Additionally, the patch tokens in foundation models can enrich the features in the detector's encoder

For example, images from two different satellites may both contain RGB channels, but the remaining channels can be different for each imaging source.

The five datasets used cover a wide range of respiratory medical conditions.

Different from the standard training objective of ViTs that computes the classification loss on an additional trainable class token, our proposed one takes advantage of all the image patch tokens to compute the training loss in a dense manner. Specifically, token labeling reformulates the image classification problem into multiple token-level recognition problems and assigns each patch token with an individual location-specific supervision generated by a machine annotator. Experiments show that token labeling can clearly and consistently improve the performance of various ViT models across a wide spectrum. For a vision transformer with 26M learnable parameters serving as an example, with token labeling, the model can achieve 84.4% Top-1 accuracy on ImageNet. The result can be further increased to 86.4% by slightly scaling the model size up to 150M, delivering the minimal-sized model among previous models (250M+) reaching 86%. We also show that token labeling can clearly improve the generalization capability of the pretrained models on downstream tasks with dense prediction, such as semantic segmentation.

Representation alignment (REPA) guides generative training by distilling representations from a strong, pretrained vision encoder to intermediate diffusion features. We investigate a fundamental question: what aspect of the target representation matters for generation, its \textit{global} \revision{semantic} information (e.g., measured by ImageNet-1K accuracy) or its spatial structure (i.e. pairwise cosine similarity between patch tokens)? Prevalent wisdom holds that stronger global semantic performance leads to better generation as a target representation. To study this, we first perform a large-scale empirical analysis across 27 different vision encoders and different model scales. The results are surprising; spatial structure, rather than global performance, drives the generation performance of a target representation. To further study this, we introduce two straightforward modifications, which specifically accentuate the transfer of \emph{spatial} information. We replace the standard MLP projection layer in REPA with a simple convolution layer and introduce a spatial normalization layer for the external representation. Surprisingly, our simple method (implemented in $<$4 lines of code), termed iREPA, consistently improves convergence speed of REPA, across a diverse set of vision encoders, model sizes, and training variants (such as REPA, REPA-E, Meanflow, JiT etc). %, etc. Our work motivates revisiting the fundamental working mechanism of representational alignment and how it can be leveraged for improved training of generative models. The code and project page are available at https://end2end-diffusion.github.io/irepa

Abstract--Transformer-based audio SSL (self-supervised learning) models often treat spectrograms as images, applying convolutional patchification with heavy temporal downsampling. This lowers the effective Nyquist frequency and introduces aliasing, while na ıve low-pass filtering removes task-relevant high-frequency cues. AaPE augments standard patch tokens with features produced by a band-limited complex sinusoidal kernel using a two-sided exponential window that dynamically targets alias-prone bands. Frequency and decay parameters of the kernel are estimated from the input, enabling parallel, adaptive subband analysis whose outputs are fused with the standard patch tokens. AaPE integrates seamlessly into the masked teacher-student self-supervised learning. In addition, we combine a multi-mask strategy with a contrastive objective to enforce consistency across diverse mask patterns, stabilizing training. Pre-training on AudioSet followed by fine-tuning evaluation across diverse downstream benchmarks, which spanned categories, such as environmental sounds and other common audio domains. Complementary linear probing evaluation mirrors this pattern, yielding clear gains on several benchmarks and strong performance elsewhere. The collective analysis of these results indicates that AaPE serves to mitigate the effects of aliasing without discarding of informative high-frequency content. Index T erms--Self-supervised learning, masked audio modeling, transformers, aliasing, structured state-space models. ECENT advances in natural language processing (NLP) and computer vision demonstrate the effectiveness of self-supervised learning (SSL), thereby training neural networks from unlabeled data via auxiliary objectives.

Zero-shot anomaly classification and segmentation (AC/AS) aim to detect anomalous samples and regions without any training data, a capability increasingly crucial in industrial inspection and medical imaging. This dissertation aims to investigate the core challenges of zero-shot AC/AS and presents principled solutions rooted in theory and algorithmic design. We first formalize the problem of consistent anomalies, a failure mode in which recurring similar anomalies systematically bias distance-based methods. By analyzing the statistical and geometric behavior of patch representations from pre-trained Vision Transformers, we identify two key phenomena - similarity scaling and neighbor-burnout - that describe how relationships among normal patches change with and without consistent anomalies in settings characterized by highly similar objects. We then introduce CoDeGraph, a graph-based framework for filtering consistent anomalies built on the similarity scaling and neighbor-burnout phenomena. Through multi-stage graph construction, community detection, and structured refinement, CoDeGraph effectively suppresses the influence of consistent anomalies. Next, we extend this framework to 3D medical imaging by proposing a training-free, computationally efficient volumetric tokenization strategy for MRI data. This enables a genuinely zero-shot 3D anomaly detection pipeline and shows that volumetric anomaly segmentation is achievable without any 3D training samples. Finally, we bridge batch-based and text-based zero-shot methods by demonstrating that CoDeGraph-derived pseudo-masks can supervise prompt-driven vision-language models. Together, this dissertation provides theoretical understanding and practical solutions for the zero-shot AC/AS problem.