Attn-Adapter: Attention Is All You Need for Online Few-shot Learner of Vision-Language Model

Contrastive vision-language models excel in zero-shot image recognition but face challenges in few-shot scenarios due to computationally intensive offline fine-tuning using prompt learning, which risks overfitting. To overcome these limitations, we propose Attn-Adapter, a novel online few-shot learning framework that enhances CLIP's adaptability via a dual attention mechanism. Our design incorporates dataset-specific information through two components: the Memory Attn-Adapter, which refines category embeddings using support examples, and the Local-Global Attn-Adapter, which enriches image embeddings by integrating local and global features. This architecture enables dynamic adaptation from a few labeled samples without retraining the base model. Attn-Adapter outperforms state-of-the-art methods in cross-category and cross-dataset generalization, maintaining efficient inference and scaling across CLIP backbones.

Adaptive Cache Enhancement for Test-Time Adaptation of Vision-Language Models

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 this challenge by enabling online optimization of VLMs during inference, eliminating the need for annotated data. Cache-based TTA methods exploit historical knowledge by maintaining a dynamic memory cache of low-entropy or high-confidence samples, promoting efficient adaptation to out-of-distribution data. Nevertheless, these methods face two critical challenges: (1) unreliable confidence metrics under significant distribution shifts, resulting in error accumulation within the cache and degraded adaptation performance; and (2) rigid decision boundaries that fail to accommodate substantial distributional variations, leading to suboptimal predictions. To overcome these limitations, we introduce the Adaptive Cache Enhancement (ACE) framework, which constructs a robust cache by selectively storing high-confidence or low-entropy image embeddings per class, guided by dynamic, class-specific thresholds initialized from zero-shot statistics and iteratively refined using an exponential moving average and exploration-augmented updates. This approach enables adaptive, class-wise decision boundaries, ensuring robust and accurate predictions across diverse visual distributions. Extensive experiments on 15 diverse benchmark datasets demonstrate that ACE achieves state-of-the-art performance, delivering superior robustness and generalization compared to existing TTA methods in challenging out-of-distribution scenarios.

Accelerating Conditional Prompt Learning via Masked Image Modeling for Vision-Language Models

Vision-language models (VLMs) like CLIP excel in zero-shot learning but often require resource-intensive training to adapt to new tasks. Prompt learning techniques, such as CoOp and CoCoOp, offer efficient adaptation but tend to overfit to known classes, limiting generalization to unseen categories. We introduce ProMIM, a plug-and-play framework that enhances conditional prompt learning by integrating masked image modeling (MIM) into existing VLM pipelines. ProMIM leverages a simple yet effective masking strategy to generate robust, instance-conditioned prompts, seamlessly augmenting methods like CoOp and CoCoOp without altering their core architectures. By masking only visible image patches and using these representations to guide prompt generation, ProMIM improves feature robustness and mitigates overfitting, all while introducing negligible additional computational cost. Extensive experiments across zero-shot and few-shot classification tasks demonstrate that ProMIM consistently boosts generalization performance when plugged into existing approaches, providing a practical, lightweight solution for real-world vision-language applications.

Multi-scale Feature Enhancement in Multi-task Learning for Medical Image Analysis

Traditional deep learning methods in medical imaging often focus solely on segmentation or classification, limiting their ability to leverage shared information. Multi-task learning (MTL) addresses this by combining both tasks through shared representations but often struggles to balance local spatial features for segmentation and global semantic features for classification, leading to suboptimal performance. In this paper, we propose a simple yet effective UNet-based MTL model, where features extracted by the encoder are used to predict classification labels, while the decoder produces the segmentation mask. The model introduces an advanced encoder incorporating a novel ResFormer block that integrates local context from convolutional feature extraction with long-range dependencies modeled by the Transformer. This design captures broader contextual relationships and fine-grained details, improving classification and segmentation accuracy. To enhance classification performance, multi-scale features from different encoder levels are combined to leverage the hierarchical representation of the input image. For segmentation, the features passed to the decoder via skip connections are refined using a novel dilated feature enhancement (DFE) module, which captures information at different scales through three parallel convolution branches with varying dilation rates. This allows the decoder to detect lesions of varying sizes with greater accuracy. Experimental results across multiple medical datasets confirm the superior performance of our model in both segmentation and classification tasks, compared to state-of-the-art single-task and multi-task learning methods.