Related papers: Align, Minimize and Diversify: A Source-Free Unsup…
We present a novel multiple-source unsupervised model for text classification under domain shift. Our model exploits the update rates in document representations to dynamically integrate domain encoders. It also employs a probabilistic…
Learning predictive models in new domains with scarce training data is a growing challenge in modern supervised learning scenarios. This incentivizes developing domain adaptation methods that leverage the knowledge in known domains (source)…
Distribution Matching Distillation (DMD) is a powerful acceleration paradigm, yet its stability is often compromised in Forbidden Zone, regions where the real teacher provides unreliable guidance while the fake teacher exerts insufficient…
This work presents a new method for unsupervised thermal image classification and semantic segmentation by transferring knowledge from the RGB domain using a multi-domain attention network. Our method does not require any thermal…
The advent of recurrent neural networks for handwriting recognition marked an important milestone reaching impressive recognition accuracies despite the great variability that we observe across different writing styles. Sequential…
Modern deep neural networks (DNNs) are highly accurate on many recognition tasks for overhead (e.g., satellite) imagery. However, visual domain shifts (e.g., statistical changes due to geography, sensor, or atmospheric conditions) remain a…
Optical character recognition (OCR) systems performance have improved significantly in the deep learning era. This is especially true for handwritten text recognition (HTR), where each author has a unique style, unlike printed text, where…
Unsupervised domain adaption has proven to be an effective approach for alleviating the intensive workload of manual annotation by aligning the synthetic source-domain data and the real-world target-domain samples. Unfortunately, mapping…
We present an unsupervised deep learning method for text line segmentation that is inspired by the relative variance between text lines and spaces among text lines. Handwritten text line segmentation is important for the efficiency of…
Unsupervised binary representation allows fast data retrieval without any annotations, enabling practical application like fast person re-identification and multimedia retrieval. It is argued that conflicts in binary space are one of the…
Unsupervised domain adaptation aims to transfer and adapt knowledge learned from a labeled source domain to an unlabeled target domain. Key components of unsupervised domain adaptation include: (a) maximizing performance on the target, and…
Distribution alignment has many applications in deep learning, including domain adaptation and unsupervised image-to-image translation. Most prior work on unsupervised distribution alignment relies either on minimizing simple non-parametric…
Autonomous systems (AS) often use Deep Neural Network (DNN) classifiers to allow them to operate in complex, high-dimensional, non-linear, and dynamically changing environments. Due to the complexity of these environments, DNN classifiers…
Performing unsupervised domain adaptation on resource-constrained edge devices is challenging. Existing research typically adopts architecture optimization (e.g., designing slimmable networks) but requires expensive training costs.…
Preference-based alignment methods (e.g., RLHF, DPO) typically optimize a single scalar objective, implicitly averaging over heterogeneous human preferences. In practice, systematic annotator and user-group disagreement makes mean-reward…
Historical documents present many challenges for offline handwriting recognition systems, among them, the segmentation and labeling steps. Carefully annotated textlines are needed to train an HTR system. In some scenarios, transcripts are…
Self-supervised learning (SSL) leverages large amounts of unlabelled data to learn rich speech representations, fostering improvements in automatic speech recognition (ASR), even when only a small amount of labelled data is available for…
The Transformer has quickly become the dominant architecture for various pattern recognition tasks due to its capacity for long-range representation. However, transformers are data-hungry models and need large datasets for training. In…
Unsupervised Domain Adaptation (UDA) addresses the problem of performance degradation due to domain shift between training and testing sets, which is common in computer vision applications. Most existing UDA approaches are based on…
Existing domain adaptation methods aim to reduce the distributional difference between the source and target domains and respect their specific discriminative information, by establishing the Maximum Mean Discrepancy (MMD) and the…