Applying pre-trained models to assist point cloud understanding has recently become a mainstream paradigm in 3D perception. However, existing application strategies are straightforward, utilizing only the final output of the pre-trained model for various task heads. It neglects the rich complementary information in the intermediate layer, thereby failing to fully unlock the potential of pre-trained models. To overcome this limitation, we propose an orthogonal solution: Point Mamba Adapter (PMA), which constructs an ordered feature sequence from all layers of the pre-trained model and leverages Mamba to fuse all complementary semantics, thereby promoting comprehensive point cloud understanding. Constructing this ordered sequence is non-trivial due to the inherent isotropy of 3D space. Therefore, we further propose a geometry-constrained gate prompt generator (G2PG) shared across different layers, which applies shared geometric constraints to the output gates of the Mamba and dynamically optimizes the spatial order, thus enabling more effective integration of multi-layer information. Extensive experiments conducted on challenging point cloud datasets across various tasks demonstrate that our PMA elevates the capability for point cloud understanding to a new level by fusing diverse complementary intermediate features. Code is available at https://github.com/zyh16143998882/PMA.

Question-answering (QA) is a natural approach for humans to understand a piece of music audio. However, for machines, accessing a large-scale dataset covering diverse aspects of music is crucial, yet challenging, due to the scarcity of publicly available music data of this type. This paper introduces MQAD, a music QA dataset built on the Million Song Dataset (MSD), encompassing a rich array of musical features - including beat, chord, key, structure, instrument, and genre — across 270,000 tracks, featuring nearly 3 million diverse questions and captions. MQAD distinguishes itself by offering detailed time-varying musical information such as chords and sections, enabling exploration into the inherent structure of music within a song. To compile MQAD, our methodology leverages specialized Music Information Retrieval (MIR) models to extract higher-level musical features and Large Language Models (LLMs) to generate natural language QA pairs. Then, we leverage a multimodal LLM that integrates the LLaMA2 and Whisper architectures, along with novel subjective metrics to assess the performance of MQAD. In experiments, our model trained on MQAD demonstrates advancements over conventional music audio captioning approaches. The dataset and codes are at https://github.com/oyzh888/MQAD.

Recent advances in diffusion-based Large Restoration Models (LRMs) have significantly improved photo-realistic image restoration by leveraging the internal knowledge embedded within model weights. However, existing LRMs often suffer from the hallucination dilemma, i.e., producing incorrect contents or textures when dealing with severe degradations, due to their heavy reliance on limited internal knowledge. In this paper, we propose an orthogonal solution called the Retrieval-augmented Framework for Image Restoration (ReFIR), which incorporates retrieved images as external knowledge to extend the knowledge boundary of existing LRMs in generating details faithful to the original scene. Specifically, we first introduce the nearest neighbor lookup to retrieve content-relevant high-quality images as reference, after which we propose the cross-image injection to modify existing LRMs to utilize high-quality textures from retrieved images. Thanks to the additional external knowledge, our ReFIR can well handle the hallucination challenge and facilitate faithfully results. Extensive experiments demonstrate that ReFIR can achieve not only high-fidelity but also realistic restoration results. Importantly, our ReFIR requires no training and is adaptable to various LRMs.

The pre-trained point cloud model based on Masked Point Modeling (MPM) has exhibited substantial improvements across various tasks. However, these models heavily rely on the Transformer, leading to quadratic complexity and limited decoder, hindering their practice application. To address this limitation, we first conduct a comprehensive analysis of existing Transformer-based MPM, emphasizing the idea that redundancy reduction is crucial for point cloud analysis. To this end, we propose a Locally constrained Compact point cloud Model (LCM) consisting of a locally constrained compact encoder and a locally constrained Mamba-based decoder. Our encoder replaces self-attention with our local aggregation layers to achieve an elegant balance between performance and efficiency. Considering the varying information density between masked and unmasked patches in the decoder inputs of MPM, we introduce a locally constrained Mamba-based decoder. This decoder ensures linear complexity while maximizing the perception of point cloud geometry information from unmasked patches with higher information density. Extensive experimental results show that our compact model significantly surpasses existing Transformer-based models in both performance and efficiency, especially our LCM-based Point-MAE model, compared to the Transformer-based model, achieved an improvement of 1.84%, 0.67%, and 0.60% in performance on the three variants of ScanObjectNN while reducing parameters by 88% and computation by 73%. The code is available at https://github.com/zyh16143998882/LCM.

Dropout has been widely used in fully connected networks but becomes less effective for convolutional neural networks (CNNs), since the spatially correlated features still allow dropped information to flow through the network. To make dropout more practical for CNNs, structured dropout methods have been recently proposed by dropping regions with fixed shapes and random positions, which nonetheless may lead to unexpected discarding of information. To address this problem, in this paper, we propose a novel dropout variant based on attention information named AttentionDrop that drops features adaptively. Specifically, it precisely localizes masks that have irregular shapes according to the values of activation units. In addition, the use of soft values in adaptive masks lowers the risk of a complete loss of indispensable information. Experimental results demonstrate the effectiveness of our AttentionDrop on public datasets for image classification.