相关论文: SNAP: Low-Latency Test-Time Adaptation with Sparse…

Test-time adaptation (TTA) is a task that continually adapts a pre-trained source model to the target domain during inference. One popular approach involves fine-tuning model with cross-entropy loss according to estimated pseudo-labels.…

Test-time domain adaptation (TTDA) is an excellent method which helps generalize models across domains, tasks, and distributions without the use of labeled datasets. Thus, TTDA is very useful in natural language processing (NLP) in the…

Speech Foundation Models encounter significant performance degradation when deployed in real-world scenarios involving acoustic domain shifts, such as background noise and speaker accents. Test-time adaptation (TTA) has recently emerged as…

On-device training is essential for user personalisation and privacy. With the pervasiveness of IoT devices and microcontroller units (MCUs), this task becomes more challenging due to the constrained memory and compute resources, and the…

Test-Time Optimization enables models to adapt to new data during inference by updating parameters on-the-fly. Recent advances in Vision-Language Models (VLMs) have explored learning prompts at test time to improve performance in downstream…

Transformer-based methods have achieved remarkable performance in event-based object detection, owing to the global modeling ability. However, they neglect the influence of non-event and noisy regions and process them uniformly, leading to…

Performance of convolutional neural networks (CNNs) in image analysis tasks is often marred in the presence of acquisition-related distribution shifts between training and test images. Recently, it has been proposed to tackle this problem…

Nowadays, deep neural networks outperform humans in many tasks. However, if the input distribution drifts away from the one used in training, their performance drops significantly. Recently published research has shown that adapting the…

Wearable human activity recognition (WHAR) models often suffer from performance degradation under real-world cross-user distribution shifts. Test-time adaptation (TTA) mitigates this degradation by adapting models online using unlabeled…

Recent strides in low-latency spiking neural network (SNN) algorithms have drawn significant interest, particularly due to their event-driven computing nature and fast inference capability. One of the most efficient ways to construct a…

Continual Test-Time Adaptation (CTA) is a challenging task that aims to adapt a source pre-trained model to continually changing target domains. In the CTA setting, a model does not know when the target domain changes, thus facing a drastic…

Spiking neural networks (SNNs) offer energy efficiency over artificial neural networks (ANNs) but suffer from high latency and computational overhead due to their multi-timestep operational nature. While various dynamic computation methods…

Neural Radiance Fields (NeRF)-based models have achieved remarkable success in 3D reconstruction and rendering tasks. However, during both training and inference, these models rely heavily on dense point sampling along rays from multiple…

In this paper, we seek to develop a versatile test-time adaptation (TTA) objective for a variety of tasks - classification and regression across image-, object-, and pixel-level predictions. We achieve this through a self-bootstrapping…

Domain adaptation helps generalizing object detection models to target domain data with distribution shift. It is often achieved by adapting with access to the whole target domain data. In a more realistic scenario, target distribution is…

Test-time adaptation (TTA) has recently emerged as a promising approach for improving time series forecasting (TSF) under distribution shift. Existing TSF-TTA methods differ in how they utilize revealed targets, yet the resulting adaptation…

Long-context modeling is crucial for next-generation language models, yet the high computational cost of standard attention mechanisms poses significant computational challenges. Sparse attention offers a promising direction for improving…

Vision-language models (VLMs) exhibit remarkable zero-shot generalization but suffer performance degradation under distribution shifts in downstream tasks, particularly in the absence of labeled data. Test-Time Adaptation (TTA) addresses…

Signal classification models based on deep neural networks are typically trained on datasets collected under controlled conditions, either simulated or over-the-air (OTA), which are constrained to specific channel environments with limited…

Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising interpretability approach. However, current SAE training…