Enhancing Robustness of CLIP to Common Corruptions through Bimodal Test-Time Adaptation

Although open-vocabulary classification models like Contrastive Language Image Pretraining (CLIP) have demonstrated strong zero-shot learning capabilities, their robustness to common image corruptions remains poorly understood. Through extensive experiments, we show that zero-shot CLIP lacks robustness to common image corruptions at increasing severity levels during test-time, necessitating the adaptation of CLIP to unlabeled corrupted images using test-time adaptation (TTA). However, we found that existing TTA methods have severe limitations in adapting CLIP due to their unimodal nature. To address these limitations, we propose \framework, a bimodal TTA method specially designed to improve CLIP's robustness to common image corruptions. The key insight of our approach is not only to adapt the visual encoders for better image feature extraction but also to strengthen the alignment between image and text features by promoting a stronger association between the image class prototype, computed using pseudo-labels, and the corresponding text feature. We evaluate our approach on benchmark image corruption datasets and achieve state-of-the-art results in TTA for CLIP, specifically for domains involving image corruption. Particularly, with a ViT-B/16 vision backbone, we obtain mean accuracy improvements of 9.7%, 5.94%, and 5.12% for CIFAR-10C, CIFAR-100C, and ImageNet-C, respectively.

STONE: A Submodular Optimization Framework for Active 3D Object Detection

3D object detection is fundamentally important for various emerging applications, including autonomous driving and robotics. A key requirement for training an accurate 3D object detector is the availability of a large amount of LiDAR-based point cloud data. Unfortunately, labeling point cloud data is extremely challenging, as accurate 3D bounding boxes and semantic labels are required for each potential object. This paper proposes a unified active 3D object detection framework, for greatly reducing the labeling cost of training 3D object detector. Our framework is based on a novel formulation of submodular optimization, specifically tailored to the problem of active 3D object detection. In particular, we address two fundamental challenges associated with active 3D object detection: data imbalance and the need to cover the distribution of the data, including LiDAR-based point cloud data of varying difficulty levels. Extensive experiments demonstrate that our method achieves state-of-the-art performance with high computational efficiency compared to existing active learning methods.

Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Data

With the increasing prevalence of Machine Learning as a Service (MLaaS) platforms, there is a growing focus on deep neural network (DNN) watermarking techniques. These methods are used to facilitate the verification of ownership for a target DNN model to protect intellectual property. One of the most widely employed watermarking techniques involves embedding a trigger set into the source model. Unfortunately, existing methodologies based on trigger sets are still susceptible to functionality-stealing attacks, potentially enabling adversaries to steal the functionality of the source model without a reliable means of verifying ownership. In this paper, we first introduce a novel perspective on trigger set-based watermarking methods from a feature learning perspective. Specifically, we demonstrate that by selecting data exhibiting multiple features, also referred to as $\textit{multi-view data}$, it becomes feasible to effectively defend functionality stealing attacks. Based on this perspective, we introduce a novel watermarking technique based on Multi-view dATa, called MAT, for efficiently embedding watermarks within DNNs. This approach involves constructing a trigger set with multi-view data and incorporating a simple feature-based regularization method for training the source model. We validate our method across various benchmarks and demonstrate its efficacy in defending against model extraction attacks, surpassing relevant baselines by a significant margin.

PALM: Pushing Adaptive Learning Rate Mechanisms for Continual Test-Time Adaptation

Real-world vision models in dynamic environments face rapid shifts in domain distributions, leading to decreased recognition performance. Continual test-time adaptation (CTTA) directly adjusts a pre-trained source discriminative model to these changing domains using test data. A highly effective CTTA method involves applying layer-wise adaptive learning rates, and selectively adapting pre-trained layers. However, it suffers from the poor estimation of domain shift and the inaccuracies arising from the pseudo-labels. In this work, we aim to overcome these limitations by identifying layers through the quantification of model prediction uncertainty without relying on pseudo-labels. We utilize the magnitude of gradients as a metric, calculated by backpropagating the KL divergence between the softmax output and a uniform distribution, to select layers for further adaptation. Subsequently, for the parameters exclusively belonging to these selected layers, with the remaining ones frozen, we evaluate their sensitivity in order to approximate the domain shift, followed by adjusting their learning rates accordingly. Overall, this approach leads to a more robust and stable optimization than prior approaches. We conduct extensive image classification experiments on CIFAR-10C, CIFAR-100C, and ImageNet-C and demonstrate the efficacy of our method against standard benchmarks and prior methods.

Acoustic-to-articulatory inversion for dysarthric speech: Are pre-trained self-supervised representations favorable?

$ $Acoustic-to-articulatory inversion (AAI) involves mapping from the acoustic space to the articulatory space. Signal-processing features like the MFCCs, have been widely used for the AAI task. For subjects with dysarthric speech, AAI is challenging because of an imprecise and indistinct pronunciation. In this work, we perform AAI for dysarthric speech using representations from pre-trained self-supervised learning (SSL) models. We demonstrate the impact of different pre-trained features on this challenging AAI task, at low-resource conditions. In addition, we also condition x-vectors to the extracted SSL features to train a BLSTM network. In the seen case, we experiment with three AAI training schemes (subject-specific, pooled, and fine-tuned). The results, consistent across training schemes, reveal that DeCoAR, in the fine-tuned scheme, achieves a relative improvement of the Pearson Correlation Coefficient (CC) by ${\sim}$1.81\% and ${\sim}$4.56\% for healthy controls and patients, respectively, over MFCCs. In the unseen case, we observe similar average trends for different SSL features. Overall, SSL networks like wav2vec, APC, and DeCoAR, which are trained with feature reconstruction or future timestep prediction tasks, perform well in predicting dysarthric articulatory trajectories.