Related papers: Frequency Composition for Compressed and Domain-Ad…

Tremendous research efforts have been made to thrive deep domain adaptation (DA) by seeking domain-invariant features. Most existing deep DA models only focus on aligning feature representations of task-specific layers across domains while…

Structured pruning and quantization are fundamental techniques used to reduce the size of deep neural networks (DNNs) and typically are applied independently. Applying these techniques jointly via co-optimization has the potential to…

Current parameter-efficient fine-tuning (PEFT) methods build adapters widely agnostic of the context of downstream task to learn, or the context of important knowledge to maintain. As a result, there is often a performance gap compared to…

Conventional low-rank adaptation methods build adapters without considering data context, leading to sub-optimal fine-tuning performance and severe forgetting of inherent world knowledge. In this paper, we propose context-oriented…

Test-time domain adaptation aims to adapt a source pre-trained model to a target domain without using any source data. Existing works mainly consider the case where the target domain is static. However, real-world machine perception systems…

As deep neural networks are increasingly deployed in dynamic, real-world environments, relying on a single static model is often insufficient. Changes in input data distributions caused by sensor drift or lighting variations necessitate…

Unsupervised Domain Adaptation (UDA) seeks to transfer knowledge from a labeled source domain to an unlabeled target domain but often suffers from severe domain and scale gaps that degrade performance. Existing cross-attention-based…

Domain adaptation is a popular paradigm in modern machine learning which aims at tackling the problem of divergence (or shift) between the labeled training and validation datasets (source domain) and a potentially large unlabeled dataset…

The growing complexity of neural networks hinders the deployment of distributed machine learning on resource-constrained devices. Split learning (SL) offers a promising solution by partitioning the large model and offloading the primary…

Continual Test-time adaptation (CTTA) continuously adapts the deployed model on every incoming batch of data. While achieving optimal accuracy, existing CTTA approaches present poor real-world applicability on resource-constrained edge…

Unsupervised domain adaptation (UDA) involves learning class semantics from labeled data within a source domain that generalize to an unseen target domain. UDA methods are particularly impactful for semantic segmentation, where annotations…

Test-time adaptation (TTA) allows a model to be adapted to an unseen domain without accessing the source data. Due to the nature of practical environments, TTA has a limited amount of data for adaptation. Recent TTA methods further restrict…

JPEG images can be further compressed to enhance the storage and transmission of large-scale image datasets. Existing learned lossless compressors for RGB images cannot be well transferred to JPEG images due to the distinguishing…

Contemporary deep learning, characterized by the training of cumbersome neural networks on massive datasets, confronts substantial computational hurdles. To alleviate heavy data storage burdens on limited hardware resources, numerous…

Discrete visual tokenizers transform images into a sequence of tokens, enabling token-based visual generation akin to language models. However, this process is inherently challenging, as it requires both compressing visual signals into a…

Learning-based image compression was shown to achieve a competitive performance with state-of-the-art transform-based codecs. This motivated the development of new learning-based visual compression standards such as JPEG-AI. Of particular…

Recent advancements in keypoint detection and descriptor extraction have shown impressive performance in local feature learning tasks. However, existing methods generally exhibit suboptimal performance under extreme conditions such as…

Efficient inference is critical for deploying deep learning models on edge AI devices. Low-bit quantization (e.g., 3- and 4-bit) with fixed-point arithmetic improves efficiency, while low-power memory technologies like analog nonvolatile…

Camouflaged Object Detection is challenging due to the high degree of similarity between camouflaged objects and their surrounding backgrounds. Current COD methods mainly rely on edge extraction in the spatial domain and local pixel-level…

Continual Test-Time Adaptation (CTTA) aims to quickly fine-tune the model during the test phase so that it can adapt to multiple unknown downstream domain distributions without pre-acquiring downstream domain data. To this end, existing…