explore alternatives to these requirements, we investigate two forms of "faking it" in vision transformers. First, we study the potential of generative models for unsupervised representation learning, leveraging synthetic data to augment sample diversity. Second, we examine the feasibility of generating synthetic hard negatives in the representation space, creating diverse and challenging contrasts. Our framework - dubbed Syn2Co - combines both approaches and evaluates whether synthetically enhanced training can lead to more robust and transferable visual representations on DeiT-S and Swin-T architectures. Our findings highlight the promise and limitations of synthetic data in self-supervised learning, offering insights for future work in this direction.

cs.CV↗

arXiv2025

Distilling Invariant Representations with Dual Augmentation

Knowledge distillation (KD) has been widely used to transfer knowledge from large, accurate models (teachers) to smaller, efficient ones (students). Recent methods have explored enforcing consistency by incorporating causal interpretations to distill invariant representations. In this work, we extend this line of research by introducing a dual augmentation strategy to promote invariant feature learning in both teacher and student models. Our approach leverages different augmentations applied to both models during distillation, pushing the student to capture robust, transferable features. This dual augmentation strategy complements invariant causal distillation by ensuring that the learned representations remain stable across a wider range of data variations and transformations. Extensive experiments on CIFAR-100 demonstrate the effectiveness of this approach, achieving competitive results in same-architecture KD.

cs.CV↗

arXiv2025

Cluster Contrast for Unsupervised Visual Representation Learning

We introduce Cluster Contrast (CueCo), a novel approach to unsupervised visual representation learning that effectively combines the strengths of contrastive learning and clustering methods. Inspired by recent advancements, CueCo is designed to simultaneously scatter and align feature representations within the feature space. This method utilizes two neural networks, a query and a key, where the key network is updated through a slow-moving average of the query outputs. CueCo employs a contrastive loss to push dissimilar features apart, enhancing inter-class separation, and a clustering objective to pull together features of the same cluster, promoting intra-class compactness. Our method achieves 91.40% top-1 classification accuracy on CIFAR-10, 68.56% on CIFAR-100, and 78.65% on ImageNet-100 using linear evaluation with a ResNet-18 backbone. By integrating contrastive learning with clustering, CueCo sets a new direction for advancing unsupervised visual representation learning.

cs.CV↗

arXiv2025

A Review on Discriminative Self-supervised Learning Methods in Computer Vision

Self-supervised learning (SSL) has rapidly emerged as a transformative approach in computer vision, enabling the extraction of rich feature representations from vast amounts of unlabeled data and reducing reliance on costly manual annotations. This review presents a comprehensive analysis of discriminative SSL methods, which focus on learning representations by solving pretext tasks that do not require human labels. The paper systematically categorizes discriminative SSL approaches into five main groups: contrastive methods, clustering methods, self-distillation methods, knowledge distillation methods, and feature decorrelation methods. For each category, the review details the underlying principles, architectural components, loss functions, and representative algorithms, highlighting their unique mechanisms and contributions to the field. Extensive comparative evaluations are provided, including linear and semi-supervised protocols on standard benchmarks such as ImageNet, as well as transfer learning performance across diverse downstream tasks. The review also discusses theoretical foundations, scalability, efficiency, and practical challenges, such as computational demands and accessibility. By synthesizing recent advancements and identifying key trends, open challenges, and future research directions, this work serves as a valuable resource for researchers and practitioners aiming to leverage discriminative SSL for robust and generalizable computer vision models.

cs.CV↗