Large-scale vision-language models (VLMs) embedded with expansive representations and visual concepts have showcased significant potential in image and text understanding. Efficiently adapting VLMs such as CLIP to downstream tasks like few-shot image classification has garnered growing attention, with prompt learning emerging as a representative approach. However, most existing prompt-based adaptation methods, which rely solely on coarse-grained textual prompts, suffer from limited performance and interpretability when handling domain tasks that require specific knowledge. This results in a failure to satisfy the stringent trustworthiness requirements of Explainable Artificial Intelligence (XAI) in high-risk scenarios like healthcare. To address this issue, we propose a Knowledge-Enhanced Explainable Prompting (KEEP) framework that leverages fine-grained domain-specific knowledge to enhance the adaptation process of VLMs across various domains and image modalities. By incorporating retrieval augmented generation and domain foundation models, our framework can provide more reliable image-wise knowledge for prompt learning in various domains, alleviating the lack of fine-grained annotations, while offering both visual and textual explanations. Extensive experiments and explainability analyses conducted on eight datasets of different domains and image modalities demonstrate that our method simultaneously achieves superior performance and interpretability, highlighting the effectiveness of the collaboration between foundation models and XAI.

Temporal Graph Neural Network (TGNN) has attracted much research attention because it can capture the dynamic nature of complex networks. However, existing solutions suffer from redundant computation overhead and excessive off-chip communications for TGNN inference because they often rely on redundant graph sampling and repeatedly fetching the features and vertex memory. This paper proposes a redundancy-free accelerator, RTGA, for high-performance TGNN inference. Specifically, RTGA proposes a redundancy-aware execution approach with temporal tree into a novel accelerator design to effectively eliminate unnecessary data processing for fewer redundant computations and off-chip communications and also designs a temporal-aware data caching method to improve data locality for TGNN. We have implemented and evaluated RTGA on a Xilinx Alveo U280 FPGA card. Compared with cutting-edge software solutions (i.e., TGN and TGL) and hardware solutions (i.e., BlockGNN and FlowGNN), RTGA improves the performance of TGNN inference by an average of 473.2x, 87.4x, 8.2x, and 6.9x and saves energy by 542.8x, 102.2x, 9.4x, and 8.3x, respectively.

Post-hoc explainability methods such as Grad-CAM are popular because they do not influence the performance of a trained model. However, they mainly reveal ”where” a model looks at for a given input, fail to explain ”what” the model looks for (e.g., what is important to classify a bird image to a Scott Oriole?). Existing part-prototype networks leverage part-prototypes (e.g., characteristic Scott Oriole’s wing and head) to answer both ”where" and ”what", but often under-perform their black box counterparts in the accuracy. Therefore, a natural question is: can one construct a network that answers both ”where” and ”what" in a post-hoc manner to guarantee the model’s performance? To this end, we propose the first post-hoc part-prototype network via decomposing the classification head of a trained model into a set of interpretable part-prototypes. Concretely, we propose an unsupervised prototype discovery and refining strategy to obtain prototypes that can precisely reconstruct the classification head, yet being interpretable. Besides guaranteeing the performance, we show that our network offers more faithful explanations qualitatively and yields even better part-prototypes quantitatively than prior part-prototype networks.

Current methods for 3D hand pose estimation fail to generalize well to in-the-wild new scenarios due to varying camera viewpoints, self-occlusions, and complex environments. To address this problem, we propose CycleHand to improve the generalization ability of the model in a self-supervised manner. Our motivation is based on an observation: if one globally rotates the whole hand and reversely rotates it back, the estimated 3D poses of fingers should keep consistent before and after the rotation because the wrist-relative hand poses stay unchanged during global 3D rotation. Hence, we propose arbitrary-rotation self-supervised consistency learning to improve the model's robustness for varying viewpoints. Another innovation of CycleHand is that we propose a high-fidelity texture map to render the photorealistic rotated hand with different lighting conditions, backgrounds, and skin tones to further enhance the effectiveness of our self-supervised task. To reduce the potential negative effects brought by the domain shift of synthetic images, we use the idea of contrastive learning to learn a synthetic-real consistent feature extractor in extracting domain-irrelevant hand representations. Experiments show that CycleHand can largely improve the hand pose estimation performance in both canonical datasets and real-world applications.

Self-attention networks have shown remarkable progress in computer vision tasks such as image classification. The main benefit of the self-attention mechanism is the ability to capture long-range feature interactions in attention-maps. However, the computation of attention-maps requires a learnable key, query, and positional encoding, whose usage is often not intuitive and computationally expensive. To mitigate this problem, we propose a novel self-attention module with explicitly modeled attention-maps using only a single learnable parameter for low computational overhead. The design of explicitly modeled attention-maps using geometric prior is based on the observation that the spatial context for a given pixel within an image is mostly dominated by its neighbors, while more distant pixels have a minor contribution. Concretely, the attention-maps are parametrized via simple functions (e.g., Gaussian kernel) with a learnable radius, which is modeled independently of the input content. Our evaluation shows that our method achieves an accuracy improvement of up to 2.2% over the ResNet-baselines in ImageNet ILSVRC and outperforms other self-attention methods such as AA-ResNet152 in accuracy by 0.9% with 6.4% fewer parameters and 6.7% fewer GFLOPs. This result empirically indicates the value of incorporating geometric prior into self-attention mechanism when applied in image classification.