Selective Transformer for Hyperspectral Image Classification

Transformer has achieved satisfactory results in the field of hyperspectral image (HSI) classification. However, existing Transformer models face two key challenges when dealing with HSI scenes characterized by diverse land cover types and rich spectral information: (1) fixed receptive field representation overlooks effective contextual information; (2) redundant self-attention feature representation. To address these limitations, we propose a novel Selective Transformer (SFormer) for HSI classification. The SFormer is designed to dynamically select receptive fields for capturing both spatial and spectral contextual information, while mitigating the impact of redundant data by prioritizing the most relevant features. This enables a highly accurate classification of the land covers of the HSI. Specifically, a Kernel Selective Transformer Block (KSTB) is first utilized to dynamically select an appropriate receptive field range to effectively extract spatial-spectral features. Furthermore, to capture the most crucial tokens, a Token Selective Transformer Block (TSTB) is introduced, which selects the most relevant tokens based on the ranking of attention scores for each query. Extensive experiments on four benchmark HSI datasets demonstrate that the proposed SFormer outperforms the state-of-the-art HSI classification models. The codes will be released.

VHASR: A Multimodal Speech Recognition System With Vision Hotwords

The image-based multimodal automatic speech recognition (ASR) model enhances speech recognition performance by incorporating audio-related image. However, some works suggest that introducing image information to model does not help improving ASR performance. In this paper, we propose a novel approach effectively utilizing audio-related image information and set up VHASR, a multimodal speech recognition system that uses vision as hotwords to strengthen the model's speech recognition capability. Our system utilizes a dual-stream architecture, which firstly transcribes the text on the two streams separately, and then combines the outputs. We evaluate the proposed model on four datasets: Flickr8k, ADE20k, COCO, and OpenImages. The experimental results show that VHASR can effectively utilize key information in images to enhance the model's speech recognition ability. Its performance not only surpasses unimodal ASR, but also achieves SOTA among existing image-based multimodal ASR.

Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models

Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and Parameter-Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting LLMs to downstream tasks. ICL typically constructs a few-shot learning scenario, either manually or by setting up a Retrieval-Augmented Generation (RAG) system, helping models quickly grasp domain knowledge or question-answering patterns without changing model parameters. However, this approach involves trade-offs, such as slower inference speed and increased space occupancy. PEFT assists the model in adapting to tasks through minimal parameter modifications, but the training process still demands high hardware requirements, even with a small number of parameters involved. To address these challenges, we propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning, maintaining low inference costs. RTD constructs a reference datastore from the provided training examples and optimizes the LLM's final vocabulary distribution by flexibly selecting suitable references based on the input, resulting in more trustable responses and enabling the model to adapt to downstream tasks at a low cost. Experimental evaluations on various LLMs using different benchmarks demonstrate that RTD establishes a new paradigm for augmenting models to downstream tasks. Furthermore, our method exhibits strong orthogonality with traditional methods, allowing for concurrent usage.

A Coin Has Two Sides: A Novel Detector-Corrector Framework for Chinese Spelling Correction

Chinese Spelling Correction (CSC) stands as a foundational Natural Language Processing (NLP) task, which primarily focuses on the correction of erroneous characters in Chinese texts. Certain existing methodologies opt to disentangle the error correction process, employing an additional error detector to pinpoint error positions. However, owing to the inherent performance limitations of error detector, precision and recall are like two sides of the coin which can not be both facing up simultaneously. Furthermore, it is also worth investigating how the error position information can be judiciously applied to assist the error correction. In this paper, we introduce a novel approach based on error detector-corrector framework. Our detector is designed to yield two error detection results, each characterized by high precision and recall. Given that the occurrence of errors is context-dependent and detection outcomes may be less precise, we incorporate the error detection results into the CSC task using an innovative feature fusion strategy and a selective masking strategy. Empirical experiments conducted on mainstream CSC datasets substantiate the efficacy of our proposed method.

Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration

The limitations of task-specific and general image restoration methods for specific degradation have prompted the development of all-in-one image restoration techniques. However, the diversity of patterns among multiple degradation, along with the significant uncertainties in mapping between degraded images of different severities and their corresponding undistorted versions, pose significant challenges to the all-in-one restoration tasks. To address these challenges, we propose Perceive-IR, an all-in-one image restorer designed to achieve fine-grained quality control that enables restored images to more closely resemble their undistorted counterparts, regardless of the type or severity of degradation. Specifically, Perceive-IR contains two stages: (1) prompt learning stage and (2) restoration stage. In the prompt learning stage, we leverage prompt learning to acquire a fine-grained quality perceiver capable of distinguishing three-tier quality levels by constraining the prompt-image similarity in the CLIP perception space. Subsequently, this quality perceiver and difficulty-adaptive perceptual loss are integrated as a quality-aware learning strategy to realize fine-grained quality control in restoration stage. For the restoration stage, a semantic guidance module (SGM) and compact feature extraction (CFE) are proposed to further promote the restoration process by utilizing the robust semantic information from the pre-trained large scale vision models and distinguishing degradation-specific features. Extensive experiments demonstrate that our Perceive-IR outperforms state-of-the-art methods in all-in-one image restoration tasks and exhibit superior generalization ability when dealing with unseen tasks.

SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models

Deep model training on extensive datasets is increasingly becoming cost-prohibitive, prompting the widespread adoption of deep model fusion techniques to leverage knowledge from pre-existing models. From simple weight averaging to more sophisticated methods like AdaMerging, model fusion effectively improves model performance and accelerates the development of new models. However, potential interference between parameters of individual models and the lack of interpretability in the fusion progress remain significant challenges. Existing methods often try to resolve the parameter interference issue by evaluating attributes of parameters, such as their magnitude or sign, or by parameter pruning. In this study, we begin by examining the fine-tuning of linear layers through the lens of subspace analysis and explicitly define parameter interference as an optimization problem to shed light on this subject. Subsequently, we introduce an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction, which allows for the upscaling of source models into an MoE model without extra data or further training. Our approach relies on the observation that fine-tuning mostly keeps the important parts from the pre-training, but it uses less significant or unused areas to adapt to new tasks. Also, the issue of parameter interference, which is intrinsically intractable in the original parameter space, can be managed by expanding the dimensions. We conduct extensive experiments across diverse scenarios, such as image classification and text generalization tasks, using full fine-tuning and LoRA fine-tuning, and we apply our method to large language models (CLIP models, Flan-T5 models, and Mistral-7B models), highlighting the adaptability and scalability of SMILE. Code is available at https://github.com/tanganke/fusion_bench

Venturing into Uncharted Waters: The Navigation Compass from Transformer to Mamba

Transformer, a deep neural network architecture, has long dominated the field of natural language processing and beyond. Nevertheless, the recent introduction of Mamba challenges its supremacy, sparks considerable interest among researchers, and gives rise to a series of Mamba-based models that have exhibited notable potential. This survey paper orchestrates a comprehensive discussion, diving into essential research dimensions, covering: (i) the functioning of the Mamba mechanism and its foundation on the principles of structured state space models; (ii) the proposed improvements and the integration of Mamba with various networks, exploring its potential as a substitute for Transformers; (iii) the combination of Transformers and Mamba to compensate for each other's shortcomings. We have also made efforts to interpret Mamba and Transformer in the framework of kernel functions, allowing for a comparison of their mathematical nature within a unified context. Our paper encompasses the vast majority of improvements related to Mamba to date.

HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model

Foundation models (FMs) are revolutionizing the analysis and understanding of remote sensing (RS) scenes, including aerial RGB, multispectral, and SAR images. However, hyperspectral images (HSIs), which are rich in spectral information, have not seen much application of FMs, with existing methods often restricted to specific tasks and lacking generality. To fill this gap, we introduce HyperSIGMA, a vision transformer-based foundation model for HSI interpretation, scalable to over a billion parameters. To tackle the spectral and spatial redundancy challenges in HSIs, we introduce a novel sparse sampling attention (SSA) mechanism, which effectively promotes the learning of diverse contextual features and serves as the basic block of HyperSIGMA. HyperSIGMA integrates spatial and spectral features using a specially designed spectral enhancement module. In addition, we construct a large-scale hyperspectral dataset, HyperGlobal-450K, for pre-training, which contains about 450K hyperspectral images, significantly surpassing existing datasets in scale. Extensive experiments on various high-level and low-level HSI tasks demonstrate HyperSIGMA's versatility and superior representational capability compared to current state-of-the-art methods. Moreover, HyperSIGMA shows significant advantages in scalability, robustness, cross-modal transferring capability, and real-world applicability.

MGIMM: Multi-Granularity Instruction Multimodal Model for Attribute-Guided Remote Sensing Image Detailed Description

Recently, large multimodal models have built a bridge from visual to textual information, but they tend to underperform in remote sensing scenarios. This underperformance is due to the complex distribution of objects and the significant scale differences among targets in remote sensing images, leading to visual ambiguities and insufficient descriptions by these multimodal models. Moreover, the lack of multimodal fine-tuning data specific to the remote sensing field makes it challenging for the model's behavior to align with user queries. To address these issues, this paper proposes an attribute-guided \textbf{Multi-Granularity Instruction Multimodal Model (MGIMM)} for remote sensing image detailed description. MGIMM guides the multimodal model to learn the consistency between visual regions and corresponding text attributes (such as object names, colors, and shapes) through region-level instruction tuning. Then, with the multimodal model aligned on region-attribute, guided by multi-grain visual features, MGIMM fully perceives both region-level and global image information, utilizing large language models for comprehensive descriptions of remote sensing images. Due to the lack of a standard benchmark for generating detailed descriptions of remote sensing images, we construct a dataset featuring 38,320 region-attribute pairs and 23,463 image-detailed description pairs. Compared with various advanced methods on this dataset, the results demonstrate the effectiveness of MGIMM's region-attribute guided learning approach. Code can be available at https://github.com/yangcong356/MGIMM.git

${M^2D}$NeRF: Multi-Modal Decomposition NeRF with 3D Feature Fields

Neural fields (NeRF) have emerged as a promising approach for representing continuous 3D scenes. Nevertheless, the lack of semantic encoding in NeRFs poses a significant challenge for scene decomposition. To address this challenge, we present a single model, Multi-Modal Decomposition NeRF (${M^2D}$NeRF), that is capable of both text-based and visual patch-based edits. Specifically, we use multi-modal feature distillation to integrate teacher features from pretrained visual and language models into 3D semantic feature volumes, thereby facilitating consistent 3D editing. To enforce consistency between the visual and language features in our 3D feature volumes, we introduce a multi-modal similarity constraint. We also introduce a patch-based joint contrastive loss that helps to encourage object-regions to coalesce in the 3D feature space, resulting in more precise boundaries. Experiments on various real-world scenes show superior performance in 3D scene decomposition tasks compared to prior NeRF-based methods.