Test-time adaptation (TTA) aims to fine-tune a trained model online using unlabeled testing data to adapt to new environments or out-of-distribution data, demonstrating broad application potential in real-world scenarios. However, in this optimization process, unsupervised learning objectives like entropy minimization frequently encounter noisy learning signals. These signals produce unreliable gradients, which hinder the model ability to converge to an optimal solution quickly and introduce significant instability into the optimization process. In this paper, we seek to resolve these issues from the perspective of optimizer design. Unlike prior TTA using manually designed optimizers like SGD, we employ a learning-to-optimize approach to automatically learn an optimizer, called Meta Gradient Generator (MGG). Specifically, we aim for MGG to effectively utilize historical gradient information during the online optimization process to optimize the current model. To this end, in MGG, we design a lightweight and efficient sequence modeling layer -- gradient memory layer. It exploits a self-supervised reconstruction loss to compress historical gradient information into network parameters, thereby enabling better memorization ability over a long-term adaptation process. We only need a small number of unlabeled samples to pre-train MGG, and then the trained MGG can be deployed to process unseen samples. Promising results on ImageNet-C, R, Sketch, and A indicate that our method surpasses current state-of-the-art methods with fewer updates, less data, and significantly shorter adaptation iterations. Compared with a previous SOTA method SAR, we achieve 7.4% accuracy improvement and 4.2 times faster adaptation speed on ImageNet-C.

Transformer-based Large Language Models (LLMs) have exhibited remarkable success in various natural language processing tasks primarily attributed to selfattention mechanism, which requires a token to consider all preceding tokens as its context to compute the attention score. However, when the context length L becomes very large (e.g., 32K), more redundant context information will be included w.r.t. L; 2) The presence of redundant context information may hamper the model to capture dependencies among crucial tokens, which may degrade the representation performance. In this paper, we propose a plug-and-play Core Context Aware (CCA) Attention for efficient long-range context modeling, which consists of two components: 1) Globality-pooling attention that divides input tokens into groups and then dynamically merges tokens within each group into one core token based on their significance; 2) Locality-preserved attention that incorporates neighboring tokens into the attention calculation. The two complementary attentions will then be fused to the final attention, maintaining comprehensive modeling ability as the full self-attention. In this way, the core context information w.r.t. a given token will be automatically focused and strengthened, while the context information in redundant groups will be diminished during the learning process. As a result, the computational and memory complexity will be significantly reduced. More importantly, the CCA-Attention can improve the long-context modeling ability by diminishing the redundant context information. Extensive experimental results demonstrate that our CCA-Attention significantly outperforms state-of-theart models in terms of computational efficiency and long-context modeling ability. Large language models (LLMs) (Brown et al., 2020; OpenAI, 2023; Touvron et al., 2023a) have demonstrated exceptional proficiency across various applications by effectively modeling extended contexts, particularly in tasks involving natural language understanding and generation (Ouyang et al., 2022; Chang et al., 2024). The remarkable success of LLMs is predominantly credited to the self-attention mechanism (Vaswani et al., 2017), which requires each token in the input sequence to calculate attention with all preceding tokens. Nonetheless, the computational and memory requirements of self-attention grow quadratically with the increase in sequence length, posing challenges for long context understanding tasks (Liu et al., 2024; Shaham et al., 2023). Recent studies (Beltagy et al., 2020; Zaheer et al., 2020; Xiao et al., 2024b) have demonstrated that the majority of layers within autoregressive LLMs exhibit redundant tokens across various attention heads and input tokens. This redundancy is visually exemplified in Figure 1, where we present a detailed visualization of the attention weights within LLaMA2 (Touvron et al., 2023a).

Abstract--Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and testing data by adapting a given model w.r.t. This task is particularly important when the test environment changes frequently. Although some recent attempts have been made to handle this task, we still face two key challenges: 1) prior methods have to perform backpropagation for each test sample, resulting in unbearable optimization costs to many applications; 2) while existing TTA solutions can significantly improve the test performance on out-of-distribution data, they often suffer from severe performance degradation on in-distribution data after TTA (known as catastrophic forgetting). To this end, we have proposed an Efficient Anti-Forgetting Test-Time Adaptation (EATA) method which develops an active sample selection criterion to identify reliable and non-redundant samples for test-time entropy minimization. To alleviate forgetting, EATA introduces a Fisher regularizer estimated from test samples to constrain important model parameters from drastic changes. However, in EATA, the adopted entropy loss consistently assigns higher confidence to predictions even when the samples are underlying uncertain, leading to overconfident predictions that underestimate the data uncertainty. To tackle this, we further propose EATA with Calibration (EATA-C) to separately exploit the reducible model uncertainty and the inherent data uncertainty for calibrated TTA. Specifically, we compare the divergence between predictions from the full network and its sub-networks to measure the reducible model uncertainty, on which we propose a test-time uncertainty reduction strategy with divergence minimization loss to encourage consistent predictions instead of overconfident ones. To further re-calibrate predicting confidence on different samples, we utilize the disagreement among predicted labels as an indicator of the data uncertainty. Based on this, we devise a min-max entropy regularization to selectively increase and decrease predicting confidence for confidence re-calibration. Note that EATA-C and EATA are different on the adaptation objective, while EATA-C still benefits from the active sample selection criterion and anti-forgetting Fisher regularization proposed in EATA. Extensive experiments on image classification and semantic segmentation verify the effectiveness of our proposed methods.

Test-time adaptation (TTA) has shown to be effective at tackling distribution shifts between training and testing data by adapting a given model on test samples. However, the online model updating of TTA may be unstable and this is often a key obstacle preventing existing TTA methods from being deployed in the real world. Specifically, TTA may fail to improve or even harm the model performance when test data have: 1) mixed distribution shifts, 2) small batch sizes, and 3) online imbalanced label distribution shifts, which are quite common in practice. In this paper, we investigate the unstable reasons and find that the batch norm layer is a crucial factor hindering TTA stability. Conversely, TTA can perform more stably with batch-agnostic norm layers, \ie, group or layer norm. However, we observe that TTA with group and layer norms does not always succeed and still suffers many failure cases. By digging into the failure cases, we find that certain noisy test samples with large gradients may disturb the model adaption and result in collapsed trivial solutions, \ie, assigning the same class label for all samples. To address the above collapse issue, we propose a sharpness-aware and reliable entropy minimization method, called SAR, for further stabilizing TTA from two aspects: 1) remove partial noisy samples with large gradients, 2) encourage model weights to go to a flat minimum so that the model is robust to the remaining noisy samples. Promising results demonstrate that SAR performs more stably over prior methods and is computationally efficient under the above wild test scenarios.